SplatCtrl: Perception-Action Coupling via Gaussian Scene Representations and Reactive Robot Control

Authors: Siddarth Jain, Ho Jin Choi

Abstract: Robotic manipulators excel in structured environments but face substantial challenges in unstructured and dynamic settings. This paper presents SplatCtrl, a unified framework for real-time scene reconstruction and reactive robot motion generation to enable collision-free robotic arm control in previously unseen and continuously changing environments. Building on 3D Gaussian Splatting (3D-GS), we i… ▽ More Robotic manipulators excel in structured environments but face substantial challenges in unstructured and dynamic settings. This paper presents SplatCtrl, a unified framework for real-time scene reconstruction and reactive robot motion generation to enable collision-free robotic arm control in previously unseen and continuously changing environments. Building on 3D Gaussian Splatting (3D-GS), we introduce a hybrid voxel-based filtering and dynamic Gaussian relocation strategy that supports efficient scene reconstruction from RGB-D streams while accommodating environmental changes. For safe and reactive control, we further propose a method for deriving continuous signed distance functions from isotropic Gaussians, providing stable and differentiable collision probability estimates that bridge classical distance fields with the modern implicit representation. These continuous distance metrics are incorporated into control barrier functions, resulting in a unified perception-action coupling framework that supports smooth and reliable real-time motion generation in response to scene changes. Experimental validation in simulation, on physical robot, and within shared human-robot workspace demonstrates the framework's effectiveness, achieving integrated scene reconstruction and reactive control in uncertain, and dynamic environments. △ Less

Submitted 9 July, 2026; originally announced July 2026.

Understanding Axes of Difficulty For Long Context Tasks Via PredicateLongBench

Authors: Siddhartha Jain, Ameya Velingker

Abstract: Large language models (LLMs) have demonstrated rapidly improving long-context capabilities, prompting a wave of benchmarks designed to evaluate them. However, existing long-context evaluations - from Needle-in-a-Haystack (NIAH) tests to more recent multi-hop reasoning and summarization tasks - predominantly measure average-case performance, and many are either saturated or lack robustness. Notably… ▽ More Large language models (LLMs) have demonstrated rapidly improving long-context capabilities, prompting a wave of benchmarks designed to evaluate them. However, existing long-context evaluations - from Needle-in-a-Haystack (NIAH) tests to more recent multi-hop reasoning and summarization tasks - predominantly measure average-case performance, and many are either saturated or lack robustness. Notably absent is a systematic way to probe how models perform as we scale up the difficulty of tasks along various axes. We address this gap by proposing PredicateLongBench, a benchmark that stress-tests long-context reasoning by asking models to identify the longest contiguous subsequence of words in a long input that satisfies given predicates/constraints (e.g., lexicographic ordering), drawn from a broader predicate class. The central innovation of our benchmark is the identification and systematic exploration of multiple different axes of difficulty which test multiple aspects of long context understanding. We provide two complementary generation pipelines - a fully synthetic setup using random word-like strings, and a real-world setup that samples words from natural documents while preserving their distributional properties. We find that frontier models struggle to perform well as we scale up the difficulty of tasks along our axes, demonstrating the utility of our benchmark in understanding the limitations of current long-context capabilities. Furthermore, the tasks in PredicateLongBench, though challenging, are conceptually simple and do not require LLM-based generations or judges. △ Less

Submitted 9 July, 2026; originally announced July 2026.

FurnitureVLA: Learning Long-Horizon Bimanual Furniture Assembly with Vision-Language-Action Model

Authors: Chenyang Ma, Yue Yang, Radu Corcodel, Siddarth Jain, Andrew Wu, Chiori Hori, Diego Romeres

Abstract: Current work on robot furniture assembly mostly focuses on toy-scale settings or single-arm manipulation. We introduce FurnitureVLA, the first systematic study of real-scale bimanual furniture assembly using Vision-Language-Action models (VLAs). We formalize the task, develop a scalable simulation pipeline for expert data generation and evaluation, and build a VR teleoperation system for single-op… ▽ More Current work on robot furniture assembly mostly focuses on toy-scale settings or single-arm manipulation. We introduce FurnitureVLA, the first systematic study of real-scale bimanual furniture assembly using Vision-Language-Action models (VLAs). We formalize the task, develop a scalable simulation pipeline for expert data generation and evaluation, and build a VR teleoperation system for single-operator bimanual control to collect high-quality real-world demonstrations. To address extreme long-horizon assembly with up to 7 subtasks and 1550 control steps, we propose a progress-enhanced VLA, finetuned on semantically grounded subtasks, that jointly predicts actions and a continuous progress signal, enabling automatic subtask transitions and reducing compounding errors during inference. We further study perception and control design factors that critically affect precision in real-scale assembly. FurnitureVLA improves average simulation success from 48% to 80% compared to baselines across three furniture types, with an additional 21% gain from our design factor study. We validate on a real Kinova Gen3 platform with only 16% drop on the hardest task. △ Less

Submitted 1 July, 2026; originally announced July 2026.

Coachable agents for interactive gameplay

Authors: Roberto Capobianco, Harm van Seijen, Nolan D. Bard, Neil Burch, Fatima Davelouis, Josh Davidson, Alisa Devlic, Yunshu Du, Ishan Durugkar, Siddhant Gangapurwala, Daniel Hernandez, G. Zacharias Holland, Sahil Jain, Kenta Kawamoto, Raksha Kumaraswamy, Patrick MacAlpine, Dustin R. Morrill, Declan Oller, Francesco Riccio, Akanksha Saran, Craig Sherstan, Kaushik Subramanian, Thomas J. Walsh, Samuel Barrett, Kizza N. Frisbee , et al. (16 additional authors not shown)

Abstract: Reinforcement learning has proven to be a valuable tool in the creation of advanced AI and robotic systems, contributing to everything from game playing to robotics to foundation models. Through trial-and-error, these AI systems typically learn one, near-optimal behavior to solve their tasks. However, there are many use cases in which one would like to assert some level of control, preferably in r… ▽ More Reinforcement learning has proven to be a valuable tool in the creation of advanced AI and robotic systems, contributing to everything from game playing to robotics to foundation models. Through trial-and-error, these AI systems typically learn one, near-optimal behavior to solve their tasks. However, there are many use cases in which one would like to assert some level of control, preferably in real time, over how the task is solved. We refer to these modifications of a core task as styles. We combine universal value function approximators (UVFAs) with carefully selected training scenarios, learning algorithms, and data augmentation to create a framework for coaching agents that exhibit styles in complex domains. We demonstrate the framework's application in the AAA video games Horizon Forbidden West and Gran Turismo, and in an open-source humanoid test domain. Despite the different nature of the domains -- car racing, stylized game combat, and humanoid walking -- each agent shows strong coherence to the style requests while still satisfying the main task in its domain. Importantly, the techniques outlined in this paper allow an end user to choose the final behavior at run time, giving them flexible control over the final executed performance. △ Less

Submitted 1 July, 2026; originally announced July 2026.

Learning Dexterous Manipulation Using Contact Wrench Guidance From Human Demonstration

Authors: Xinghao Zhu, Zixi Liu, Shalin Jain, Chenran Li, Milad Noori, Huihua Zhao, John Welsh, Michael Andres Lin, Wei Liu, Tingwu Wang, Xingye Da, Zhengyi Luo, Vishal Kulkarni, Naema Bhatti, Yuke Zhu, Linxi Fan, Bowen Wen, Danfei Xu, Soha Pouya, Yan Chang

Abstract: Dexterous robot manipulation can benefit from the abundance of human demonstrations, but transferring such demonstrations to robot policies remains challenging. We present Contact Wrench Guidance from Human Demonstration in Robotic Dexterous Manipulation (CHORD), a framework for long-horizon manipulation of rigid and articulated objects with reinforcement learning. The key idea is object-centric c… ▽ More Dexterous robot manipulation can benefit from the abundance of human demonstrations, but transferring such demonstrations to robot policies remains challenging. We present Contact Wrench Guidance from Human Demonstration in Robotic Dexterous Manipulation (CHORD), a framework for long-horizon manipulation of rigid and articulated objects with reinforcement learning. The key idea is object-centric contact wrench space guidance: we represent human and robot motions by the forces and torques they can induce on the object, enabling similarity to be measured by the induced instantaneous motions. This guidance makes reinforcement learning more scalable for contact-rich dexterous manipulation. We further introduce a large-scale simulation benchmark with 4,739 bimanual dexterous manipulation tasks, constructed from motion-capture datasets and reconstructed in-house videos. Evaluated on 1,831 benchmark tasks, CHORD achieves an average success rate of 82.12%, demonstrating strong scalability. CHORD also generalizes to whole-body manipulation from hand-only and third-person demonstrations, achieving a 90.77% success rate, and the learned policies transfer to the real world in both open-loop and closed-loop settings. △ Less

Submitted 22 June, 2026; originally announced July 2026.

AC3S: Adaptive Conditioning for 3D-Aware Synthetic Data Generation

Authors: Eric Ji, Qiran Hu, Wufei Ma, Sarthak Jain, Yingying Li, Minh N. Do, Yaoyao Liu

Abstract: Synthetic data generation has emerged as a powerful tool for improving data scalability in computer vision. Recent diffusion-based pipelines have demonstrated strong photorealism. However, how to enforce precise 3D structure and pose consistency in generated images remains challenging. Existing methods leverage visual prompts such as edge maps to guide diffusion models, but often suffer from over-… ▽ More Synthetic data generation has emerged as a powerful tool for improving data scalability in computer vision. Recent diffusion-based pipelines have demonstrated strong photorealism. However, how to enforce precise 3D structure and pose consistency in generated images remains challenging. Existing methods leverage visual prompts such as edge maps to guide diffusion models, but often suffer from over-conditioning artifacts that degrade image realism and limit dataset quality. In this paper, we present a diffusion-based image generation framework that enforces 3D structural alignment while preserving photorealism through adaptive conditioning. Our framework, Adaptive Conditioning for 3D-Aware Synthetic Data Generation (AC3S), introduces a self-supervised visual prompt modulator that dynamically adjusts the strength of ControlNet conditioning, preventing over-conditioning and enabling the diffusion model to retain its generative expressiveness. To further enhance diversity and semantic consistency, we develop a multi-agent vision language model framework that composes detailed and 3D-aware prompts aligned with the underlying geometric structure. Together, these components enable the scalable generation of high-quality synthetic datasets with accurate 2D and 3D annotations. Extensive experiments demonstrate that our method significantly improves image quality and downstream utility. △ Less

Submitted 30 June, 2026; originally announced June 2026.

