Showing 1–50 of 153 results for author: Mittal, A

TextNCA: Neural Cellular Automata for Language Modeling via Hierarchical Local Attention

Authors: Avni Mittal, Avinash Anand, Ashutosh Kumar, Dikshant Kukreja, Kritarth Prasad, Sushane Dulloo, Erik Cambria, Timothy Liu, Zhengkui Wang, Rajiv Ratn Shah

Abstract: Can a strictly local, iterated, weight-shared computation primitive support language modelling, and which of those three properties actually drives the model's behaviour? We define \textsc{TextNCA}, a 1D causal windowed-attention realisation of the Neural Cellular Automaton primitive, and study a hierarchical variant that cascades three stages with windows $w \in \{8, 32, 128\}$ and $T_s$ shared-w… ▽ More Can a strictly local, iterated, weight-shared computation primitive support language modelling, and which of those three properties actually drives the model's behaviour? We define \textsc{TextNCA}, a 1D causal windowed-attention realisation of the Neural Cellular Automaton primitive, and study a hierarchical variant that cascades three stages with windows $w \in \{8, 32, 128\}$ and $T_s$ shared-weight iterations per stage, all on WikiText-103 at roughly 30M parameters and 60k training steps. The model does not match a parameter-matched Transformer at this scale (Hier-TextNCA $60.3$ vs.\ Transformer-6L $52.8$ and Transformer-12L $44.7$ PPL), so we treat it as an analytical probe rather than a proposed alternative. The behaviour we observe is largely explained by the staged narrow-to-wide schedule: a non-iterating sliding-window Transformer that reuses the same schedule comes within $+4.1$ PPL of the iterated model, while reversing, flattening, or breaking the monotonic ordering of the schedule costs between $+16.7$ and $+70.8$ PPL. Iteration adds a smaller bounded benefit on top of the schedule, with a clear optimum at $T_s{=}4$ and a U-shaped degradation beyond it. The GRU gate and learned per-step embeddings are required for that benefit to appear, and training with random $T_s$ yields an inference-time iteration-count knob at the cost of substantially higher absolute PPL. We position the work as a controlled reading of which parts of NCA-style computation carry the weight in language modelling. △ Less

Submitted 3 August, 2026; originally announced August 2026.

HumanCLAW: Can Vision-Language Models Act Through a Body?

Authors: Li Siyao, Jiawei Gu, Shuai Liu, Kairui Hu, Zekun Li, Linjie Li, Chengcheng Tang, Po-Chen Wu, Ivan Shugurov, Lingni Ma, Michael Zollhoefer, Sizhe An, Abhay Mittal, Amy Zhao, Ranjay Krishna, Manling Li, Ziwei Liu, Chuan Guo

Abstract: Evaluating whether a vision-language model (VLM) can act through a physical body is challenging. The outcome of an action couples the VLM's decision with motor control. When a task fails, it is hard to tell whether the VLM made a bad choice or the motor controller simply failed to execute it, e.g., losing balance and falling. In this work, we introduce HumanCLAW, an evaluation framework that decou… ▽ More Evaluating whether a vision-language model (VLM) can act through a physical body is challenging. The outcome of an action couples the VLM's decision with motor control. When a task fails, it is hard to tell whether the VLM made a bad choice or the motor controller simply failed to execute it, e.g., losing balance and falling. In this work, we introduce HumanCLAW, an evaluation framework that decouples action decision-making from low-level execution. At every step, a harnessed, off-the-shelf VLM issues an atomic skill command, and the command is translated into a sub-second chunk of continuous full-body motion with real physical consequences, including gravity and collisions. The body can therefore act freely in the physical world, while execution-side disturbances, balance and motor errors, are factored out. What remains measurable is the model's action intelligence: its moment-to-moment choice of what the body should execute next. Based on this framework, we build HumanCLAW-Bench: 1,218 long-horizon, egocentric find-navigate-interact episodes across 41 indoor scenes. We test nine state-of-the-art VLMs and find that none solves the benchmark; the best model reaches only a 16.8% success rate. Recognizing the target is not the bottleneck. What current VLMs lack is embodied self-awareness: they lose track of their own body, failing to tell where it is, whether it has reached the goal, or whether it has hit an obstacle. △ Less

Submitted 3 August, 2026; v1 submitted 29 July, 2026; originally announced July 2026.

Comments: Project page: https://human-claw.github.io/

Ms. Forcing: Efficient Streaming Video Generation with Multi-Scale Patchification and Attention

Authors: Zekun Li, Xiaoyan Cong, Hongyu Li, Zhiyang Dou, Chuan Guo, Abhay Mittal, Sizhe An, Srinath Sridhar

Abstract: Streaming video diffusion models have made substantial progress toward interactive and dynamic world simulation, but the nested autoregressive and denoising loops of conventional next-frame generation hinder real-time deployment. Recent rolling-window methods pipeline denoising across multiple consecutive frames at different noise levels, improving throughput and long-horizon stability. However, t… ▽ More Streaming video diffusion models have made substantial progress toward interactive and dynamic world simulation, but the nested autoregressive and denoising loops of conventional next-frame generation hinder real-time deployment. Recent rolling-window methods pipeline denoising across multiple consecutive frames at different noise levels, improving throughput and long-horizon stability. However, they tokenize every state at the same fine spatial granularity, leaving substantial noise-dependent redundancy in the joint denoising window. We propose Ms.Forcing, an efficient streaming video generation paradigm that adapts spatial granularity to each state's noise level. Its Multi-Scale Patchification (MSP) assigns coarser patches to noisier states, reducing the active-window token count by 45%, while Multi-Scale Self-Attention (MSSA) matches the density of visible non-sink keys and values to each query scale to further reduce attention cost. Because both schedules are fixed by window position, Ms.Forcing retains a static, hardware-friendly computation graph. We further introduce Homogeneous-Noise-Level DMD (H-DMD), which assembles each fake video from clean predictions sharing the same source noise level, thereby reducing the mismatch between DMD training sequences and inference-time rollouts. The multi-scale design helps offset the additional training cost of backpropagating through overlapping windows. We include both quantitative and qualitative experiments to show that Ms.Forcing reaches 22.84 FPS on a single H200 GPU, 39.6% faster than Rolling Forcing, while significantly improving VBench scores in both short video and long video generation setting. △ Less

Submitted 23 July, 2026; originally announced July 2026.

Can LLMs Perform Deep Technical Comprehension of Computer Architecture Papers?

Authors: Nishant Aggarwal, Ayushi Dubal, Sreeraj Kannakarankodi, Ian McDougall, Adarsh Mittal, Vishnu Ramadas, Noah Scott, Ranganath Selagamsetty, Weichu Yang, Karthikeyan Sankaralingam

Abstract: Can large language models perform deep technical comprehension of computer architecture papers -- not summarization, but structured critique that names the core mechanism, surfaces buried assumptions, and connects a contribution beyond its own scope? We study Gauntlet, an open-source pipeline that analyzes a paper through five independent expert-persona reviewers and an adversarial synthesis stage… ▽ More Can large language models perform deep technical comprehension of computer architecture papers -- not summarization, but structured critique that names the core mechanism, surfaces buried assumptions, and connects a contribution beyond its own scope? We study Gauntlet, an open-source pipeline that analyzes a paper through five independent expert-persona reviewers and an adversarial synthesis stage. On 20 ISCA 2025 and HPCA 2026 papers, ten researchers each wrote their own analyses and then judged, for papers other than their own, the human analysis against Gauntlet's. Across the 20 comparisons evaluators preferred Gauntlet in 15 (human in 4, one tie); its advantage is significant on per-analyst totals (paired Wilcoxon, p < 0.01) and largest on Critical Rigor, vanishing only on Calibration. Where humans win, it is on trust and usefulness rather than depth: a confident wrong claim, a mechanism described but not taught, or unprioritized breadth. A 98-paper automated ablation shows the gain comes from the multi-agent structure -- the pipeline beats the same model run as a single rich-persona agent on 96% of papers -- and specifically from its synthesis pass. We release all analyses, scores, and the rubric as a community resource. △ Less

Submitted 13 July, 2026; originally announced July 2026.