A Multi Center Breast FNAC Whole-Slide Cytology Dataset for AI-Assisted Patch-Wise Classification Using C1 to C5 Reporting Categories

Authors: Garima Jain, Abhijeet Patil, Surabhi Jain, Sanghamitra Pati, Amit Sethi, Sandeep Mathur, Pulkit Verma, Nishi Halduniya, Jatin Kashyap, Sharat Kumar, Simmi Kharb, Sunita Singh, Sucheta Devi Khuraijam, Sushma Khuraijam, Ratan Konjengbam, Arvind Kumar, Deepali Tirkey, Saurav Banerjee, Shivani Kalhan, Rakesh Kumar Gupta, Ranjana Solanki, Deepika Hemranjani, Shashank Nath Singh, Uma Handa, Manveen Kaur , et al. (14 additional authors not shown)

Abstract: We present a multi center breast fine needle aspiration cytology (FNAC) dataset designed for patch wise classification using C1 to C5 reporting labels. The prospective dataset includes 321 patients and 470 whole-slide images (WSIs) collected from participating tertiary medical centers in India between May 2023 and March 2026. Slides were stained using Papanicolaou (190 WSIs) or MayGrunwald Giemsa… ▽ More We present a multi center breast fine needle aspiration cytology (FNAC) dataset designed for patch wise classification using C1 to C5 reporting labels. The prospective dataset includes 321 patients and 470 whole-slide images (WSIs) collected from participating tertiary medical centers in India between May 2023 and March 2026. Slides were stained using Papanicolaou (190 WSIs) or MayGrunwald Giemsa (280 WSIs), scanned on a Hamamatsu NanoZoomer S360 at 40X magnification and 0.25 microns per pixel, and stored directly in NDPI format. Across the 470 WSIs, 446 WSIs contain annotated patch regions, yielding 7,398 PNG image patches with expert-verified C1 to C5 labels. The release includes NDPI WSIs, WSI-level GeoJSON annotation files, extracted patch images, deidentified metadata, a data dictionary, a validation summary, a manifest linking WSIs to Zenodo records, and code for dataset inspection and reuse. The complete dataset is approximately 950 GB and is available through Zenodo. △ Less

Submitted 29 June, 2026; originally announced June 2026.

IMCBench: A benchmark for multimodal LLMs in Image-grounded Medical Conversations

Authors: Maria Xenochristou, Ashutosh Joshi, Korosh Vatanparvar, Mohammad Abuzar Hashemi, Prasad Kasu, Deepak Bansal, Anchal Nema, Nivedita Wadhwa, Prashams S Jain, Rebecca Abraham, Will Kimbrough, Dilek Hakkani-Tur, Wilko Schulz-Mahlendorf

Abstract: Recent advances in large language models and vision-language models have enabled reasoning over multimodal data, offering opportunities for clinical applications such as decision support and triaging. However, existing medical AI benchmarks are fragmented: some support multi-turn dialogues but lack images, while others provide multimodal inputs but focus on single-turn QA tasks. To address this ga… ▽ More Recent advances in large language models and vision-language models have enabled reasoning over multimodal data, offering opportunities for clinical applications such as decision support and triaging. However, existing medical AI benchmarks are fragmented: some support multi-turn dialogues but lack images, while others provide multimodal inputs but focus on single-turn QA tasks. To address this gap, we introduce IMCBench, an image-grounded, multi-turn medical conversation benchmark that pairs real, publicly available clinical images with synthetic patient profiles to simulate realistic patient-clinician interactions. Each conversation is evaluated across three clinical dimensions: safety, accuracy, and appropriate use of uncertainty in diagnosis. We benchmark eight multimodal frontier models across four model families (Claude, GPT, Nova, and Llama), scoring each on a 1-5 scale using LLM-as-Jury scoring calibrated against expert clinician annotations. Our results show that Claude Opus 4.6 achieves the highest overall score (3.61), followed by Claude Sonnet 4.6 (3.30) and GPT-5.2 (3.29), though no model dominates all dimensions and safety degrades for both malignant and rare conditions ($Δ$ = -0.27 each). Ablation studies further reveal that both visual input and EHR context contribute to safe guidance (safety drops of 0.18 and 0.23 on average when each is removed), with stronger models leveraging visual features more effectively. Together, these findings demonstrate that accurate clinical description does not guarantee safe patient guidance, motivating the need for multi-dimensional evaluation frameworks in medical AI. △ Less

Submitted 26 June, 2026; originally announced June 2026.

Productionized Fairness Measurement Under Privacy Constraints

Authors: Osonde A. Osoba, Yuzi He, Saikrishna Badrinarayanan, Varun Mithal, Sakshi Jain, Natesh S. Pillai

Abstract: Fairness measurements in the form of disaggregated evaluations often rely on demographic signals that are legally constrained or culturally sensitive. Race and ethnicity signals are among the more difficult signals to curate and use for this task. This paper presents Privacy-Preserving Probabilistic Race/Ethnicity Estimation (PPRE) as a method for enabling fairness measurements with respect to rac… ▽ More Fairness measurements in the form of disaggregated evaluations often rely on demographic signals that are legally constrained or culturally sensitive. Race and ethnicity signals are among the more difficult signals to curate and use for this task. This paper presents Privacy-Preserving Probabilistic Race/Ethnicity Estimation (PPRE) as a method for enabling fairness measurements with respect to race/ethnicity for U.S.\ LinkedIn members in a privacy-preserving manner. PPRE applies privacy technologies (specifically: secure two-party computation, differential privacy, and additive homomorphic encryption) on top of two race/ethnicity demographic signal sources (the Bayesian Improved Surname Geocoding estimator and a sparse golden survey set of self-reported demographics) to power a fairness measurement solution with respect to US-based race/ethnicity demographics. We detail its privacy guarantees and demonstrate its application on candidate- and viewer-side fairness measurements. We close with a transferable framework for institutions seeking to implement similar privacy-preserving measurement infrastructure. △ Less

Submitted 25 June, 2026; originally announced June 2026.

KG-TRACE: A Neuro-Symbolic Framework for Mechanistic Grounding in Antimicrobial Resistance Prediction

Authors: Naman Garg, Sarika Jain, Sourav Yadav, Bharat K. Bhargava, Ghanapriya Singh, Abhishek Srivastava, Parimal Kar

Abstract: While WGS-based AMR prediction has reached high accuracy, existing models lack a mechanism to ground neural attributions in established biological pathways. We present KG-TRACE, a novel neuro-symbolic framework that integrates the WHO mutation knowledge graph (KG) as a structured biological constraint on a neural genomic model. Unlike existing methods that learn statistical patterns in isolation,… ▽ More While WGS-based AMR prediction has reached high accuracy, existing models lack a mechanism to ground neural attributions in established biological pathways. We present KG-TRACE, a novel neuro-symbolic framework that integrates the WHO mutation knowledge graph (KG) as a structured biological constraint on a neural genomic model. Unlike existing methods that learn statistical patterns in isolation, KG-TRACE fuses genomic features and RotatE-based KG embeddings through a learned epistemic trust gate, dynamically weighting neural evidence against symbolic biological knowledge. Evaluated on the CRyPTIC M. tuberculosis cohort, KG-TRACE achieves an AUROC of 0.9760 for isoniazid, achieving competitive accuracy while its primary value lies in symbolic grounding, not predictive uplift. More importantly, we introduce the Biological Grounding Ratio (BGR), a dataset-level metric that quantifies alignment between neural attributions and established biology. Our framework achieves a 92.5% symbolic coverage of isoniazid-resistant predictions and effectively identifies MDR co-occurrence artifacts by issuing laboratory follow-up flags for 'UNCERTAIN' cases. We demonstrate that neuro-symbolic grounding provides a verifiable audit trail for clinicians, bridging the gap between predictive accuracy and clinical trust. △ Less

Submitted 24 June, 2026; originally announced June 2026.

Teaching LLMs String Matching, Backtracking, and Error Recovery to Deduce Bases and Truth Tables for the Combinatorially Exploding Bit Manipulation Puzzles

Authors: Prateek Agnihotri, Sanchit Jain, Prabhat Agnihotri, Aditya Prasad, Shubham Jain

Abstract: This paper presents our algorithmic innovations for the NVIDIA Nemotron Model Reasoning Challenge, focusing on Bit Manipulation Puzzles. In this task, the objective is to discover a hidden logical rule transforming input binary strings to outputs, then apply it to unseen inputs. Large Language Models (LLMs) notoriously struggle here; traditional methods force them to simulate complex boolean logic… ▽ More This paper presents our algorithmic innovations for the NVIDIA Nemotron Model Reasoning Challenge, focusing on Bit Manipulation Puzzles. In this task, the objective is to discover a hidden logical rule transforming input binary strings to outputs, then apply it to unseen inputs. Large Language Models (LLMs) notoriously struggle here; traditional methods force them to simulate complex boolean logic and arithmetic, leading to hallucinations. Furthermore, the search space of bitwise operations (combinations of shifts, rotations, and logic gates) suffers from a severe combinatorial explosion. To overcome this computational intractability, we present a novel approach that abandons arithmetic logic entirely in favor of string similarity, structured search, and autonomous error recovery. Our core contributions are: 1. Bases and Truth Table Formulation: We reframe logic-gate deduction into a base-selection task, leveraging string similarity (minimal bit flips) to isolate primitive transformations ("bases") and deduce truth tables without complex arithmetic. 2. Backtracking DFS and Error Recovery: We formalize a search process that tests candidate bases, detects logical collisions across examples, and backtracks upon failure to perform robust error recovery. 3. Bit Tokenization and Interactive Reasoning SFT: We force the tokenizer to encode binary strings as individual single-bit tokens. We use dynamic masking to simulate external oracle feedback, training the model to hypothesize, self-evaluate, and backtrack natively. Evaluated on bit manipulation puzzles, our approach achieved over 96% validation accuracy. This represents the highest performance in this category, driving our 7th Place overall finish in the contest. △ Less

Submitted 30 June, 2026; v1 submitted 22 June, 2026; originally announced June 2026.

$φ$-Scene: Physically Grounded Image-to-3D Scene Reconstruction

Authors: Haodong Li, Lulu Shao, Haolin Lu, Yu Fu, Yen-Ru Chen, Seemandhar Jain, Manmohan Chandraker

Abstract: Reconstructing compositional 3D scenes from a single image is a fundamental challenge in 3D world modeling. Recent methods can recover high-fidelity, complete 3D objects and predict plausible scene arrangements, but most still treat scene reconstruction primarily as a visual and geometric prediction problem. Their outputs may therefore contain floating objects, interpenetrations, or unstable-conta… ▽ More Reconstructing compositional 3D scenes from a single image is a fundamental challenge in 3D world modeling. Recent methods can recover high-fidelity, complete 3D objects and predict plausible scene arrangements, but most still treat scene reconstruction primarily as a visual and geometric prediction problem. Their outputs may therefore contain floating objects, interpenetrations, or unstable-contact artifacts, limiting their physical validity and downstream usability in simulation, robotics, and interactive environments. We present $φ$-Scene, a physically grounded approach to open-vocabulary and compositional image-to-3D scene reconstruction. The key premise is that a reconstructed scene should not be treated merely as a set of objects with predicted poses, but as a stable physical system. Accordingly, $φ$-Scene formulates reconstruction as topology-driven physical assembly: it infers how objects support one another, orders them accordingly, and progressively settles each object against its already stabilized support context. For each object in topological order, SDF-based optimization first resolves penetrations against the pre-settled support context, and rigid-body simulation then settles the object into a stable contact configuration under real-world physical constraints. Experiments on 3D-Front show that $φ$-Scene achieves the strongest overall performance among out-of-domain methods and remains highly competitive with in-domain baselines. Human and VLM evaluations further show strong preference for $φ$-Scene in visual quality, reference alignment, and physical plausibility. Finally, dedicated physical plausibility metrics covering static contact quality and dynamic stability demonstrate that $φ$-Scene substantially reduces penetration artifacts while producing much lower post-simulation drift, indicating more stable and physically grounded 3D scenes. △ Less

Submitted 19 June, 2026; originally announced June 2026.

SA-VIS: Sparse frame Annotations for training Video Instance Segmentation

Authors: Edoardo Mello Rella, Ajad Chhatkuli, Shipra Jain, Ender Konukoglu, Luc Van Gool

Abstract: Recent online video instance segmentation (VIS) methods have achieved impressive results, thus becoming the preferred approach to segment instances in videos. Despite the resurgence of impressive single image models, the online (or semi-online) VIS approaches outperform single-image models (e.g., based on SAM) by using long sequences of densely annotated frames during training. However,such a trai… ▽ More Recent online video instance segmentation (VIS) methods have achieved impressive results, thus becoming the preferred approach to segment instances in videos. Despite the resurgence of impressive single image models, the online (or semi-online) VIS approaches outperform single-image models (e.g., based on SAM) by using long sequences of densely annotated frames during training. However,such a training setup of VIS is expensive in the sense of compute as well as dense annotations required. In order to solve these major flaws, we argue that the effective modeling of the instances and their evolution in videos do not require densely annotated frames. To that end, we propose a simple and effective module, called Past-frames Feature Propagation (PFP) which aggregates low-dimensional features from the image encoder of multiple frames. This simple low-compute module provides tremendous learning capability in using sparse video frame labels for end-to-end training. Combined with a light-weight frame-specific Instance Queries, our Sparse frame Annotation VIS (SA-VIS) significantly improves performance over its baseline. Most interestingly, our simple design that avoids complexities effectively bridges the gap in accuracy between training on sparsely and densely annotated video sequences. This translates to a mere 0.4% drop in performance of SA-VIS when using annotations for only 1/5 of the images in the dataset. Empirically, SA-VIS shows strong improvements over the baseline on YouTube-VIS 2019/2021/2022 and Occluded VIS (OVIS) and an over 1% improvement in AP on the state-of-the-art in a limited annotations scenario. △ Less

Submitted 29 June, 2026; v1 submitted 18 June, 2026; originally announced June 2026.

Efficient Neural Network Model Selection for Few-Class Application Datasets

Authors: Bryan Bo Cao, Abhinav Sharma, Lawrence O'Gorman, Michael Coss, Shubham Jain

Abstract: While much effort has focused on developing and benchmarking high-performance neural networks, less attention has been given to how dataset properties, known to practitioners, can guide efficient model selection. Neural models are typically evaluated on datasets with thousands of classes, yet many real-world applications involve fewer than ten. To address this understudied but common setting, we d… ▽ More While much effort has focused on developing and benchmarking high-performance neural networks, less attention has been given to how dataset properties, known to practitioners, can guide efficient model selection. Neural models are typically evaluated on datasets with thousands of classes, yet many real-world applications involve fewer than ten. To address this understudied but common setting, we develop a measure of classification difficulty based on data-side properties and show how it enables more efficient model selection for few-class datasets, where traditional approaches are less effective. We term this phenomenon "few-class distinctiveness". Our metric allows comparison of models and datasets 6 to 29$\times$ faster than repeated training and testing. Leveraging this insight, we extend scaled model families below the smallest published models, achieving greater efficiency at similar accuracy, for example models up to 42% smaller than YOLOv5-nano for a mobile robot task. Targeting resource-constrained applications, we demonstrate few-class model selection across mobile robot, drone, and IoT scenarios, highlighting practical gains in efficiency without sacrificing performance. △ Less

Submitted 17 June, 2026; originally announced June 2026.

MAJIC: Leveraging Articulatory Motion for Speech-based Emotion Recognition

Authors: Tanmay Srivastava, Paras Bhavnani, Benjir Alvee Islam, Shubham Jain

Abstract: We introduce MAJIC, a multimodal emotion recognition system that leverages articulatory motion of the jaw and facial muscles for speech-based emotion recognition (SER). While most SER systems perform well on datasets with strongly expressed emotional speech of trained actors, their performance often degrades when emotional expressions become more subtle. We explore this challenge by engineering fe… ▽ More We introduce MAJIC, a multimodal emotion recognition system that leverages articulatory motion of the jaw and facial muscles for speech-based emotion recognition (SER). While most SER systems perform well on datasets with strongly expressed emotional speech of trained actors, their performance often degrades when emotional expressions become more subtle. We explore this challenge by engineering features from articulatory motion and integrating them with audio features using a multi-task learning framework. Our key insight is that emotion in speech manifests not only through vocal characteristics but also through distinct articulatory motions: jaw movements, facial muscle vibrations, and speech-induced vibrations. While audio captures features such as pitch and prosody, articulatory motion contains complementary information that is not present in audio alone. We evaluate our system on data collected from 20 participants across multiple sessions, 10 languages, and diverse scenarios, including prompted and conversational speech, showing its robustness across users and settings. MAJIC achieves 93% accuracy and 91% F1 score for emotion classification, outperforming strong audio-based baselines on our dataset. △ Less

Submitted 16 June, 2026; originally announced June 2026.

Video2Sim2Real: Full-Stack Autonomous Dexterous Skill Acquisition from a Single Human Video

Authors: Yunhai Han, Jianuo Qiu, Linhao Bai, Ziyu Xiao, Zihang Zeng, Yangcen Liu, Zhaodong Yang, Shalin Jain, Wenrui Ma, Jiaqi Fu, Yuqian Zheng, Manisha Natarajan, Muhammad Zubair Irshad, Kenneth Shaw, Matthew Gombolay, Zsolt Kira, Harish Ravichandar

Abstract: Human manipulation videos are a convenient and intuitive source for robot learning. However, directly transferring human dexterity to robots remains challenging due to perception errors and embodiment gap. To address this, we introduce Video2Sim2Real, a full-stack framework for autonomous skill acquisition from a single human manipulation video. Our framework first uses off-the-shelf foundation mo… ▽ More Human manipulation videos are a convenient and intuitive source for robot learning. However, directly transferring human dexterity to robots remains challenging due to perception errors and embodiment gap. To address this, we introduce Video2Sim2Real, a full-stack framework for autonomous skill acquisition from a single human manipulation video. Our framework first uses off-the-shelf foundation models to reconstruct a simulator-ready digital twin and extract robot and object motion priors. Rather than treating the extracted robot motion as a reliable reference throughout execution, our key idea is to recover and leverage the most fundamental sources of supervision from the demonstrated skill: We identify object-centric keyframes to optimize the corresponding robot configurations using object information from the simulator, and use these configurations as anchors that refine the robot motion such that it ultimately has the desired impact on the environment. To bridge the remaining sim-to-real gap, we introduce a sim-to-real strategy that decouples robustness to noisy and incomplete perception from variations in hand-object interaction dynamics. Specifically, we learn to recalibrate robot configurations from noisy real-world point clouds via IL, and leverage residual RL to perform local finger-level adaptations to ensure for robust and effective interactions. Finally, a collision-aware motion planning module enables spatial generalization to novel object configurations. Across several everyday manipulation tasks, Video2Sim2Real improves simulated task success, safety, and trajectory coherence over numerous baselines, and achieves better sim-to-real transfer than existing techniques. These results demonstrate a promising path toward autonomous dexterous skill acquisition from human videos. △ Less

Submitted 7 June, 2026; originally announced June 2026.

VOLT: Vision and Language Trajectory Segmentation for Faster-than-Demonstration Policies

Authors: Robert Ramirez Sanchez, Daniel J. Evans, Dylan P. Losey, Siddarth Jain

Abstract: Humans often take longer to demonstrate a task than a robot would need to execute it. Rather than learning to replicate the demonstration at the same pace, many industrial and practical applications require robots to perform tasks as quickly as possible. In this paper, we investigate several hypotheses for learning policies that operate faster-than-demonstrations. Our experiments show that the mos… ▽ More Humans often take longer to demonstrate a task than a robot would need to execute it. Rather than learning to replicate the demonstration at the same pace, many industrial and practical applications require robots to perform tasks as quickly as possible. In this paper, we investigate several hypotheses for learning policies that operate faster-than-demonstrations. Our experiments show that the most effective strategy is to downsample recorded demonstrations and train the robot's policy on this accelerated data. However, uniformly downsampling an entire trajectory can be problematic. Some parts of a task can be safely sped up (e.g., unconstrained motion), while others demand slower, more precise motion (e.g., object interactions or fine manipulation). To address this challenge, we introduce VOLT, a vision-and-language trajectory segmentation method that reasons over video demonstrations, and leverages contextual cues to determine when acceleration is appropriate and when careful precision is required. VOLT identifies segments where slow, deliberate motion is necessary, then selectively downsamples the remaining segments. The resulting reformatted trajectories can be used with standard imitation learning approaches, such as diffusion policies. Our results highlight that segmentation quality is critical -- baseline methods often misidentify when acceleration is possible, leading to overly cautious or unreliable policies. Compared to state-of-the-art alternatives, VOLT allows robots to execute tasks faster while maintaining strong performance. △ Less

Submitted 9 June, 2026; v1 submitted 4 June, 2026; originally announced June 2026.

A Theory-Guided LLM Pedagogical Agent for STEM+C Scaffolding Without Over-Reliance

Authors: Clayton Cohn, Surya Rayala, Siyuan Guo, Hanchen David Wang, Naveeduddin Mohammed, Umesh Timalsina, Shruti Jain, Ryan Li, Angela Eeds, Menton Deweese, Pamela J. Osborn Popp, Rebekah Stanton, Shakeera Walker, Ashwin T S, Meiyi Ma, Gautam Biswas

Abstract: LLM pedagogical agents are proliferating, yet recent findings have raised questions about their adherence to established theories of learning and, by extension, their educational value. Concerns regarding cognitive offloading, over-reliance, and "gaming" behaviors persist and remain largely unaddressed. In response, we developed Copa, an agentic, multi-agent, multimodal Collaborative Peer Agent fo… ▽ More LLM pedagogical agents are proliferating, yet recent findings have raised questions about their adherence to established theories of learning and, by extension, their educational value. Concerns regarding cognitive offloading, over-reliance, and "gaming" behaviors persist and remain largely unaddressed. In response, we developed Copa, an agentic, multi-agent, multimodal Collaborative Peer Agent for STEM+C learning. Copa is built on top of the Evidence-Decision-Feedback (EDF) framework, grounding its interactions in Social Cognitive Theory and Social Constructivism and promoting sense-making through adaptive, dialogic support rather than answer-seeking. In an authentic high school computational-modeling study (n=33 dyads), we demonstrate that Copa (1) supports students' confidence building and ability to verbalize conceptual understanding without causing dependence; and (2) provides adaptive feedback personalized to learners that is interpretable with respect to students' multimodal input data. These findings position theory-guided, multimodal LLM agents as a promising path toward classroom AI integration that amplifies students' reasoning rather than replacing it. △ Less

Submitted 28 May, 2026; originally announced May 2026.