Comments: 4 pages, 1 figure

Aleena: Alignment Agent for Research Software Engineering Collaborations

Authors: Kshitij Dani, Cordero Core, Landung Setiawan, Carlos Garcia Jurado Suarez, Anshul Tambay, Vani Mandava, Anant Mittal

Abstract: Research software collaborations span meetings, informal chats, pull requests, and GitHub issues. A decision surfaced in a Slack thread, refined in a meeting, and implemented in a pull request can lose its original rationale across these artifacts, leaving domain researchers and research software engineers with divergent mental models of project intent, ownership, and scientific assumptions. We ar… ▽ More Research software collaborations span meetings, informal chats, pull requests, and GitHub issues. A decision surfaced in a Slack thread, refined in a meeting, and implemented in a pull request can lose its original rationale across these artifacts, leaving domain researchers and research software engineers with divergent mental models of project intent, ownership, and scientific assumptions. We argue that alignment in research software engineering is a continuous lifecycle problem, and that agentic AI can support stakeholder alignment and project-state tracking without replacing human decision-making. We present Aleena, an open-source lifecycle alignment agent that uses GitHub as a shared collaboration surface, transforming multi-modal stakeholder interactions into structured project records that surface risks, track open questions, and preserve decision continuity. Grounded in university-based research software engineering center experiences, this paper presents the motivating problem, system design, prototype, and illustrative lifecycle scenarios for Aleena. △ Less

Submitted 8 July, 2026; originally announced July 2026.

Comments: 8 pages, 5 figures. AgenticSE @ KDD '26: Agentic Software Engineering (SE 3.0): The Rise of AI Teammates, KDD 2026 Workshop

LLMoxie: Exploring Agentic AI for Scientific Software Development

Authors: Landung Setiawan, Anant Mittal, Cordero Core, Anshul Tambay, Carlos Garcia Jurado Suarez, David A. C. Beck, Andrew J. Connolly, Vani Mandava

Abstract: In this paper, we describe LLMoxie, an institutional AI platform whose three-tiered architecture supports multi-cloud and on-premise inference, a LiteLLM/MLflow control plane for authentication, budgeting, PII masking, and observability, and an application augmentation layer for AI coding agents. Layered on top, an open-source RSE-Plugins ecosystem encodes accumulated RSE knowledge as a Plugin-Age… ▽ More In this paper, we describe LLMoxie, an institutional AI platform whose three-tiered architecture supports multi-cloud and on-premise inference, a LiteLLM/MLflow control plane for authentication, budgeting, PII masking, and observability, and an application augmentation layer for AI coding agents. Layered on top, an open-source RSE-Plugins ecosystem encodes accumulated RSE knowledge as a Plugin-Agent-Skill hierarchy spanning scientific Python practice, domain-specific knowledge, a six-phase research-and-implement workflow, and project lifecycle management. Scientific software is judged less by raw code quality than by whether it can be cited, audited, reproduced, and extended. Off-the-shelf AI coding agents, optimized against commercial software benchmarks, are poorly calibrated for this setting: they ignore the conventions of the scientific Python libraries they invoke, mishandle sensitive or embargoed data, and leave decision trails that are difficult to reconstruct after the fact. We report on twenty months of practice at a university-based research software engineering (RSE) center, where RSEs embedded across astronomy, earth and climate science, agriculture, and health projects worked to close this gap. We characterize the recurring infrastructure, governance, and process challenges of adopting Agentic AI inside a multi-domain RSE center, describe the platform and plugin design, and distill operational lessons from real scientific software deployments. Together, the platform and plugins shift AI coding agents from generic code generators into domain-aware collaborators that respect community norms and produce auditable provenance of technical reasoning. △ Less

Submitted 2 July, 2026; originally announced July 2026.

Comments: 9 pages, 4 figures. Accepted to ACM SIGKDD 2026 Workshop: Agentic AI for Scientific and Societal Advances (SciSoc Agents and LLMs). Describes an agentic AI platform for scientific software engineering with governed multi-cloud inference, structured multiagent workflows, and domain-aware coding support (cs.SE, cs.MA, cs.AI)

Triadic Werewolf: A Jester Role for Multi-Hop Theory of Mind in LLMs

Authors: Avni Mittal

Abstract: Theory-of-mind evaluations of large language models typically use dyadic social-deduction games, where every observable cue points to a single hidden side, so a model with strong language priors can score well without ever simulating opponents' incentives. We extend the Werewolf game with a Jester, a third faction whose utility on peer suspicion is inverted because it wins by being voted out, so o… ▽ More Theory-of-mind evaluations of large language models typically use dyadic social-deduction games, where every observable cue points to a single hidden side, so a model with strong language priors can score well without ever simulating opponents' incentives. We extend the Werewolf game with a Jester, a third faction whose utility on peer suspicion is inverted because it wins by being voted out, so optimal play requires reasoning across three opposing utility functions. Across 60 games on GPT-4.1, DeepSeek-V3.1, and Llama-3.3-70B with Jester self-learning on and off, the Jester wins 60-70% of games while Werewolves never exceed 20%, and GPT-4.1 wolves vote the Jester out on day 1 in 60-70% of games, a strictly self-defeating action. Self-learning helps DeepSeek and Llama but hurts GPT-4.1, with the cost landing on Villagers rather than Werewolves. Only DeepSeek learns the subtle strategy of looking suspicious without looking intentionally suspicious, and it gains the most from the loop. Triadic incentive structure exposes a layer of multi-agent reasoning that dyadic deduction games leave invisible. △ Less

Submitted 26 June, 2026; originally announced June 2026.

The Periodic Table of LLM Reasoning: A Structured Survey of Reasoning Paradigms, Methods, and Failure Modes

Authors: Avinash Anand, Mahisha Ramesh, Avni Mittal, Ashutosh Kumar, Rishitej Reddy Vyalla, Erik Cambria, Zhengkui Wang, Timothy Liu, Aik Beng Ng, Simon See, Rajiv Ratn Shah

Abstract: Reasoning has become central to how Large Language Models (LLMs) are evaluated and interpreted, spanning Chain-of-Thought (CoT), mathematical problem-solving, multi-hop question answering, code generation, retrieval-augmented reasoning, tool use, and multimodal decision-making. In this survey, we introduce the Periodic Table of LLM Reasoning, a framework organizing 300+ recent papers by reasoning… ▽ More Reasoning has become central to how Large Language Models (LLMs) are evaluated and interpreted, spanning Chain-of-Thought (CoT), mathematical problem-solving, multi-hop question answering, code generation, retrieval-augmented reasoning, tool use, and multimodal decision-making. In this survey, we introduce the Periodic Table of LLM Reasoning, a framework organizing 300+ recent papers by reasoning paradigm, methodological mechanism, evaluation setting, and failure mode. We classify LLM reasoning into nine paradigms: Chain-of-Thought, Multi-Hop, Mathematical, Commonsense, Visual and Temporal, Code and Algorithmic, Retrieval-Augmented, Tool-Augmented or Agentic, and Reinforcement Learning-based reasoning. For each, we review approaches, including prompting, architectural interventions, supervised fine-tuning, verifier-guided inference, reward modeling, retrieval, tool interfaces, agentic workflows, and benchmark design. We argue that LLM reasoning is not a single emergent capability but a family of scaffolded behaviors shaped by model scale, task structure, external memory, supervision, and evaluation protocols. We synthesize recurring failure modes, including hallucinated reasoning, brittle multi-step inference, spurious rationales, weak causal grounding, poor out-of-distribution generalization, benchmark contamination, and unreliable self-verification. Progress is difficult to compare across paradigms because gains may arise from prompting, retrieval, verifier design, or benchmark structure rather than general reasoning ability. The survey connects methods to their assumptions, strengths, and failure modes, providing a reference map of the field and a diagnostic framework for future work. We conclude that robust LLM reasoning will require meta-reasoning, multimodal and temporal grounding, adaptive tool use, and principled evaluation under distribution shift. △ Less

Submitted 10 August, 2026; v1 submitted 9 June, 2026; originally announced June 2026.