On the Optimizer Dependence of Neural Scaling Laws

Authors: Vansh Ramani, Shourya Vir Jain

Abstract: The scaling exponent $α$ in neural scaling laws $L(N) \propto N^{-α}$ is commonly treated as a fixed constant set by architecture and data. We present evidence that $α$ depends systematically on the optimizer. In controlled random-feature regression experiments -- the canonical theoretical framework for neural scaling -- we measure $α$ across five optimizer variants and six spectral conditions. Pr… ▽ More The scaling exponent $α$ in neural scaling laws $L(N) \propto N^{-α}$ is commonly treated as a fixed constant set by architecture and data. We present evidence that $α$ depends systematically on the optimizer. In controlled random-feature regression experiments -- the canonical theoretical framework for neural scaling -- we measure $α$ across five optimizer variants and six spectral conditions. Preconditioned optimizers consistently yield steeper scaling (larger $α$), with the $α$-shift increasing across most of the tested spectral range, peaking near $s = 1.5$, and remaining large at $s = 2.0$. At $s \approx 1.0$ (characteristic of natural language), the full natural gradient achieves $α\approx 0.31$ versus $α\approx 0.12$ for gradient descent -- a $2.6\times$ larger fitted exponent that, within the random-feature model, compounds with each model-size doubling. Whether and how this exponent shift transfers to large-scale LLM training -- where recent evidence suggests the advantage may attenuate with scale -- remains an important open question. Our results imply that scaling-law forecasts should account for optimizer choice, and we provide a spectral diagnostic predicting when advanced optimizers will pay off. △ Less

Submitted 28 May, 2026; originally announced May 2026.

Generative Animations: A Multi-Model Pipeline for Prompt-Driven Motion Synthesis

Authors: Mannat Khurana, Sanyam Jain, Rishav Agarwal

Abstract: Animation elevates digital documents into immersive experiences, yet creating custom motion paths remains cumbersome, requiring designers to manually select presets, plot Bézier points, and configure timing properties. We introduce Generative Animations, a system that transforms natural language prompts into production-ready animations. By chaining Large Language Models (LLMs) for semantic parsing… ▽ More Animation elevates digital documents into immersive experiences, yet creating custom motion paths remains cumbersome, requiring designers to manually select presets, plot Bézier points, and configure timing properties. We introduce Generative Animations, a system that transforms natural language prompts into production-ready animations. By chaining Large Language Models (LLMs) for semantic parsing with the Segment Anything Model (SAM) for visual grounding, our pipeline automatically generates motion paths that respect scene geometry, handle depth-based occlusions, and honor 3D perspective transforms. We demonstrate the system through three use cases: contour-following trajectories, orbital animations with z-order awareness, and perspective-aligned motion on transformed objects. △ Less

Submitted 26 May, 2026; originally announced May 2026.

E3: Issue-Level Backtesting for Automated Research Critique

Authors: Yashwardhan Chaudhuri, Sanyam Jain, Paridhi Mundra

Abstract: We present E3, an automated review assistant that augments reviewers and engineering teams by identifying decision-relevant technical concerns in research papers. For each concern, E3 reports its nature, its location, its bearing on the contribution, and the analysis or evidence that would resolve it, covering unsupported claims, missing ablations, weak baselines, hidden assumptions, threats to va… ▽ More We present E3, an automated review assistant that augments reviewers and engineering teams by identifying decision-relevant technical concerns in research papers. For each concern, E3 reports its nature, its location, its bearing on the contribution, and the analysis or evidence that would resolve it, covering unsupported claims, missing ablations, weak baselines, hidden assumptions, threats to validity, and leakage risks. To evaluate E3 without contamination confounds we adopt an issue-level backtesting protocol: the corpus is restricted to papers postdating the training cutoff of every automated source, and for each paper a meta-judge that observes only anonymised reviews labels every issue-source pair as Caught, Partial, or Missed. Applied to 100 ICLR 2026 papers and 4598 judged issue rows, comparing E3 against the ICLR human reviews and two prompt-matched LLM baselines built on gpt-5.4 from OpenAI and claude-opus-4-6 from Anthropic, with meta-judge gpt-5.5, E3 attains the highest recall on every aggregate metric. Partial-inclusive recall reaches 90.2 percent, which is 15.5 points over GPT, 17.1 points over Claude, and 29.2 points over the human reviews, and strict recall preserves the ordering at 65.8 percent. On concerns raised by the human reviewers, E3 recovers 89.6 percent; on concerns the human reviewers missed it surfaces 1635 additional rows admitted into the judged union, 406 above the next-best source. Corpus, baseline prompts, judge prompt template, and evaluation code are released. △ Less

Submitted 26 May, 2026; originally announced May 2026.

PhylaFlow: Hybrid Flow Matching in Billera-Holmes-Vogtmann Tree Space for Phylogenetic Inference

Authors: Yasha Ektefaie, Leo Cui, Shrey Jain, Marinka Zitnik, Pardis Sabeti

Abstract: Phylogenetic trees are hybrid objects: branch lengths vary continuously, while topologies change discretely through edge contractions and expansions. Billera-Holmes-Vogtmann (BHV) tree space provides a canonical geometry for this structure, representing each resolved topology as a Euclidean orthant and topological changes as motion across shared lower-dimensional boundaries. We introduce PhylaFlow… ▽ More Phylogenetic trees are hybrid objects: branch lengths vary continuously, while topologies change discretely through edge contractions and expansions. Billera-Holmes-Vogtmann (BHV) tree space provides a canonical geometry for this structure, representing each resolved topology as a Euclidean orthant and topological changes as motion across shared lower-dimensional boundaries. We introduce PhylaFlow, a hybrid flow-matching model that learns posterior-basin transport in BHV tree space. PhylaFlow is trained on BHV geodesic paths from random starting trees to short-run posterior samples, coupling continuous branch-length motion within orthants with learned boundary events and discrete topology transitions. We evaluate the learned geometry operationally: if the flow reaches posterior-relevant regions, finite-budget Bayesian refinement initialized from, or guided by, its terminal trees should recover posterior-supported topologies more efficiently. Across DS1-DS8 phylogenetic posterior benchmarks, PhylaFlow substantially reduces initial Tree-KL relative to classical initializers. After finite-budget MrBayes refinement, direct PhylaFlow improves early and intermediate topology-recovery trajectories on most datasets, while split-guided PhylaFlow-MCMC obtains the strongest hard-case results. The best PhylaFlow variant outperforms short-warmup on seven of eight datasets and PhyloGFN on five of eight under the same refinement budget. In a joint sequence-conditioned experiment, sequence embeddings steer posterior split recovery, although exact posterior topology recovery remains preliminary. These results show that hybrid flow matching can learn actionable transport in BHV tree space and provide a geometry-aware proposal mechanism for Bayesian phylogenetic inference. △ Less

Submitted 20 May, 2026; originally announced May 2026.

AgentNLQ: A General-Purpose Agent for Natural Language to SQL

Authors: Olena Bogdanov, Yeunji Jung, Chandra Dhir, Pareekshitreddy Gaddam, Saurabh Jain, Lakshmi Tumati, Vijay Parthasarathy, Anup Shirgaonkar

Abstract: Natural language to SQL (NL2SQL) conversion is an important problem for researchers and enterprises due to the ubiquitous importance of relational databases in broad-ranging practical problems. Despite the rapid advancements in the capabilities of LLMs, NL2SQL has not reached parity in accuracy with human expert SQL writers, hence needing additional improvements in NL2SQL algorithms. This study pr… ▽ More Natural language to SQL (NL2SQL) conversion is an important problem for researchers and enterprises due to the ubiquitous importance of relational databases in broad-ranging practical problems. Despite the rapid advancements in the capabilities of LLMs, NL2SQL has not reached parity in accuracy with human expert SQL writers, hence needing additional improvements in NL2SQL algorithms. This study presents a new multi-agent method for NL2SQL that achieves 78.1% semantic accuracy on the BIg Bench for LaRge-scale Database (BIRD) benchmark. Our method leverages a semantically enriched representation of user-provided schema, adds user-provided business rules, and produces accurate SQL queries. The main contributions of this study are (a) We designed an optimized new orchestrator in a multi-agent solution that uses LLMs to plan, orchestrate, reflect, and self-correct to generate accurate SQL queries, (b) We developed an advanced schema enrichment method that creates context-aware metadata to improve accuracy, and (c) We demonstrated the accuracy and generalizability of the method across different domains and datasets by evaluating it on the BIRD-SQL benchmark. △ Less

Submitted 18 May, 2026; originally announced May 2026.

Position: Graph Condensation Needs a Reset -- Move Beyond Full-dataset Training and Model-Dependence

Authors: Mridul Gupta, Samyak Jain, Vansh Ramani, Hariprasad Kodamana, Sayan Ranu

Abstract: Graph Neural Networks (GNNs) are powerful tools for learning from graph-structured data, but their scalability is increasingly strained by the size of real-world graphs in domains like recommender systems, fraud detection, and molecular biology. Graph condensation -- the task of generating a smaller synthetic graph that retains the performance of models trained on the original -- has emerged as a… ▽ More Graph Neural Networks (GNNs) are powerful tools for learning from graph-structured data, but their scalability is increasingly strained by the size of real-world graphs in domains like recommender systems, fraud detection, and molecular biology. Graph condensation -- the task of generating a smaller synthetic graph that retains the performance of models trained on the original -- has emerged as a promising solution. However, the dominant approach of gradient matching introduces a fundamental contradiction: it requires training on the full dataset to create the compressed version, thereby undermining the goal of efficiency. Worse still, these methods suffer from high computational overhead, poor generalization across GNN architectures, and brittle reliance on specific model configurations. Equally concerning is the community's reliance on misleading evaluation protocols such as node compression ratios, which fail to reflect true resource savings, condensation overhead, and illusory application to neural architecture search. These shortcomings are not incidental -- they are systemic, and they obstruct meaningful progress. In this position paper, we argue that graph condensation, in its current form, needs a reset. We call for moving beyond full-dataset training and model-dependent design, and instead advocate for methods that are lightweight, architecture-agnostic, and practically deployable. By identifying key methodological flaws and outlining concrete research directions, we aim to reorient the field toward approaches that deliver on the true promise of condensation: efficient, generalizable, and usable GNN training at scale. △ Less

Submitted 20 May, 2026; v1 submitted 17 May, 2026; originally announced May 2026.

Operationalising Post Quantum TLS Automated Configuration Profiling and Hybrid PQC Deployment in Financial Infrastructure

Authors: Harish Balaji, Aarav Varshney, Prasanna Ravi, Sripal Jain, Robin Foe, Jorden Seet, Huaxiong Wang, Kwok-Yan Lam, Anupam Chattopadhyay

Abstract: Organisations are upgrading their cryptographic infrastructure to become quantum safe before large scale quantum computers materialise. Post quantum cryptography (PQC) standards now exist for key exchange and digital signatures, but the urgent question for adopters is how to operationalise PQC in complex environments with confidence. In banking, Transport Layer Security (TLS), for example, protect… ▽ More Organisations are upgrading their cryptographic infrastructure to become quantum safe before large scale quantum computers materialise. Post quantum cryptography (PQC) standards now exist for key exchange and digital signatures, but the urgent question for adopters is how to operationalise PQC in complex environments with confidence. In banking, Transport Layer Security (TLS), for example, protects data in transit across public facing channels and internal services, and is terminated at many heterogeneous endpoints (web servers, API gateways, load balancers, reverse proxies), each a potential quantum vulnerable component and migration target. We argue that the bottleneck is operational rather than algorithmic, hybrid key exchanges such as MLKEM and hybrid MLKEM key exchanges are already available in mainstream libraries, but security teams lack precise visibility into TLS configurations and repeatable methods for enabling PQC compatible settings across a heterogeneous estate. This paper presents a configuration parsing methodology that automatically extracts and normalises TLS cryptographic posture across dominant enterprise web server stacks, producing a unified, provenance traced cryptographic inventory as a foundation for migration and compliance. We demonstrate the approach on 8,443 real world Nginx configurations from public repositories and in a proof of concept deployment at a financial institution, where MLKEM and hybrid MLKEM key exchanges at TLS termination points (web server and API gateway) securing an internal application, with zero application layer changes and manageable performance overhead. △ Less

Submitted 18 May, 2026; originally announced May 2026.