Signed Compression Progress on a Sealed Audit is Goodhart-Resistant

Authors: Ayush Mittal, Dhruv Gupta

Abstract: Compression progress is a long-standing proposal for intrinsic motivation: reward an agent when its world model becomes better at predicting or compressing experience. The folk claim is that this reward is "credible" because it is paid only for learning. We make this precise and prove it. If intrinsic reward is the signed decrease of a fixed sealed-audit loss, r_t = E(theta_{t-1}) - E(theta_t), th… ▽ More Compression progress is a long-standing proposal for intrinsic motivation: reward an agent when its world model becomes better at predicting or compressing experience. The folk claim is that this reward is "credible" because it is paid only for learning. We make this precise and prove it. If intrinsic reward is the signed decrease of a fixed sealed-audit loss, r_t = E(theta_{t-1}) - E(theta_t), then cumulative reward telescopes exactly to endpoint audit improvement, so no policy can push reward up indefinitely while true audit performance stagnates or degrades. For finite audit panels the same result holds with a sharp false-positive budget: cumulative empirical reward is at most true audit improvement plus 2 Delta_n(F, delta), the uniform audit deviation of the model class. This is horizon-free: adaptivity over time costs nothing once the sealed panel uniformly controls the class. The theorem also identifies the failure modes: the guarantee disappears if progress is clipped, scored on the agent's own stream, exposed to a high-capacity model on a reusable panel, or applied to a neural class that makes Delta_n vacuous. We give a Lean 4 mechanization of the structural core (telescoping, the finite-audit bound, finite Gibbs, and the entropy floor) and an experiment suite on ARC-TGI grid-transformation generators with adaptive holdout attacks. Experiments confirm the theory: finite-audit deviation scales as n^{-0.527}; signed progress resists clip-farming, stream leakage, and noisy-TV curiosity; naive reusable audits are exploitable by black-box scalar feedback, while standard release defenses keep the attack below the 2 Delta_n threshold. Signed compression progress on a sealed audit is an accounting signal of genuine improvement. △ Less

Submitted 9 June, 2026; originally announced June 2026.

Comments: 16 pages, 7 figures. Lean 4 (Mathlib) mechanized core and ARC-TGI experiment code: https://github.com/Zetetic-Dhruv/audit-compression-progress

Jailbreaking Vision-Language Models Through the Visual Modality

Authors: Aharon Azulay, Jan Dubiński, Zhuoyun Li, Atharv Mittal, Yossi Gandelsman

Abstract: The visual modality of vision-language models (VLMs) is an underexplored attack surface for bypassing safety alignment. We introduce four jailbreak attacks exploiting the vision component: (1) encoding harmful instructions as visual symbol sequences with a decoding legend, (2) replacing harmful objects with benign substitutes (e.g., bomb -> banana) then prompting for harmful actions using the subs… ▽ More The visual modality of vision-language models (VLMs) is an underexplored attack surface for bypassing safety alignment. We introduce four jailbreak attacks exploiting the vision component: (1) encoding harmful instructions as visual symbol sequences with a decoding legend, (2) replacing harmful objects with benign substitutes (e.g., bomb -> banana) then prompting for harmful actions using the substitute term, (3) replacing harmful text in images (e.g., on book covers) with benign words while visual context preserves the original meaning, and (4) visual analogy puzzles whose solution requires inferring a prohibited concept. Evaluating across six frontier VLMs, our visual attacks bypass safety alignment and expose a cross-modality alignment gap: text-based safety training does not automatically generalize to harmful intent conveyed visually. For example, our visual cipher achieves 40.9% attack success on Claude-Haiku-4.5 versus 10.7% for an equivalent textual cipher. To further our insight into the attack mechanism, we present preliminary interpretability and mitigation results. These findings highlight that robust VLM alignment requires treating vision as a first-class target for safety post-training. △ Less

Submitted 1 May, 2026; originally announced May 2026.

Comments: Accepted to ICML 2026

Agent Name Service (ANS): A Proof-of-Concept Trust Layer for Secure AI Agent Discovery, Identity, and Governance in Kubernetes

Authors: Akshay Mittal, Elyson De La Cruz

Abstract: Autonomous AI agent ecosystems require stronger mechanisms for secure discovery, identity verification, capability attestation, and policy governance. Current deployments frequently lack (1) uniform agent discovery, (2) cryptographic agent authentication, (3) capability proofs that protect secrets, and (4) enforceable policy controls. This paper presents an implementation-oriented proof of concept… ▽ More Autonomous AI agent ecosystems require stronger mechanisms for secure discovery, identity verification, capability attestation, and policy governance. Current deployments frequently lack (1) uniform agent discovery, (2) cryptographic agent authentication, (3) capability proofs that protect secrets, and (4) enforceable policy controls. This paper presents an implementation-oriented proof of concept for the Agent Name Service (ANS), a DNS-inspired trust layer for AI agent discovery and interoperability in Kubernetes, grounded in the ANS protocol specification~\cite{huang2025ans}. The implementation uses Decentralized Identifiers (DIDs), Verifiable Credentials (VCs), policy-as-code enforcement with Open Policy Agent (OPA), and Kubernetes-native integration patterns (CRDs, admission controls, service mesh integration). In a demo research environment (3-node cluster, 50-agent workflow simulation), we observe sub-10ms response in demonstrated service paths and full success for scripted demo deployment scenarios. We explicitly scope these findings as proof-of-concept evidence rather than production certification. We further provide a threat model, assumptions, and limitations to separate implemented evidence from protocol-defined and roadmap capabilities. The result is an evidence-grounded pathway from ANS protocol concepts to reproducible engineering practice for secure multi-agent systems. △ Less

Submitted 28 April, 2026; originally announced April 2026.

Comments: 9 pages, 2 figures

IAM: Identity-Aware Human Motion and Shape Joint Generation

Authors: Wenqi Jia, Zekun Li, Abhay Mittal, Chengcheng Tang, Chuan Guo, Lezi Wang, James Matthew Rehg, Lingling Tao, Size An

Abstract: Recent advances in text-driven human motion generation enable models to synthesize realistic motion sequences from natural language descriptions. However, most existing approaches assume identity-neutral motion and generate movements using a canonical body representation, ignoring the strong influence of body morphology on motion dynamics. In practice, attributes such as body proportions, mass dis… ▽ More Recent advances in text-driven human motion generation enable models to synthesize realistic motion sequences from natural language descriptions. However, most existing approaches assume identity-neutral motion and generate movements using a canonical body representation, ignoring the strong influence of body morphology on motion dynamics. In practice, attributes such as body proportions, mass distribution, and age significantly affect how actions are performed, and neglecting this coupling often leads to physically inconsistent motions. We propose an identity-aware motion generation framework that explicitly models the relationship between body morphology and motion dynamics. Instead of relying on explicit geometric measurements, identity is represented using multimodal signals, including natural language descriptions and visual cues. We further introduce a joint motion-shape generation paradigm that simultaneously synthesizes motion sequences and body shape parameters, allowing identity cues to directly modulate motion dynamics. Extensive experiments on motion capture datasets and large-scale in-the-wild videos demonstrate improved motion realism and motion-identity consistency while maintaining high motion quality. Project page: https://vjwq.github.io/IAM △ Less

Submitted 27 April, 2026; originally announced April 2026.

JTPRO: A Joint Tool-Prompt Reflective Optimization Framework for Language Agents

Authors: Sandip Ghoshal, Anshul Mittal, Jyotika Singh, Miguel Ballesteros, Weiyi Sun, Fang Tu, Shailender Singh, Yassine Benajiba, Fahad Shah, Sujeeth Bharadwaj, Sujith Ravi, Dan Roth

Abstract: Large language model (LLM) agents augmented with external tools often struggle as number of tools grow large and become domain-specific. In such settings, ambiguous tool descriptions and under-specified agent instructions frequently lead to tool mis-selection and incorrect slot/value instantiation. We hypothesize that this is due to two root causes: generic, one-size-fits-all prompts that ignore t… ▽ More Large language model (LLM) agents augmented with external tools often struggle as number of tools grow large and become domain-specific. In such settings, ambiguous tool descriptions and under-specified agent instructions frequently lead to tool mis-selection and incorrect slot/value instantiation. We hypothesize that this is due to two root causes: generic, one-size-fits-all prompts that ignore tool-specific nuances, and underspecified tool schemas that lack clear guidance on when and how to use each tool and how to format its parameters. We introduce Joint Tool-Prompt Reflective Optimization (JTPRO), a framework for improving tool-calling reliability in trace-supervised settings by iteratively using rollout-driven reflection to co-optimize global instructions and per-tool schema/argument descriptions for accurate tool selection and argument instantiation in large tool inventories. JTPRO is designed to preserve only tool-local cues needed for correct disambiguation and slot filling. We evaluate JTPRO across multi-tool benchmarks, which account for different number of tools using three metrics: Tool Selection Accuracy (TSA), Slot Filling Accuracy(SFA), and Overall Success Rate(OSR) (correct tool + correct slots + correct values). JTPRO consistently outperforms strong baselines, including CoT-style agents, and reflective prompt optimizers such as GEPA by 5%-20% (relative) on OSR. Ablations show that joint optimization of instructions and tool schemas is more effective and robust than optimizing either component in isolation. △ Less

Submitted 20 April, 2026; originally announced April 2026.

Comments: Conference: ACL-2026

Do LLMs Follow Their Own Rules? A Reflexive Audit of Self-Stated Safety Policies

Authors: Avni Mittal

Abstract: LLMs internalize safety policies through RLHF, yet these policies are never formally specified and remain difficult to inspect. Existing benchmarks evaluate models against external standards but do not measure whether models understand and enforce their own stated boundaries. We introduce the Symbolic-Neural Consistency Audit (SNCA), a framework that (1) extracts a model's self-stated safety rules… ▽ More LLMs internalize safety policies through RLHF, yet these policies are never formally specified and remain difficult to inspect. Existing benchmarks evaluate models against external standards but do not measure whether models understand and enforce their own stated boundaries. We introduce the Symbolic-Neural Consistency Audit (SNCA), a framework that (1) extracts a model's self-stated safety rules via structured prompts, (2) formalizes them as typed predicates (Absolute, Conditional, Adaptive), and (3) measures behavioral compliance via deterministic comparison against harm benchmarks. Evaluating four frontier models across 45 harm categories and 47,496 observations reveals systematic gaps between stated policy and observed behavior: models claiming absolute refusal frequently comply with harmful prompts, reasoning models achieve the highest self-consistency but fail to articulate policies for 29% of categories, and cross-model agreement on rule types is remarkably low (11%). These results demonstrate that the gap between what LLMs say and what they do is measurable and architecture-dependent, motivating reflexive consistency audits as a complement to behavioral benchmarks. △ Less

Submitted 10 April, 2026; originally announced April 2026.

Litmus (Re)Agent: A Benchmark and Agentic System for Predictive Evaluation of Multilingual Models

Authors: Avni Mittal, Shanu Kumar, Sandipan Dandapat, Monojit Choudhury

Abstract: We study predictive multilingual evaluation: estimating how well a model will perform on a task in a target language when direct benchmark results are missing. This problem is common in multilingual deployment, where evaluation coverage is sparse and published evidence is uneven across languages, tasks, and model families. We introduce a controlled benchmark of 1,500 questions spanning six tasks a… ▽ More We study predictive multilingual evaluation: estimating how well a model will perform on a task in a target language when direct benchmark results are missing. This problem is common in multilingual deployment, where evaluation coverage is sparse and published evidence is uneven across languages, tasks, and model families. We introduce a controlled benchmark of 1,500 questions spanning six tasks and five evidence scenarios. The benchmark separates accessible evidence from ground truth, enabling evaluation of systems that must infer missing results from incomplete literature evidence. We also present Litmus (Re)Agent, a DAG-orchestrated agentic system that decomposes queries into hypotheses, retrieves evidence, and synthesises predictions through feature-aware aggregation. Across six systems, Litmus (Re)Agent achieves the best overall performance, with the largest gains in transfer-heavy scenarios where direct evidence is weak or absent. These results show that structured agentic reasoning is a promising approach to multilingual performance estimation under incomplete evidence. △ Less

Submitted 10 April, 2026; originally announced April 2026.

Comparing Developer and LLM Biases in Code Evaluation

Authors: Aditya Mittal, Ryan Shar, Zichu Wu, Shyam Agarwal, Tongshuang Wu, Chris Donahue, Ameet Talwalkar, Wayne Chi, Valerie Chen

Abstract: As LLMs are increasingly used as judges in code applications, they should be evaluated in realistic interactive settings that capture partial context and ambiguous intent. We present TRACE (Tool for Rubric Analysis in Code Evaluation), a framework that evaluates LLM judges' ability to predict human preferences and automatically extracts rubric items to reveal systematic biases in how humans and mo… ▽ More As LLMs are increasingly used as judges in code applications, they should be evaluated in realistic interactive settings that capture partial context and ambiguous intent. We present TRACE (Tool for Rubric Analysis in Code Evaluation), a framework that evaluates LLM judges' ability to predict human preferences and automatically extracts rubric items to reveal systematic biases in how humans and models weigh each item. Across three modalities -- chat-based programming, IDE autocompletion, and instructed code editing -- we use TRACE to measure how well LLM judges align with developer preferences. Among 13 different models, the best judges underperform human annotators by 12-23%. TRACE identifies 35 significant sources of misalignment between humans and judges across interaction modalities, the majority of which correspond to existing software engineering code quality criteria. For example, in chat-based coding, judges are biased towards longer code explanations while humans prefer shorter ones. We find significant misalignment on the majority of existing code quality dimensions, showing alignment gaps between LLM judges and human preference in realistic coding applications. △ Less

Submitted 14 May, 2026; v1 submitted 25 March, 2026; originally announced March 2026.