New Algorithms for Parity-SAT and Its Bounded-Occurrence Versions

Authors: Sanjay Jain, Junqiang Peng, Frank Stephan, Haoyun Tang, Mingyu Xiao

Abstract: Parity-SAT is the problem of determining whether a given CNF formula has an odd number of satisfying assignments. As a canonical $\oplus$P-complete problem, it represents a fundamental variant of the exact model counting problem (#SAT). Under the Strong Exponential Time Hypothesis (SETH), Parity-SAT admits no $O^*((2-\varepsilon)^n)$-time or $O^*((2-\varepsilon)^m)$-time algorithm for any constant… ▽ More Parity-SAT is the problem of determining whether a given CNF formula has an odd number of satisfying assignments. As a canonical $\oplus$P-complete problem, it represents a fundamental variant of the exact model counting problem (#SAT). Under the Strong Exponential Time Hypothesis (SETH), Parity-SAT admits no $O^*((2-\varepsilon)^n)$-time or $O^*((2-\varepsilon)^m)$-time algorithm for any constant $\varepsilon>0$, where $n$ and $m$ denote the numbers of variables and clauses, respectively. Thus, breaking the $2^n$ or $2^m$ barrier appears impossible in full generality. In this work, we revisit this barrier through structural restrictions and a refined exploitation of parity. We study Parity-$d$-occ-SAT, where each variable appears in at most $d$ clauses, and obtain three main results. First, we design a randomized $O^*(2^{m(1-1/O(d))})$-time algorithm, thereby breaking the $2^m$ barrier for every fixed $d$. Second, for the special case $d=2$, we develop a significantly sharper branching algorithm running in $O^*(1.1193^n)$ time or $O^*(1.3248^m)$ time. Third, leveraging the structural insights underlying the $d=2$ case, we obtain an $O^*(1.1052^L)$-time algorithm for general Parity-SAT, where $L$ denotes the formula length. All algorithms use only polynomial space. Notably, our running-time bounds are better than the best known bounds for the corresponding exact counting counterparts, highlighting a genuine algorithmic advantage of parity over counting. Conceptually, our results demonstrate that parity admits finer structural reductions and more efficient branching than exact model counting, and that bounded occurrence can be systematically leveraged to circumvent classical exponential barriers. △ Less

Submitted 15 May, 2026; v1 submitted 13 May, 2026; originally announced May 2026.

SleepWalk: A Three-Tier Benchmark for Stress-Testing Instruction-Guided Vision-Language Navigation

Authors: Niyati Rawal, Sushant Ravva, Shah Alam Abir, Saksham Jain, Aman Chadha, Vinija Jain, Suranjana Trivedy, Amitava Das

Abstract: Vision-Language Models (VLMs) have advanced rapidly in multimodal perception and language understanding, yet it remains unclear whether they can reliably ground language into spatially coherent, plausibly executable actions in 3D digital environments. We introduce SleepWalk, a benchmark for evaluating instruction-grounded trajectory prediction in single-scene 3D worlds generated from textual scene… ▽ More Vision-Language Models (VLMs) have advanced rapidly in multimodal perception and language understanding, yet it remains unclear whether they can reliably ground language into spatially coherent, plausibly executable actions in 3D digital environments. We introduce SleepWalk, a benchmark for evaluating instruction-grounded trajectory prediction in single-scene 3D worlds generated from textual scene descriptions and filtered for navigability. Unlike prior navigation benchmarks centered on long-range exploration across rooms, SleepWalk targets localized, interaction-centric embodied reasoning: given rendered visual observations and a natural-language instruction, a model must predict a trajectory that respects scene geometry, avoids collisions, and terminates at an action-compatible location. The benchmark covers diverse indoor and outdoor environments and organizes tasks into three tiers of spatial and temporal difficulty, enabling fine-grained analysis of grounding under increasing compositional complexity. Using a standardized pointwise judge-based evaluation protocol, we evaluate three frontier VLMs on 2,472 curated 3D environments with nine instructions per scene. Results reveal systematic failures in grounded spatial reasoning, especially under occlusion, interaction constraints, and multi-step instructions: performance drops as the difficulty level of the tasks increase. In general, current VLMs can somewhat produce trajectories that are simultaneously spatially coherent, plausibly executable, and aligned with intended actions. By exposing failures in a controlled yet scalable setting, SleepWalk provides a critical benchmark for advancing grounded multimodal reasoning, embodied planning, vision-language navigation, and action-capable agents in 3D environments. △ Less

Submitted 7 June, 2026; v1 submitted 11 May, 2026; originally announced May 2026.

PLACO: A Multi-Stage Framework for Cost-Effective Performance in Human-AI Teams

Authors: Pranavkumar Mallela, Vinay Kumar, Shashi Shekhar Jha, Shweta Jain

Abstract: Human-AI teams play a pivotal role in improving overall system performance when neither the human nor the model can achieve such performance on their own. With the advent of powerful and accessible Generative AI models, several mundane tasks have morphed into Human-AI team tasks. From writing essays to developing advanced algorithms, humans have found that using AI assistance has led to an acceler… ▽ More Human-AI teams play a pivotal role in improving overall system performance when neither the human nor the model can achieve such performance on their own. With the advent of powerful and accessible Generative AI models, several mundane tasks have morphed into Human-AI team tasks. From writing essays to developing advanced algorithms, humans have found that using AI assistance has led to an accelerated work pace like never before. In classification tasks, where the final output is a single hard label, it is crucial to address the combination of human and model output. Prior work elegantly solves this problem using Bayes rule, using the assumption that human and model output are conditionally independent given the ground truth. Specifically, it discusses a combination method to combine a single deterministic labeler (the human) and a probabilistic labeler (the classifier model) using the model's instance-level and the human's class-level calibrated probabilities. △ Less

Submitted 8 May, 2026; originally announced May 2026.

Pen-Strategist: A Reasoning Framework for Penetration Testing Strategy Formation and Analysis

Authors: Yasod Ginige, Pasindu Marasinghe, Sajal Jain, Suranga Seneviratne

Abstract: Cyber threats are rapidly increasing, expanding their impact from large-scale enterprises to government services and individual users, making robust security systems increasingly essential. However, a significant shortage of skilled cybersecurity professionals exacerbates this challenge. While recent research has explored automating tasks such as penetration testing using LLM-based agents, existin… ▽ More Cyber threats are rapidly increasing, expanding their impact from large-scale enterprises to government services and individual users, making robust security systems increasingly essential. However, a significant shortage of skilled cybersecurity professionals exacerbates this challenge. While recent research has explored automating tasks such as penetration testing using LLM-based agents, existing frameworks often perform poorly due to limited capability in strategy formulation, domain-specific reasoning, and accurate action and tool selection. To overcome these limitations, we propose Pen-Strategist framework, consisting of a novel domain-specific reasoning model that derives pentesting strategies via logical reasoning and a classifier that converts the strategies into actionable steps. First, we construct a reasoning dataset containing logical explanations for both strategy derivation and step selection in pentesting scenarios. We then fine-tune a Qwen-3-14B model for strategy generation using reinforcement learning. Evaluation on the test split of the dataset demonstrates a 87% improvement in strategy derivation performance compared to the baseline. Furthermore, we integrate the fine-tuned Pen-Strategist model into existing automated pentesting frameworks, such as PentestGPT, and evaluate its performance on vulnerable machines, achieving a 47.5% improvement in subtask completion while surpassing the baseline GPT-5. Further experiments on the CTFKnow benchmark show an 18% performance gain over the base model. For step prediction, we train a semantic-based CNN classifier, which outperforms commercial LLMs by 28% and enhances execution stability. Finally, we conduct a user study to qualitatively assess the generated strategies, and Pen-Strategist demonstrates superior performance compared to the Claude-4.6-Sonnet. △ Less

Submitted 6 May, 2026; originally announced May 2026.

Sequential vs. Simultaneous Entanglement Swapping under Optimal Link-Layer Control

Authors: Priyam Srivastava, Akshat R. Sabavat, Siddharth Jain, Alan Scheller-Wolf, Sridhar Tayur, David Tipper, Prashant Krishnamurthy, Amy Babay, Kaushik P. Seshadreesan

Abstract: Connection-less, packet-switched quantum network architectures distribute entanglement across multi-hop paths through sequential entanglement swapping, in which each node acts on purely local state information. The architectural advantages over the connection-oriented alternative -- simultaneous SWAP-ASAP -- are compelling, but sequential swapping holds partial chains in intermediate buffers betwe… ▽ More Connection-less, packet-switched quantum network architectures distribute entanglement across multi-hop paths through sequential entanglement swapping, in which each node acts on purely local state information. The architectural advantages over the connection-oriented alternative -- simultaneous SWAP-ASAP -- are compelling, but sequential swapping holds partial chains in intermediate buffers between successive swaps, exposing them to memory decoherence in a way simultaneous SWAP-ASAP avoids by design. We present a proof-of-principle study at fixed chain length $n = 4$ in which each elementary link is governed by a fixed reinforcement-learning policy optimizing the secret-key rate of the six-state protocol, leaving the network-layer protocol as the sole independent variable. Sweeping the network-layer memory coherence time $T_c^{\mathrm{ext}}$ over four orders of magnitude reveals a clear regime structure governed by the dimensionless ratio $T_c^{\mathrm{ext}}/τ$, where $τ$ is the per-link entanglement heralding latency. Simultaneous SWAP-ASAP delivers a constant rate across the full sweep. Sequential swapping, by contrast, collapses to zero end-to-end deliveries below $T_c^{\mathrm{ext}}/τ= 25$, and begins recovering at $T_c^{\mathrm{ext}}/τ= 50$. It remains limited by the simultaneous rate, which it saturates only at the relaxed end of the sweep. These results suggest that the connection-less penalty is a near-term phenomenon tied to present-day memory coherence rather than a fundamental property of sequential swapping. △ Less

Submitted 5 May, 2026; originally announced May 2026.

Multimodal Data Curation Through Ranked Retrieval

Authors: Pratyush Muthukumar, Harshil Kotamreddy, Sarah Amiraslani, Tomo Kanazawa, Ramani Akkati, Shaan Jain, Andrew Mathau

Abstract: Shared embedding spaces are widely used for multimodal search and data curation. In practice, two problems often limit how well this works. First, embeddings can reflect modality more than meaning, so examples cluster by input type even when the underlying content matches. Second, the paired supervision used to train these spaces is often noisy. When we blend many heterogeneous, human-labeled data… ▽ More Shared embedding spaces are widely used for multimodal search and data curation. In practice, two problems often limit how well this works. First, embeddings can reflect modality more than meaning, so examples cluster by input type even when the underlying content matches. Second, the paired supervision used to train these spaces is often noisy. When we blend many heterogeneous, human-labeled datasets, these issues reinforce each other and degrade cross-modal retrieval. We present a framework that improves alignment by acting on both the training pairs and the embedding model. Symmetric Nucleus Subsampling (SNS) refines training pairs by trimming raw inputs and annotations to the portions that best support each other. Expert Embedding Engine (EEE) combines complementary embedding experts using a learned projection network, together with a bias-aware objective that reduces modality-driven separation in the embedding space. We demonstrate that this approach collapses the modality gap by over 90% on average vs base embedding experts and is a strong data curator, with datablends from our method outperforming stratified sampling and traditional curation baselines in downstream model performance. △ Less

Submitted 1 May, 2026; originally announced May 2026.