Did You Forget What I Asked? Prospective Memory Failures in Large Language Models

Authors: Avni Mittal

Abstract: Large language models often fail to satisfy formatting instructions when they must simultaneously perform demanding tasks. We study this behaviour through a prospective memory inspired lens from cognitive psychology, using a controlled paradigm that combines verifiable formatting constraints with benchmark tasks of increasing complexity. Across three model families and over 8,000 prompts, complian… ▽ More Large language models often fail to satisfy formatting instructions when they must simultaneously perform demanding tasks. We study this behaviour through a prospective memory inspired lens from cognitive psychology, using a controlled paradigm that combines verifiable formatting constraints with benchmark tasks of increasing complexity. Across three model families and over 8,000 prompts, compliance drops by 2-21% under concurrent task load. Vulnerability is highly type-dependent: terminal constraints (requiring action at the response boundary) degrade most, with drops up to 50%, while avoidance constraints remain comparatively robust. A salience-enhanced format (explicit instruction framing plus a trailing reminder) recovers much of the lost compliance, restoring performance to 90-100% in many settings. Interference is bidirectional: formatting constraints can also reduce task accuracy, with one model's GSM8K accuracy dropping from 93% to 27%. In additional stacking experiments, joint compliance declines sharply as constraints accumulate. All results use deterministic programmatic checkers without an LLM-as-judge component on publicly available datasets. △ Less

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

UMO: Unified In-Context Learning Unlocks Motion Foundation Model Priors

Authors: Xiaoyan Cong, Zekun Li, Zhiyang Dou, Hongyu Li, Omid Taheri, Chuan Guo, Abhay Mittal, Sizhe An, Taku Komura, Wojciech Matusik, Michael J. Black, Srinath Sridhar

Abstract: Large-scale foundation models (LFMs) have recently made impressive progress in text-to-motion generation by learning strong generative priors from massive 3D human motion datasets and paired text descriptions. However, how to effectively and efficiently leverage such single-purpose motion LFMs, i.e., text-to-motion synthesis, in more diverse cross-modal and in-context motion generation downstream… ▽ More Large-scale foundation models (LFMs) have recently made impressive progress in text-to-motion generation by learning strong generative priors from massive 3D human motion datasets and paired text descriptions. However, how to effectively and efficiently leverage such single-purpose motion LFMs, i.e., text-to-motion synthesis, in more diverse cross-modal and in-context motion generation downstream tasks remains largely unclear. Prior work typically adapts pretrained generative priors to individual downstream tasks in a task-specific manner. In contrast, our goal is to unlock such priors to support a broad spectrum of downstream motion generation tasks within a single unified framework. To bridge this gap, we present UMO, a simple yet general unified formulation that casts diverse downstream tasks into compositions of atomic per-frame operations, enabling in-context adaptation to unlock the generative priors of pretrained DiT-based motion LFMs. Specifically, UMO introduces three learnable frame-level meta-operation embeddings to specify per-frame intent and employs lightweight temporal fusion to inject in-context cues into the pretrained backbone, with negligible runtime overhead compared to the base model. With this design, UMO finetunes the pretrained model, originally limited to text-to-motion generation, to support diverse previously unsupported tasks, including temporal inpainting, text-guided motion editing, text-serialized geometric constraints, and multi-identity reaction generation. Experiments demonstrate that UMO consistently outperforms task-specific and training-free baselines across a wide range of benchmarks, despite using a single unified model. Code and model will be publicly available. Project Page: https://oliver-cong02.github.io/UMO.github.io/ △ Less

Submitted 16 March, 2026; originally announced March 2026.

Comments: Project Page: https://oliver-cong02.github.io/UMO.github.io/

C2-Faith: Benchmarking LLM Judges for Causal and Coverage Faithfulness in Chain-of-Thought Reasoning

Authors: Avni Mittal, Rauno Arike

Abstract: Large language models (LLMs) are increasingly used as judges of chain-of-thought (CoT) reasoning, yet it remains unclear whether they can reliably assess process faithfulness rather than merely answer plausibility. We introduce C2-Faith, a benchmark built from PRM800K that explicitly decomposes faithfulness into two complementary dimensions: causality (whether each step logically follows from prio… ▽ More Large language models (LLMs) are increasingly used as judges of chain-of-thought (CoT) reasoning, yet it remains unclear whether they can reliably assess process faithfulness rather than merely answer plausibility. We introduce C2-Faith, a benchmark built from PRM800K that explicitly decomposes faithfulness into two complementary dimensions: causality (whether each step logically follows from prior context) and coverage (whether essential intermediate inferences are present). Using controlled perturbations, we construct examples with known causal error positions by replacing a single step with a logically inconsistent variant, and with controlled coverage deletions at varying rates, enabling direct measurement against reference labels. We evaluate three frontier LLM judges across three tasks: binary causal detection, causal step localization, and coverage scoring. Our results reveal that judge reliability is highly task-dependent, with no single model dominating across settings. While models often detect that an error exists, they struggle to accurately localize it, indicating a substantial gap between detection and attribution. Moreover, all judges systematically overestimate reasoning completeness, assigning high coverage scores even when substantial portions of intermediate reasoning are missing. These findings expose fundamental limitations of LLM judges in process-level evaluation and highlight the need for more reliable and calibrated methods when using LLMs to assess reasoning quality. △ Less

Submitted 11 June, 2026; v1 submitted 5 March, 2026; originally announced March 2026.

DiffusionXRay: A Diffusion and GAN-Based Approach for Enhancing Digitally Reconstructed Chest Radiographs

Authors: Aryan Goyal, Ashish Mittal, Pranav Rao, Manoj Tadepalli, Preetham Putha

Abstract: Deep learning-based automated diagnosis of lung cancer has emerged as a crucial advancement that enables healthcare professionals to detect and initiate treatment earlier. However, these models require extensive training datasets with diverse case-specific properties. High-quality annotated data is particularly challenging to obtain, especially for cases with subtle pulmonary nodules that are diff… ▽ More Deep learning-based automated diagnosis of lung cancer has emerged as a crucial advancement that enables healthcare professionals to detect and initiate treatment earlier. However, these models require extensive training datasets with diverse case-specific properties. High-quality annotated data is particularly challenging to obtain, especially for cases with subtle pulmonary nodules that are difficult to detect even for experienced radiologists. This scarcity of well-labeled datasets can limit model performance and generalization across different patient populations. Digitally reconstructed radiographs (DRR) using CT-Scan to generate synthetic frontal chest X-rays with artificially inserted lung nodules offers one potential solution. However, this approach suffers from significant image quality degradation, particularly in the form of blurred anatomical features and loss of fine lung field structures. To overcome this, we introduce DiffusionXRay, a novel image restoration pipeline for Chest X-ray images that synergistically leverages denoising diffusion probabilistic models (DDPMs) and generative adversarial networks (GANs). DiffusionXRay incorporates a unique two-stage training process: First, we investigate two independent approaches, DDPM-LQ and GAN-based MUNIT-LQ, to generate low-quality CXRs, addressing the challenge of training data scarcity, posing this as a style transfer problem. Subsequently, we train a DDPM-based model on paired low-quality and high-quality images, enabling it to learn the nuances of X-ray image restoration. Our method demonstrates promising results in enhancing image clarity, contrast, and overall diagnostic value of chest X-rays while preserving subtle yet clinically significant artifacts, validated by both quantitative metrics and expert radiological assessment. △ Less

Submitted 2 March, 2026; originally announced March 2026.