Meritocratic Fairness in Budgeted Combinatorial Multi-armed Bandits via Shapley Values

Authors: Shradha Sharma, Swapnil Dhamal, Shweta Jain

Abstract: We propose a new framework for meritocratic fairness in budgeted combinatorial multi-armed bandits with full-bandit feedback (BCMAB-FBF). Unlike semi-bandit feedback, the contribution of individual arms is not received in full-bandit feedback, making the setting significantly more challenging. To compute arm contributions in BCMAB-FBF, we first extend the Shapley value, a classical solution concep… ▽ More We propose a new framework for meritocratic fairness in budgeted combinatorial multi-armed bandits with full-bandit feedback (BCMAB-FBF). Unlike semi-bandit feedback, the contribution of individual arms is not received in full-bandit feedback, making the setting significantly more challenging. To compute arm contributions in BCMAB-FBF, we first extend the Shapley value, a classical solution concept from cooperative game theory, to the $K$-Shapley value, which captures the marginal contribution of an agent restricted to a set of size at most $K$. We show that $K$-Shapley value is a unique solution concept that satisfies Symmetry, Linearity, Null player, and efficiency properties. We next propose K-SVFair-FBF, a fairness-aware bandit algorithm that adaptively estimates $K$-Shapley value with unknown valuation function. Unlike standard bandit literature on full bandit feedback, K-SVFair-FBF not only learns the valuation function under full feedback setting but also mitigates the noise arising from Monte Carlo approximations. Theoretically, we prove that K-SVFair-FBF achieves $O(T^{3/4})$ regret bound on fairness regret. Through experiments on federated learning and social influence maximization datasets, we demonstrate that our approach achieves fairness and performs more effectively than existing baselines. △ Less

Submitted 1 May, 2026; originally announced May 2026.

Temporal Data Requirement for Predicting Unplanned Hospital Readmissions

Authors: Ramin Mohammadi, Vahab vahdat, Sarthak Jain, Amir T. Namin, Ramya Palacholla, Sagar Kamarthi

Abstract: With the proliferation of Electronic Health Records (EHRs), a critical challenge in building predictive models is determining the optimal historical data time window to maximize accuracy. This study investigates the impact of various observation windows ranging from the day of surgery to three years prior on predicting 30-day readmission following hip and knee arthroplasties. The dataset encompass… ▽ More With the proliferation of Electronic Health Records (EHRs), a critical challenge in building predictive models is determining the optimal historical data time window to maximize accuracy. This study investigates the impact of various observation windows ranging from the day of surgery to three years prior on predicting 30-day readmission following hip and knee arthroplasties. The dataset encompasses both structured encounter records (over 4 million) and unstructured clinical notes (80,000) from 7,174 patients. To extract meaning from the clinical notes, we employed a suite of non neural (BOW, count BOW, TF IDF, LDA) and neural encoders (BERT, 1D CNN, BiLSTM, Average). We subsequently evaluated models utilizing clinical notes alone, structured data alone, and a combination of both modalities. Our results demonstrate that the optimal time window for unstructured clinical notes is significantly shorter than for structured data, maximum predictive performance was achieved using notes from just three to six months prior to surgery. In contrast, performance using structured data improved as the time window lengthened, but strictly plateaued after twelve months. These modality-specific temporal patterns remained consistent regardless of model complexity or encoder type. Ultimately, these findings challenge the general assumption that more historical data inherently yields better machine learning predictions, establishing targeted time-window guidelines for optimizing readmission prediction models. △ Less

Submitted 1 May, 2026; originally announced May 2026.

Text Style Transfer with Machine Translation for Graphic Designs

Authors: Deergh Singh Budhauria, Sanyam Jain, Rishav Agarwal, Tracy King

Abstract: Globalization of graphic designs such as those used in marketing materials and magazines is increasingly important for communication to broad audiences. To accomplish this, the textual content in the graphic designs needs to be accurately translated and have the text styling preserved in order to fit visually into the design. Preserving text styling requires high accuracy word alignment between th… ▽ More Globalization of graphic designs such as those used in marketing materials and magazines is increasingly important for communication to broad audiences. To accomplish this, the textual content in the graphic designs needs to be accurately translated and have the text styling preserved in order to fit visually into the design. Preserving text styling requires high accuracy word alignment between the original and the translated text. The problem of word alignment between source and translated text is long known. The industry standards for extracting word alignments are defined by Giza++ and attention probabilities from neural machine translation (NMT) models. In this paper, we explore three new methods to tackle the word alignment problem for transferring text styles from the source to the translated text. The proposed methods are developed on top of commercially available NMT and LLM translation technologies. They include: NMT with custom input and output tags for text styling; LLM with custom input and output tags; a hybrid with NMT for translation followed by an LLM with use of unigram mappings. To analyze the performance of these solutions, their alignment results are compared with the results of an attention head approach to gauge their usability in graphic design applications. Interestingly, the attention head strong baseline proves more accurate than the LLM or NMT approach and on par with the hybrid NMT+LLM approach. △ Less

Submitted 29 April, 2026; originally announced April 2026.

Neural posterior estimation of the neutrino direction in IceCube using transformer-encoded normalizing flows on the sphere

Authors: R. Abbasi, M. Ackermann, J. Adams, J. A. Aguilar, M. Ahlers, J. M. Alameddine, S. Ali, N. M. Amin, K. Andeen, C. Argüelles, Y. Ashida, S. Athanasiadou, S. N. Axani, R. Babu, X. Bai, A. Balagopal V., S. W. Barwick, V. Basu, R. Bay, J. J. Beatty, J. Becker Tjus, P. Behrens, J. Beise, C. Bellenghi, S. Benkel , et al. (389 additional authors not shown)

Abstract: IceCube is a cubic-kilometer-scale neutrino detector located at the geographic South Pole. A precise directional reconstruction of IceCube neutrinos is vital for associations with astronomical objects. In this context, we discuss neural posterior estimation of the neutrino direction via a transformer encoder that maps to a normalizing flow on the 2-sphere. It achieves a new state-of-the-art angula… ▽ More IceCube is a cubic-kilometer-scale neutrino detector located at the geographic South Pole. A precise directional reconstruction of IceCube neutrinos is vital for associations with astronomical objects. In this context, we discuss neural posterior estimation of the neutrino direction via a transformer encoder that maps to a normalizing flow on the 2-sphere. It achieves a new state-of-the-art angular resolution for the two main event morphologies in IceCube - tracks and showers - while being significantly faster than traditional B-spline-based likelihood reconstructions. All-sky scans can be performed within seconds rather than hours, and take constant computation time, regardless of whether the posterior extent is arc-minutes or spans the whole sky. We utilize a combination of $C^2$-smooth rational-quadratic splines, scale transformations and rotations to define a novel spherical normalizing-flow distribution whose parameters are predicted as a whole as the output of the transformer encoder. We test several structural choices diverting from the vanilla transformer architecture. In particular, we find dual residual streams, nonlinear QKV projection and a separate class token with its own cross-attention processing to boost test-time performance. The angular resolution for both showers and tracks improves substantially over the whole trained energy range from 100 GeV to 100 PeV. At 100 TeV deposited energy, for example, the median angular resolution improves by a factor of $1.3$ for throughgoing tracks, by a factor of $1.7$ for showers and by a factor of $2.5$ for starting tracks compared to state-of-the art likelihood reconstructions based on B-splines. While previous machine-learning (ML) efforts have managed to obtain competitive shower resolutions, this is the first time an ML-based method outperforms likelihood-based muon reconstructions above 100 GeV. △ Less

Submitted 21 April, 2026; originally announced April 2026.

Voice of India: A Large-Scale Benchmark for Real-World Speech Recognition in India

Authors: Kaushal Bhogale, Manas Dhir, Amritansh Walecha, Manmeet Kaur, Vanshika Chhabra, Aaditya Pareek, Hanuman Sidh, Mahima Manik, Sagar Jain, Bhaskar Singh, Utkarsh Singh, Tahir Javed, Shobhit Banga, Mitesh M. Khapra

Abstract: Existing Indic ASR benchmarks often use scripted, clean speech and leaderboard driven evaluation that encourages dataset specific overfitting. In addition, strict single reference WER penalizes natural spelling variation in Indian languages, including non standardized spellings of code-mixed English origin words. To address these limitations, we introduce Voice of India, a closed source benchmark… ▽ More Existing Indic ASR benchmarks often use scripted, clean speech and leaderboard driven evaluation that encourages dataset specific overfitting. In addition, strict single reference WER penalizes natural spelling variation in Indian languages, including non standardized spellings of code-mixed English origin words. To address these limitations, we introduce Voice of India, a closed source benchmark built from unscripted telephonic conversations covering 15 major Indian languages across 139 regional clusters. The dataset contains 306230 utterances, totaling 536 hours of speech from 36691 speakers with transcripts accounting for spelling variations. We also analyze performance geographically at the district level, revealing disparities. Finally, we provide detailed analysis across factors such as audio quality, speaking rate, gender, and device type, highlighting where current ASR systems struggle and offering insights for improving real world Indic ASR systems. △ Less

Submitted 3 July, 2026; v1 submitted 21 April, 2026; originally announced April 2026.

Sentiment Analysis of German Sign Language Fairy Tales

Authors: Fabrizio Nunnari, Siddhant Jain, Patrick Gebhard

Abstract: We present a dataset and a model for sentiment analysis of German sign language (DGS) fairy tales. First, we perform sentiment analysis for three levels of valence (negative, neutral, positive) on German fairy tales text segments using four large language models (LLMs) and majority voting, reaching an inter-annotator agreement of 0.781 Krippendorff's alpha. Second, we extract face and body motion… ▽ More We present a dataset and a model for sentiment analysis of German sign language (DGS) fairy tales. First, we perform sentiment analysis for three levels of valence (negative, neutral, positive) on German fairy tales text segments using four large language models (LLMs) and majority voting, reaching an inter-annotator agreement of 0.781 Krippendorff's alpha. Second, we extract face and body motion features from each corresponding DGS video segment using MediaPipe. Finally, we train an explainable model (based on XGBoost) to predict negative, neutral or positive sentiment from video features. Results show an average balanced accuracy of 0.631. A thorough analysis of the most important features reveal that, in addition to eyebrows and mouth motion on the face, also the motion of hips, elbows, and shoulders considerably contribute in the discrimination of the conveyed sentiment, indicating an equal importance of face and body for sentiment communication in sign language. △ Less

Submitted 17 April, 2026; originally announced April 2026.

Listening Alone, Understanding Together: Collaborative Context Recovery for Privacy-Aware AI

Authors: Tanmay Srivastava, Amartya Basu, Shubham Jain, Vaishnavi Ranganathan

Abstract: We introduce CONCORD, a privacy-aware asynchronous assistant-to-assistant (A2A) framework that leverages collaboration between proactive speech-based AI. As agents evolve from reactive to always-listening assistants, they face a core privacy risk (of capturing non-consenting speakers), which makes their social deployment a challenge. To overcome this, we implement CONCORD, which enforces owner-onl… ▽ More We introduce CONCORD, a privacy-aware asynchronous assistant-to-assistant (A2A) framework that leverages collaboration between proactive speech-based AI. As agents evolve from reactive to always-listening assistants, they face a core privacy risk (of capturing non-consenting speakers), which makes their social deployment a challenge. To overcome this, we implement CONCORD, which enforces owner-only speech capture via real-time speaker verification, producing a one-sided transcript that incurs missing context but preserves privacy. We demonstrate that CONCORD can safely recover necessary context through (1) spatio-temporal context resolution, (2) information gap detection, and (3) minimal A2A queries governed by a relationship-aware disclosure. Instead of hallucination-prone inferring, CONCORD treats context recovery as a negotiated safe exchange between assistants. Across a multi-domain dialogue dataset, CONCORD achieves 91.4% recall in gap detection, 96% relationship classification accuracy, and 97% true negative rate in privacy-sensitive disclosure decisions. By reframing always-listening AI as a coordination problem between privacy-preserving agents, CONCORD offers a practical path toward socially deployable proactive conversational agents. △ Less

Submitted 14 April, 2026; originally announced April 2026.

Nemotron 3 Super: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning

Authors: NVIDIA, :, Aakshita Chandiramani, Aaron Blakeman, Abdullahi Olaoye, Abhibha Gupta, Abhilash Somasamudramath, Abhinav Khattar, Adeola Adesoba, Adi Renduchintala, Adil Asif, Aditya Agrawal, Aditya Vavre, Ahmad Kiswani, Aishwarya Padmakumar, Ajay Hotchandani, Akanksha Shukla, Akhiad Bercovich, Aleksander Ficek, Aleksandr Shaposhnikov, Alex Gronskiy, Alex Kondratenko, Alex Neefus, Alex Steiner, Alex Yang , et al. (522 additional authors not shown)

Abstract: We describe the pre-training, post-training, and quantization of Nemotron 3 Super, a 120 billion (active 12 billion) parameter hybrid Mamba-Attention Mixture-of-Experts model. Nemotron 3 Super is the first model in the Nemotron 3 family to 1) be pre-trained in NVFP4, 2) leverage LatentMoE, a new Mixture-of-Experts architecture that optimizes for both accuracy per FLOP and accuracy per parameter, a… ▽ More We describe the pre-training, post-training, and quantization of Nemotron 3 Super, a 120 billion (active 12 billion) parameter hybrid Mamba-Attention Mixture-of-Experts model. Nemotron 3 Super is the first model in the Nemotron 3 family to 1) be pre-trained in NVFP4, 2) leverage LatentMoE, a new Mixture-of-Experts architecture that optimizes for both accuracy per FLOP and accuracy per parameter, and 3) include MTP layers for inference acceleration through native speculative decoding. We pre-trained Nemotron 3 Super on 25 trillion tokens followed by post-training using supervised fine tuning (SFT) and reinforcement learning (RL). The final model supports up to 1M context length and achieves comparable accuracy on common benchmarks, while also achieving up to 2.2x and 7.5x higher inference throughput compared to GPT-OSS-120B and Qwen3.5-122B, respectively. Nemotron 3 Super datasets, along with the base, post-trained, and quantized checkpoints, are open-sourced on HuggingFace. △ Less

Submitted 14 April, 2026; originally announced April 2026.

CatalogStitch: Dimension-Aware and Occlusion-Preserving Object Compositing for Catalog Image Generation

Authors: Sanyam Jain, Pragya Kandari, Manit Singhal, He Zhang, Soo Ye Kim

Abstract: Generative object compositing methods have shown remarkable ability to seamlessly insert objects into scenes. However, when applied to real-world catalog image generation, these methods require tedious manual intervention: users must carefully adjust masks when product dimensions differ, and painstakingly restore occluded elements post-generation. We present CatalogStitch, a set of model-agnostic… ▽ More Generative object compositing methods have shown remarkable ability to seamlessly insert objects into scenes. However, when applied to real-world catalog image generation, these methods require tedious manual intervention: users must carefully adjust masks when product dimensions differ, and painstakingly restore occluded elements post-generation. We present CatalogStitch, a set of model-agnostic techniques that automate these corrections, enabling user-friendly content creation. Our dimension-aware mask computation algorithm automatically adapts the target region to accommodate products with different dimensions; users simply provide a product image and background, without manual mask adjustments. Our occlusion-aware hybrid restoration method guarantees pixel-perfect preservation of occluding elements, eliminating post-editing workflows. We additionally introduce CatalogStitch-Eval, a 58-example benchmark covering aspect-ratio mismatch and occlusion-heavy catalog scenarios, together with supplementary PDF and HTML viewers. We evaluate our techniques with three state-of-the-art compositing models (ObjectStitch, OmniPaint, and InsertAnything), demonstrating consistent improvements across diverse catalog scenarios. By reducing manual intervention and automating tedious corrections, our approach transforms generative compositing into a practical, human-friendly tool for production catalog workflows. △ Less

Submitted 9 April, 2026; originally announced April 2026.

CUE-R: Beyond the Final Answer in Retrieval-Augmented Generation

Authors: Siddharth Jain, Venkat Narayan Vedam

Abstract: As language models shift from single-shot answer generation toward multi-step reasoning that retrieves and consumes evidence mid-inference, evaluating the role of individual retrieved items becomes more important. Existing RAG evaluation typically targets final-answer quality, citation faithfulness, or answer-level attribution, but none of these directly targets the intervention-based, per-evidenc… ▽ More As language models shift from single-shot answer generation toward multi-step reasoning that retrieves and consumes evidence mid-inference, evaluating the role of individual retrieved items becomes more important. Existing RAG evaluation typically targets final-answer quality, citation faithfulness, or answer-level attribution, but none of these directly targets the intervention-based, per-evidence-item utility view we study here. We introduce CUE-R, a lightweight intervention-based framework for measuring per-evidence-item operational utility in single-shot RAG using shallow observable retrieval-use traces. CUE-R perturbs individual evidence items via REMOVE, REPLACE, and DUPLICATE operators, then measures changes along three utility axes (correctness, proxy-based grounding faithfulness, and confidence error) plus a trace-divergence signal. We also outline an operational evidence-role taxonomy for interpreting intervention outcomes. Experiments on HotpotQA and 2WikiMultihopQA with Qwen-3 8B and GPT-5.2 reveal a consistent pattern: REMOVE and REPLACE substantially harm correctness and grounding while producing large trace shifts, whereas DUPLICATE is often answer-redundant yet not fully behaviorally neutral. A zero-retrieval control confirms that these effects arise from degradation of meaningful retrieval. A two-support ablation further shows that multi-hop evidence items can interact non-additively: removing both supports harms performance far more than either single removal. Our results suggest that answer-only evaluation misses important evidence effects and that intervention-based utility analysis is a practical complement for RAG evaluation. △ Less

Submitted 7 April, 2026; originally announced April 2026.

Chart-RL: Policy Optimization Reinforcement Learning for Enhanced Visual Reasoning in Chart Question Answering with Vision Language Models

Authors: Yunfei Bai, Amit Dhanda, Shekhar Jain

Abstract: The recent advancements in Vision Language Models (VLMs) have demonstrated progress toward true intelligence requiring robust reasoning capabilities. Beyond pattern recognition, linguistic reasoning must integrate with visual comprehension, particularly for Chart Question Answering (CQA) tasks involving complex data visualizations. Current VLMs face significant limitations in CQA, including imprec… ▽ More The recent advancements in Vision Language Models (VLMs) have demonstrated progress toward true intelligence requiring robust reasoning capabilities. Beyond pattern recognition, linguistic reasoning must integrate with visual comprehension, particularly for Chart Question Answering (CQA) tasks involving complex data visualizations. Current VLMs face significant limitations in CQA, including imprecise numerical extraction, difficulty interpreting implicit visual relationships, and inadequate attention mechanisms for capturing spatial relationships in charts. In this work, we address these challenges by presenting Chart-RL, a novel reinforcement learning framework that enhances VLMs chart understanding through feedback-driven policy optimization of visual perception and logical inference. Our key innovation includes a comprehensive framework integrating Reinforcement Learning (RL) from Policy Optimization techniques along with adaptive reward functions, that demonstrates superior performance compared to baseline foundation models and competitive results against larger state-of-the-art architectures. We also integrated Parameter-Efficient Fine-Tuning through Low-Rank Adaptation (LoRA) in the RL framework that only requires single GPU configurations while preserving performance integrity. We conducted extensive benchmarking across open-source, proprietary, and state-of-the-art closed-source models utilizing the ChartQAPro dataset. The RL fine-tuned Qwen3-VL-4B-Instruct model achieved an answer accuracy of 0.634, surpassing the 0.580 accuracy of the Qwen3-VL-8B-Instruct foundation model despite utilizing half the parameter count, while simultaneously reducing inference latency from 31 seconds to 9 seconds. △ Less

Submitted 3 April, 2026; originally announced April 2026.

Lipschitz Dueling Bandits over Continuous Action Spaces

Authors: Mudit Sharma, Shweta Jain, Vaneet Aggarwal, Ganesh Ghalme

Abstract: We study for the first time, stochastic dueling bandits over continuous action spaces with Lipschitz structure, where feedback is purely comparative. While dueling bandits and Lipschitz bandits have been studied separately, their combination has remained unexplored. We propose the first algorithm for Lipschitz dueling bandits, using round-based exploration and recursive region elimination guided b… ▽ More We study for the first time, stochastic dueling bandits over continuous action spaces with Lipschitz structure, where feedback is purely comparative. While dueling bandits and Lipschitz bandits have been studied separately, their combination has remained unexplored. We propose the first algorithm for Lipschitz dueling bandits, using round-based exploration and recursive region elimination guided by an adaptive reference arm. We develop new analytical tools for relative feedback and prove a regret bound of $\tilde O\left(T^{\frac{d_z+1}{d_z+2}}\right)$, where $d_z$ is the zooming dimension of the near-optimal region. Further, our algorithm takes only logarithmic space in terms of the total time horizon, best achievable by any bandit algorithm over a continuous action space. △ Less

Submitted 1 April, 2026; originally announced April 2026.

Composer 2 Technical Report

Authors: Cursor Research, :, Aaron Chan, Ahmed Shalaby, Alexander Wettig, Aman Sanger, Andrew Zhai, Anurag Ajay, Ashvin Nair, Charlie Snell, Chen Lu, Chen Shen, Emily Jia, Federico Cassano, Hanpeng Liu, Haoyu Chen, Henry Wildermuth, Jacob Jackson, Janet Li, Jediah Katz, Jiajun Yao, Joey Hejna, Josh Warner, Julius Vering, Kevin Frans , et al. (31 additional authors not shown)

Abstract: Composer 2 is a specialized model designed for agentic software engineering. The model demonstrates strong long-term planning and coding intelligence while maintaining the ability to efficiently solve problems for interactive use. The model is trained in two phases: first, continued pretraining to improve the model's knowledge and latent coding ability, followed by large-scale reinforcement learni… ▽ More Composer 2 is a specialized model designed for agentic software engineering. The model demonstrates strong long-term planning and coding intelligence while maintaining the ability to efficiently solve problems for interactive use. The model is trained in two phases: first, continued pretraining to improve the model's knowledge and latent coding ability, followed by large-scale reinforcement learning to improve end-to-end coding performance through stronger reasoning, accurate multi-step execution, and coherence on long-horizon realistic coding problems. We develop infrastructure to support training in the same Cursor harness that is used by the deployed model, with equivalent tools and structure, and use environments that match real problems closely. To measure the ability of the model on increasingly difficult tasks, we introduce a benchmark derived from real software engineering problems in large codebases including our own. Composer 2 is a frontier-level coding model and demonstrates a process for training strong domain-specialized models. On our CursorBench evaluations the model achieves a major improvement in accuracy compared to previous Composer models (61.3). On public benchmarks the model scores 61.7 on Terminal-Bench and 73.7 on SWE-bench Multilingual in our harness, comparable to state-of-the-art systems. △ Less

Submitted 25 March, 2026; v1 submitted 25 March, 2026; originally announced March 2026.