Comments: Published at MICCAI 2025

Journal ref: Data Engineering in Medical Imaging: Third MICCAI Workshop, DEMI 2025, Held in Conjunction with MICCAI 2025, Daejeon, South Korea, September 27, 2025, Proceedings

A Diffusion-Driven Fine-Grained Nodule Synthesis Framework for Enhanced Lung Nodule Detection from Chest Radiographs

Authors: Aryan Goyal, Shreshtha Singh, Ashish Mittal, Manoj Tadepalli, Piyush Kumar, Preetham Putha

Abstract: Early detection of lung cancer in chest radiographs (CXRs) is crucial for improving patient outcomes, yet nodule detection remains challenging due to their subtle appearance and variability in radiological characteristics like size, texture, and boundary. For robust analysis, this diversity must be well represented in training datasets for deep learning based Computer-Assisted Diagnosis (CAD) syst… ▽ More Early detection of lung cancer in chest radiographs (CXRs) is crucial for improving patient outcomes, yet nodule detection remains challenging due to their subtle appearance and variability in radiological characteristics like size, texture, and boundary. For robust analysis, this diversity must be well represented in training datasets for deep learning based Computer-Assisted Diagnosis (CAD) systems. However, assembling such datasets is costly and often impractical, motivating the need for realistic synthetic data generation. Existing methods lack fine-grained control over synthetic nodule generation, limiting their utility in addressing data scarcity. This paper proposes a novel diffusion-based framework with low-rank adaptation (LoRA) adapters for characteristic controlled nodule synthesis on CXRs. We begin by addressing size and shape control through nodule mask conditioned training of the base diffusion model. To achieve individual characteristic control, we train separate LoRA modules, each dedicated to a specific radiological feature. However, since nodules rarely exhibit isolated characteristics, effective multi-characteristic control requires a balanced integration of features. We address this by leveraging the dynamic composability of LoRAs and revisiting existing merging strategies. Building on this, we identify two key issues, overlapping attention regions and non-orthogonal parameter spaces. To overcome these limitations, we introduce a novel orthogonality loss term during LoRA composition training. Extensive experiments on both in-house and public datasets demonstrate improved downstream nodule detection. Radiologist evaluations confirm the fine-grained controllability of our generated nodules, and across multiple quantitative metrics, our method surpasses existing nodule generation approaches for CXRs. △ Less

Submitted 2 March, 2026; originally announced March 2026.

Comments: Accepted at MIDL 2026 (Poster). Published on OpenReview on February 14, 2026. Proceedings version pending. OpenReview: https://openreview.net/forum?id=7DL7cu8Ui8

As Content and Layout Co-Evolve: TangibleSite for Scaffolding Blind People's Webpage Design through Multimodal Interaction

Authors: Jiasheng Li, Zining Zhang, Zeyu Yan, Matthew Wong, Arnav Mittal, Ge Gao, Huaishu Peng

Abstract: Creating webpages requires generating content and arranging layout while iteratively refining both to achieve a coherent design, a process that can be challenging for blind individuals. To understand how blind designers navigate this process, we conducted two rounds of co-design sessions with blind participants, using design probes to elicit their strategies and support needs. Our findings reveal… ▽ More Creating webpages requires generating content and arranging layout while iteratively refining both to achieve a coherent design, a process that can be challenging for blind individuals. To understand how blind designers navigate this process, we conducted two rounds of co-design sessions with blind participants, using design probes to elicit their strategies and support needs. Our findings reveal a preference for content and layout to co-evolve, but this process requires external support through cues that situate local elements within the broader page structure as well as multimodal interactions. Building on these insights, we developed TangibleSite, an accessible web design tool that provides real-time multimodal feedback through tangible, auditory, and speech-based interactions. TangibleSite enables blind individuals to create, edit, and reposition webpage elements while integrating content and layout decisions. A formative evaluation with six blind participants demonstrated that TangibleSite enabled independent webpage creation, supported refinement across content and layout, and reduced barriers to achieving visually consistent designs. △ Less

Submitted 22 February, 2026; originally announced February 2026.

LLaMo: Scaling Pretrained Language Models for Unified Motion Understanding and Generation with Continuous Autoregressive Tokens

Authors: Zekun Li, Sizhe An, Chengcheng Tang, Chuan Guo, Ivan Shugurov, Linguang Zhang, Amy Zhao, Srinath Sridhar, Lingling Tao, Abhay Mittal

Abstract: Recent progress in large models has led to significant advances in unified multimodal generation and understanding. However, the development of models that unify motion-language generation and understanding remains largely underexplored. Existing approaches often fine-tune large language models (LLMs) on paired motion-text data, which can result in catastrophic forgetting of linguistic capabilitie… ▽ More Recent progress in large models has led to significant advances in unified multimodal generation and understanding. However, the development of models that unify motion-language generation and understanding remains largely underexplored. Existing approaches often fine-tune large language models (LLMs) on paired motion-text data, which can result in catastrophic forgetting of linguistic capabilities due to the limited scale of available text-motion pairs. Furthermore, prior methods typically convert motion into discrete representations via quantization to integrate with language models, introducing substantial jitter artifacts from discrete tokenization. To address these challenges, we propose LLaMo, a unified framework that extends pretrained LLMs through a modality-specific Mixture-of-Transformers (MoT) architecture. This design inherently preserves the language understanding of the base model while enabling scalable multimodal adaptation. We encode human motion into a causal continuous latent space and maintain the next-token prediction paradigm in the decoder-only backbone through a lightweight flow-matching head, allowing for streaming motion generation in real-time (>30 FPS). Leveraging the comprehensive language understanding of pretrained LLMs and large-scale motion-text pretraining, our experiments demonstrate that LLaMo achieves high-fidelity text-to-motion generation and motion-to-text captioning in general settings, especially zero-shot motion generation, marking a significant step towards a general unified motion-language large model. △ Less

Submitted 16 April, 2026; v1 submitted 12 February, 2026; originally announced February 2026.

Comments: Project page: https://kunkun0w0.github.io/project/LLaMo/

Enhancing Open-Vocabulary Object Detection through Multi-Level Fine-Grained Visual-Language Alignment

Authors: Tianyi Zhang, Antoine Simoulin, Kai Li, Sana Lakdawala, Shiqing Yu, Arpit Mittal, Hongyu Fu, Yu Lin

Abstract: Traditional object detection systems are typically constrained to predefined categories, limiting their applicability in dynamic environments. In contrast, open-vocabulary object detection (OVD) enables the identification of objects from novel classes not present in the training set. Recent advances in visual-language modeling have led to significant progress of OVD. However, prior works face chal… ▽ More Traditional object detection systems are typically constrained to predefined categories, limiting their applicability in dynamic environments. In contrast, open-vocabulary object detection (OVD) enables the identification of objects from novel classes not present in the training set. Recent advances in visual-language modeling have led to significant progress of OVD. However, prior works face challenges in either adapting the single-scale image backbone from CLIP to the detection framework or ensuring robust visual-language alignment. We propose Visual-Language Detection (VLDet), a novel framework that revamps feature pyramid for fine-grained visual-language alignment, leading to improved OVD performance. With the VL-PUB module, VLDet effectively exploits the visual-language knowledge from CLIP and adapts the backbone for object detection through feature pyramid. In addition, we introduce the SigRPN block, which incorporates a sigmoid-based anchor-text contrastive alignment loss to improve detection of novel categories. Through extensive experiments, our approach achieves 58.7 AP for novel classes on COCO2017 and 24.8 AP on LVIS, surpassing all state-of-the-art methods and achieving significant improvements of 27.6% and 6.9%, respectively. Furthermore, VLDet also demonstrates superior zero-shot performance on closed-set object detection. △ Less

Submitted 31 January, 2026; originally announced February 2026.

Dynamic Multi-Expert Projectors with Stabilized Routing for Multilingual Speech Recognition

Authors: Isha Pandey, Ashish Mittal, Vartul Bahuguna, Ganesh Ramakrishnan

Abstract: Recent advances in LLM-based ASR connect frozen speech encoders with Large Language Models (LLMs) via lightweight projectors. While effective in monolingual settings, a single projector struggles to capture the diverse acoustic-to-semantic mappings required for multilingual ASR. To address this, we propose SMEAR-MoE, a stabilized Mixture-of-Experts projector that ensures dense gradient flow to all… ▽ More Recent advances in LLM-based ASR connect frozen speech encoders with Large Language Models (LLMs) via lightweight projectors. While effective in monolingual settings, a single projector struggles to capture the diverse acoustic-to-semantic mappings required for multilingual ASR. To address this, we propose SMEAR-MoE, a stabilized Mixture-of-Experts projector that ensures dense gradient flow to all experts, preventing expert collapse while enabling cross-lingual sharing. We systematically compare monolithic, static multi-projector, and dynamic MoE designs across four Indic languages (Hindi, Marathi, Tamil, Telugu). Our SMEAR-MoE achieves strong performance, delivering upto a 7.6% relative WER reduction over the single-projector baseline, while maintaining comparable runtime efficiency. Analysis of expert routing further shows linguistically meaningful specialization, with related languages sharing experts. These results demonstrate that stable multi-expert projectors are key to scalable and robust multilingual ASR. △ Less

Submitted 27 January, 2026; originally announced January 2026.