DetPO: In-Context Learning with Multi-Modal LLMs for Few-Shot Object Detection

Authors: Gautam Rajendrakumar Gare, Neehar Peri, Matvei Popov, Shruti Jain, John Galeotti, Deva Ramanan

Abstract: Multi-Modal LLMs (MLLMs) demonstrate strong visual grounding capabilities on popular object detection benchmarks like OdinW-13 and RefCOCO. However, state-of-the-art models still struggle to generalize to out-of-distribution classes, tasks and imaging modalities not typically found in their pre-training. While in-context prompting is a common strategy to improve performance across diverse tasks, w… ▽ More Multi-Modal LLMs (MLLMs) demonstrate strong visual grounding capabilities on popular object detection benchmarks like OdinW-13 and RefCOCO. However, state-of-the-art models still struggle to generalize to out-of-distribution classes, tasks and imaging modalities not typically found in their pre-training. While in-context prompting is a common strategy to improve performance across diverse tasks, we find that it often yields lower detection accuracy than prompting with class names alone. This suggests that current MLLMs cannot yet effectively leverage few-shot visual examples and rich textual descriptions for object detection. Since frontier MLLMs are typically only accessible via APIs, and state-of-the-art open-weights models are prohibitively expensive to fine-tune on consumer-grade hardware, we instead explore black-box prompt optimization for few-shot object detection. To this end, we propose Detection Prompt Optimization (DetPO), a gradient-free test-time optimization approach that refines text-only prompts by maximizing detection accuracy on few-shot visual training examples while calibrating prediction confidence. Our proposed approach yields consistent improvements across generalist MLLMs on Roboflow20-VL and LVIS, outperforming prior black-box approaches by up to 9.7 mAP. Our code and optimized prompts are available at https://ggare-cmu.github.io/DetPO/ △ Less

Submitted 30 June, 2026; v1 submitted 24 March, 2026; originally announced March 2026.

AGILE: A Comprehensive Workflow for Humanoid Loco-Manipulation Learning

Authors: Huihua Zhao, Rafael Cathomen, Lionel Gulich, Wei Liu, Efe Arda Ongan, Michael Lin, Shalin Jain, Soha Pouya, Yan Chang

Abstract: Recent advances in reinforcement learning (RL) have enabled impressive humanoid behaviors in simulation, yet transferring these results to new robots remains challenging. In many real deployments, the primary bottleneck is no longer simulation throughput or algorithm design, but the absence of systematic infrastructure that links environment verification, training, evaluation, and deployment in a… ▽ More Recent advances in reinforcement learning (RL) have enabled impressive humanoid behaviors in simulation, yet transferring these results to new robots remains challenging. In many real deployments, the primary bottleneck is no longer simulation throughput or algorithm design, but the absence of systematic infrastructure that links environment verification, training, evaluation, and deployment in a coherent loop. To address this gap, we present AGILE, an end-to-end workflow for humanoid RL that standardizes the policy-development lifecycle to mitigate common sim-to-real failure modes. AGILE comprises four stages: (1) interactive environment verification, (2) reproducible training, (3) unified evaluation, and (4) descriptor-driven deployment via robot/task configuration descriptors. For evaluation stage, AGILE supports both scenario-based tests and randomized rollouts under a shared suite of motion-quality diagnostics, enabling automated regression testing and principled robustness assessment. AGILE also incorporates a set of training stabilizations and algorithmic enhancements in training stage to improve optimization stability and sim-to-real transfer. With this pipeline in place, we validate AGILE across five representative humanoid skills spanning locomotion, recovery, motion imitation, and loco-manipulation on two hardware platforms (Unitree G1 and Booster T1), achieving consistent sim-to-real transfer. Overall, AGILE shows that a standardized, end-to-end workflow can substantially improve the reliability and reproducibility of humanoid RL development. △ Less

Submitted 20 March, 2026; originally announced March 2026.

Tursio Database Search: How far are we from ChatGPT?

Authors: Sulbha Jain, Shivani Tripathi, Shi Qiao, Alekh Jindal

Abstract: Business users need to search enterprise databases using natural language, just as they now search the web using ChatGPT or Perplexity. However, existing benchmarks -- designed for open-domain QA or text-to-SQL -- do not evaluate the end-to-end quality of such a search experience. We present an evaluation framework for structured database search that generates realistic banking queries across vary… ▽ More Business users need to search enterprise databases using natural language, just as they now search the web using ChatGPT or Perplexity. However, existing benchmarks -- designed for open-domain QA or text-to-SQL -- do not evaluate the end-to-end quality of such a search experience. We present an evaluation framework for structured database search that generates realistic banking queries across varying difficulty levels and assesses answer quality using relevance, safety, and conversational metrics via an LLM-as-judge approach. We apply this framework to compare Tursio, a database search platform, against ChatGPT and Perplexity on a credit union banking schema. Our results show that Tursio achieves answer relevancy statistically comparable to both baselines (97.8% vs. 98.1% on simple, 90.0% vs. 100.0% on medium, 89.5% vs. 100.0% on hard questions), even though Tursio answers from a structured database while the baselines generate responses from the open web. We analyze the failure modes, identify database completeness as the primary bottleneck, and outline directions for improving both the evaluation methodology and the systems under evaluation. △ Less

Submitted 24 March, 2026; v1 submitted 19 March, 2026; originally announced March 2026.

Conditional Distributional Treatment Effects: Doubly Robust Estimation and Testing

Authors: Saksham Jain, Alex Luedtke

Abstract: Beyond conditional average treatment effects, treatments may impact the entire outcome distribution in covariate-dependent ways, for example, by altering the variance or tail risks for specific subpopulations. We propose a novel estimand to capture such conditional distributional treatment effects, and develop a doubly robust estimator that is minimax optimal in the local asymptotic sense. Using t… ▽ More Beyond conditional average treatment effects, treatments may impact the entire outcome distribution in covariate-dependent ways, for example, by altering the variance or tail risks for specific subpopulations. We propose a novel estimand to capture such conditional distributional treatment effects, and develop a doubly robust estimator that is minimax optimal in the local asymptotic sense. Using this, we develop a test for the global homogeneity of conditional potential outcome distributions that accommodates discrepancies beyond the maximum mean discrepancy (MMD), has provably valid type 1 error, and is consistent against fixed alternatives -- the first test, to our knowledge, with such guarantees in this setting. Furthermore, we derive exact closed-form expressions for two natural discrepancies (including the MMD), and provide a computationally efficient, permutation-free algorithm for our test. △ Less

Submitted 17 March, 2026; originally announced March 2026.

A Comprehensive Benchmark of Histopathology Foundation Models for Kidney Digital Pathology Images

Authors: Harishwar Reddy Kasireddy, Patricio S. La Rosa, Akshita Gupta, Anindya S. Paul, Jamie L. Fermin, William L. Clapp, Meryl A. Waldman, Tarek M. El-Ashkar, Sanjay Jain, Luis Rodrigues, Kuang Yu Jen, Avi Z. Rosenberg, Michael T. Eadon, Jeffrey B. Hodgin, Pinaki Sarder

Abstract: Histopathology foundation models (HFMs), pretrained on large-scale cancer datasets, have advanced computational pathology. However, their applicability to non-cancerous chronic kidney disease remains underexplored, despite coexistence of renal pathology with malignancies such as renal cell and urothelial carcinoma. We systematically evaluate 11 publicly available HFMs across 11 kidney-specific dow… ▽ More Histopathology foundation models (HFMs), pretrained on large-scale cancer datasets, have advanced computational pathology. However, their applicability to non-cancerous chronic kidney disease remains underexplored, despite coexistence of renal pathology with malignancies such as renal cell and urothelial carcinoma. We systematically evaluate 11 publicly available HFMs across 11 kidney-specific downstream tasks spanning multiple stains (PAS, H&E, PASM, and IHC), spatial scales (tile and slide-level), task types (classification, regression, and copy detection), and clinical objectives, including detection, diagnosis, and prognosis. Tile-level performance is assessed using repeated stratified group cross-validation, while slide-level tasks are evaluated using repeated nested stratified cross-validation. Statistical significance is examined using Friedman test followed by pairwise Wilcoxon signed-rank testing with Holm-Bonferroni correction and compact letter display visualization. To promote reproducibility, we release an open-source Python package, kidney-hfm-eval, available at https://pypi.org/project/kidney-hfm-eval/ , that reproduces the evaluation pipelines. Results show moderate to strong performance on tasks driven by coarse meso-scale renal morphology, including diagnostic classification and detection of prominent structural alterations. In contrast, performance consistently declines for tasks requiring fine-grained microstructural discrimination, complex biological phenotypes, or slide-level prognostic inference, largely independent of stain type. Overall, current HFMs appear to encode predominantly static meso-scale representations and may have limited capacity to capture subtle renal pathology or prognosis-related signals. Our results highlight the need for kidney-specific, multi-stain, and multimodal foundation models to support clinically reliable decision-making in nephrology. △ Less

Submitted 18 March, 2026; v1 submitted 16 March, 2026; originally announced March 2026.

UniMotion: Self-Supervised Learning for Cross-Domain IMU Motion Recognition

Authors: Prerna Khanna, Tanmay Srivastava, Shubham Jain, Aruna Balasubramanian

Abstract: IMU-based gesture interfaces are being increasingly adopted as efficient, accessible, and intuitive alternatives to traditional input methods, such as touchscreens and voice. However, current gesture recognition algorithms are tailored to work for specific devices (e.g., smartwatches vs. earbuds) or user populations (e.g., blind vs. sighted users), limiting their generalizability. In this paper, w… ▽ More IMU-based gesture interfaces are being increasingly adopted as efficient, accessible, and intuitive alternatives to traditional input methods, such as touchscreens and voice. However, current gesture recognition algorithms are tailored to work for specific devices (e.g., smartwatches vs. earbuds) or user populations (e.g., blind vs. sighted users), limiting their generalizability. In this paper, we design UniMotion, a generalized IMU-based gesture recognition framework that works across devices and populations with minimal training samples. To overcome the challenges and high cost of collecting large-scale labeled training data, UniMotion leverages readily available unlabeled human activity data. The UniMotion pipeline comprises two stages: (1) pre-training a motion representation model using abundant unlabeled human activity data, and (2) fine-tuning it with a small amount of labeled gesture data. For pre-training, we introduce a token-based strategy and embeddings that learn to identify and focus attention on the key motion signatures in the temporal data For fine-tuning, we design a text-guided classifier that can reliably differentiate between temporally or semantically similar gestures. We evaluate UniMotion across both hand gestures (captured through a smartwatch) and earbud gestures (captured through earbuds), using data collected from blind and sighted users. Across these diverse devices and user populations, UniMotion achieves an accuracy of 85\%, across an average of 13 gesture classes using only 10\% of labeled data for training. UniMotion significantly outperforms state-of-the-art self-supervised learning approaches and specialized gesture recognition models. △ Less

Submitted 12 March, 2026; originally announced March 2026.