Lost in Transcription: How Speech-to-Text Errors Derail Code Understanding

Authors: Jayant Havare, Ashish Mittal, Srikanth Tamilselvam, Ganesh Ramakrishnan

Abstract: Code understanding is a foundational capability in software engineering tools and developer workflows. However, most existing systems are designed for English-speaking users interacting via keyboards, which limits accessibility in multilingual and voice-first settings, particularly in regions like India. Voice-based interfaces offer a more inclusive modality, but spoken queries involving code pres… ▽ More Code understanding is a foundational capability in software engineering tools and developer workflows. However, most existing systems are designed for English-speaking users interacting via keyboards, which limits accessibility in multilingual and voice-first settings, particularly in regions like India. Voice-based interfaces offer a more inclusive modality, but spoken queries involving code present unique challenges due to the presence of non-standard English usage, domain-specific vocabulary, and custom identifiers such as variable and function names, often combined with code-mixed expressions. In this work, we develop a multilingual speech-driven framework for code understanding that accepts spoken queries in a user native language, transcribes them using Automatic Speech Recognition (ASR), applies code-aware ASR output refinement using Large Language Models (LLMs), and interfaces with code models to perform tasks such as code question answering and code retrieval through benchmarks such as CodeSearchNet, CoRNStack, and CodeQA. Focusing on four widely spoken Indic languages and English, we systematically characterize how transcription errors impact downstream task performance. We also identified key failure modes in ASR for code and demonstrated that LLM-guided refinement significantly improves performance across both transcription and code understanding stages. Our findings underscore the need for code-sensitive adaptations in speech interfaces and offer a practical solution for building robust, multilingual voice-driven programming tools. △ Less

Submitted 20 January, 2026; originally announced January 2026.

Hierarchical Contextual Uplift Bandits for Catalog Personalization

Authors: Anupam Agrawal, Rajesh Mohanty, Shamik Bhattacharjee, Abhimanyu Mittal

Abstract: Contextual Bandit (CB) algorithms are widely adopted for personalized recommendations but often struggle in dynamic environments typical of fantasy sports, where rapid changes in user behavior and dramatic shifts in reward distributions due to external influences necessitate frequent retraining. To address these challenges, we propose a Hierarchical Contextual Uplift Bandit framework. Our framewor… ▽ More Contextual Bandit (CB) algorithms are widely adopted for personalized recommendations but often struggle in dynamic environments typical of fantasy sports, where rapid changes in user behavior and dramatic shifts in reward distributions due to external influences necessitate frequent retraining. To address these challenges, we propose a Hierarchical Contextual Uplift Bandit framework. Our framework dynamically adjusts contextual granularity from broad, system-wide insights to detailed, user-specific contexts, using contextual similarity to facilitate effective policy transfer and mitigate cold-start issues. Additionally, we integrate uplift modeling principles into our approach. Results from large-scale A/B testing on the Dream11 fantasy sports platform show that our method significantly enhances recommendation quality, achieving a 0.4% revenue improvement while also improving user satisfaction metrics compared to the current production system. We subsequently deployed this system to production as the default catalog personalization system in May 2025 and observed a further 0.5% revenue improvement. △ Less

Submitted 20 January, 2026; originally announced January 2026.

Scaling Reinforcement Learning for Content Moderation with Large Language Models

Authors: Hamed Firooz, Rui Liu, Yuchen Lu, Zhenyu Hou, Fangzhou Xiong, Xiaoyang Zhang, Changshu Jian, Zhicheng Zhu, Jiayuan Ma, Jacob Tao, Chaitali Gupta, Xiaochang Peng, Shike Mei, Hang Cui, Yang Qin, Shuo Tang, Jason Gaedtke, Arpit Mittal

Abstract: Content moderation at scale remains one of the most pressing challenges in today's digital ecosystem, where billions of user- and AI-generated artifacts must be continuously evaluated for policy violations. Although recent advances in large language models (LLMs) have demonstrated strong potential for policy-grounded moderation, the practical challenges of training these systems to achieve expert-… ▽ More Content moderation at scale remains one of the most pressing challenges in today's digital ecosystem, where billions of user- and AI-generated artifacts must be continuously evaluated for policy violations. Although recent advances in large language models (LLMs) have demonstrated strong potential for policy-grounded moderation, the practical challenges of training these systems to achieve expert-level accuracy in real-world settings remain largely unexplored, particularly in regimes characterized by label sparsity, evolving policy definitions, and the need for nuanced reasoning beyond shallow pattern matching. In this work, we present a comprehensive empirical investigation of scaling reinforcement learning (RL) for content classification, systematically evaluating multiple RL training recipes and reward-shaping strategies-including verifiable rewards and LLM-as-judge frameworks-to transform general-purpose language models into specialized, policy-aligned classifiers across three real-world content moderation tasks. Our findings provide actionable insights for industrial-scale moderation systems, demonstrating that RL exhibits sigmoid-like scaling behavior in which performance improves smoothly with increased training data, rollouts, and optimization steps before gradually saturating. Moreover, we show that RL substantially improves performance on tasks requiring complex policy-grounded reasoning while achieving up to 100x higher data efficiency than supervised fine-tuning, making it particularly effective in domains where expert annotations are scarce or costly. △ Less

Submitted 23 December, 2025; originally announced December 2025.

CodeVaani: A Multilingual, Voice-Based Code Learning Assistant

Authors: Jayant Havare, Srikanth Tamilselvam, Ashish Mittal, Shalaka Thorat, Soham Jadia, Varsha Apte, Ganesh Ramakrishnan

Abstract: Programming education often assumes English proficiency and text-based interaction, creating barriers for students from multilingual regions such as India. We present CodeVaani, a multilingual speech-driven assistant for understanding code, built into Bodhitree [1], a Learning Management System developed at IIT Bombay. It is a voice-enabled assistant that helps learners explore programming concept… ▽ More Programming education often assumes English proficiency and text-based interaction, creating barriers for students from multilingual regions such as India. We present CodeVaani, a multilingual speech-driven assistant for understanding code, built into Bodhitree [1], a Learning Management System developed at IIT Bombay. It is a voice-enabled assistant that helps learners explore programming concepts in their native languages. The system integrates Indic ASR, a codeaware transcription refinement module, and a code model for generating relevant answers. Responses are provided in both text and audio for natural interaction. In a study with 28 beginner programmers, CodeVaani achieved 75% response accuracy, with over 80% of participants rating the experience positively. Compared to classroom assistance, our framework offers ondemand availability, scalability to support many learners, and multilingual support that lowers the entry barrier for students with limited English proficiency. The demo will illustrate these capabilities and highlight how voice-based AI systems can make programming education more inclusive. Supplementary artifacts and demo video are also made available. △ Less

Submitted 8 October, 2025; originally announced November 2025.

Routesplain: Towards Faithful and Intervenable Routing for Software-related Tasks

Authors: Adam Štorek, Vikas Upadhyay, Marianne Menglin Liu, Daniel W. Peterson, Anshul Mittal, Sujeeth Bharadwaj, Fahad Shah, Sujith Ravi, Dan Roth

Abstract: LLMs now tackle a wide range of software-related tasks, yet we show that their performance varies markedly both across and within these tasks. Routing user queries to the appropriate LLMs can therefore help improve response quality while reducing cost. Prior work, however, has focused mainly on general-purpose LLM routing via black-box models. We introduce Routesplain, the first LLM router for sof… ▽ More LLMs now tackle a wide range of software-related tasks, yet we show that their performance varies markedly both across and within these tasks. Routing user queries to the appropriate LLMs can therefore help improve response quality while reducing cost. Prior work, however, has focused mainly on general-purpose LLM routing via black-box models. We introduce Routesplain, the first LLM router for software-related tasks, including multilingual code generation and repair, input/output prediction, and computer science QA. Unlike existing routing approaches, Routesplain first extracts human-interpretable concepts from each query (e.g., task, domain, reasoning complexity) and only routes based on these concepts, thereby providing intelligible, faithful rationales. We evaluate Routesplain on 16 state-of-the-art LLMs across eight software-related tasks; Routesplain outperforms individual models both in terms of accuracy and cost, and equals or surpasses all black-box baselines, with concept-level intervention highlighting avenues for further router improvements. △ Less

Submitted 8 August, 2026; v1 submitted 12 November, 2025; originally announced November 2025.

Comments: Accepted to COLM 2026

Learning-Based Vision Systems for Semi-Autonomous Forklift Operation in Industrial Warehouse Environments

Authors: Vamshika Sutar, Mahek Maheshwari, Archak Mittal

Abstract: The automation of material handling in warehouses increasingly relies on robust, low cost perception systems for forklifts and Automated Guided Vehicles (AGVs). This work presents a vision based framework for pallet and pallet hole detection and mapping using a single standard camera. We utilized YOLOv8 and YOLOv11 architectures, enhanced through Optuna driven hyperparameter optimization and spati… ▽ More The automation of material handling in warehouses increasingly relies on robust, low cost perception systems for forklifts and Automated Guided Vehicles (AGVs). This work presents a vision based framework for pallet and pallet hole detection and mapping using a single standard camera. We utilized YOLOv8 and YOLOv11 architectures, enhanced through Optuna driven hyperparameter optimization and spatial post processing. An innovative pallet hole mapping module converts the detections into actionable spatial representations, enabling accurate pallet and pallet hole association for forklift operation. Experiments on a custom dataset augmented with real warehouse imagery show that YOLOv8 achieves high pallet and pallet hole detection accuracy, while YOLOv11, particularly under optimized configurations, offers superior precision and stable convergence. The results demonstrate the feasibility of a cost effective, retrofittable visual perception module for forklifts. This study proposes a scalable approach to advancing warehouse automation, promoting safer, economical, and intelligent logistics operations. △ Less

Submitted 9 November, 2025; originally announced November 2025.

EDIT-Bench: Evaluating LLM Abilities to Perform Real-World Instructed Code Edits

Authors: Wayne Chi, Valerie Chen, Ryan Shar, Aditya Mittal, Jenny Liang, Wei-Lin Chiang, Anastasios Nikolas Angelopoulos, Ion Stoica, Graham Neubig, Ameet Talwalkar, Chris Donahue

Abstract: Instructed code editing, where LLMs directly modify a developer's existing code based on a user instruction, is becoming a widely used interaction mode in AI coding assistants. However, few benchmarks directly evaluate this capability and current datasets often rely on artificial sources. We introduce EDIT-Bench, a benchmark for evaluating LLM code editing capabilities grounded in real-world usage… ▽ More Instructed code editing, where LLMs directly modify a developer's existing code based on a user instruction, is becoming a widely used interaction mode in AI coding assistants. However, few benchmarks directly evaluate this capability and current datasets often rely on artificial sources. We introduce EDIT-Bench, a benchmark for evaluating LLM code editing capabilities grounded in real-world usage, i.e., user instructions and code contexts collected in the wild. EDIT-Bench comprises of 540 problems, multiple natural and programming languages, and a diverse set of real-world use cases, ranging from resolving errors to adding features. EDIT-Bench introduces context-dependent problems that require the model to understand code context, highlighted code, and cursor position in addition to the user instruction. We evaluate 40 diverse LLMs and observe that EDIT-Bench is a challenging set of problems where only 1 model scores over 60%. We find that model performance varies across different categories of user instructions. Further, we find that varying levels of contextual information greatly affect task success rate, with performance varying up to 11%, indicating the importance of evaluating with realistic context. △ Less

Submitted 17 November, 2025; v1 submitted 6 November, 2025; originally announced November 2025.

Investigation of Performance and Scalability of a Quantum-Inspired Evolutionary Optimizer (QIEO) on NVIDIA GPU

Authors: Aman Mittal, Kasturi Venkata Sai Srikanth, Ferdin Sagai Don Bosco, Abhishek Singh, Rut Lineswala, Abhishek Chopra

Abstract: Quantum inspired evolutionary optimization leverages quantum computing principles like superposition, interference, and probabilistic representation to enhance classical evolutionary algorithms with improved exploration and exploitation capabilities. Implemented on NVIDIA Tesla V100 SXM2 GPUs, this study systematically investigates the performance and scalability of a GPU-accelerated Quantum Inspi… ▽ More Quantum inspired evolutionary optimization leverages quantum computing principles like superposition, interference, and probabilistic representation to enhance classical evolutionary algorithms with improved exploration and exploitation capabilities. Implemented on NVIDIA Tesla V100 SXM2 GPUs, this study systematically investigates the performance and scalability of a GPU-accelerated Quantum Inspired Evolutionary Optimizer applied to large scale 01 Knapsack problems. By exploiting CUDA`s parallel processing capabilities, particularly through optimized memory management and thread configuration, significant speedups and efficient utilization of GPU resources is demonstrated. The analysis covers various problem sizes, kernel launch configurations, and memory models including constant, shared, global, and pinned memory, alongside extensive scaling studies. The results reveal that careful tuning of memory strategies and kernel configurations is essential for maximizing throughput and efficiency, with constant memory providing superior performance up to hardware limits. Beyond these limits, global memory and strategic tiling become necessary, albeit with some performance trade offs. The findings highlight both the promise and the practical constraints of applying QIEO on GPUs for complex combinatorial optimization, offering actionable insights for future large scale metaheuristic implementations. △ Less

Submitted 9 November, 2025; v1 submitted 3 November, 2025; originally announced November 2025.

Comments: The reported execution and memory resources need to re-checked

Pixels to Signals: A Real-Time Framework for Traffic Demand Estimation

Authors: H Mhatre, M Vyas, A Mittal

Abstract: Traffic congestion is becoming a challenge in the rapidly growing urban cities, resulting in increasing delays and inefficiencies within urban transportation systems. To address this issue a comprehensive methodology is designed to optimize traffic flow and minimize delays. The framework is structured with three primary components: (a) vehicle detection, (b) traffic prediction, and (c) traffic sig… ▽ More Traffic congestion is becoming a challenge in the rapidly growing urban cities, resulting in increasing delays and inefficiencies within urban transportation systems. To address this issue a comprehensive methodology is designed to optimize traffic flow and minimize delays. The framework is structured with three primary components: (a) vehicle detection, (b) traffic prediction, and (c) traffic signal optimization. This paper presents the first component, vehicle detection. The methodology involves analyzing multiple sequential frames from a camera feed to compute the background, i.e. the underlying roadway, by averaging pixel values over time. The computed background is then utilized to extract the foreground, where the Density-Based Spatial Clustering of Applications with Noise (DBSCAN) algorithm is applied to detect vehicles. With its computational efficiency and minimal infrastructure modification requirements, the proposed methodology offers a practical and scalable solution for real-world deployment. △ Less

Submitted 28 October, 2025; originally announced October 2025.

Adaptive Weighted Loss for Sequential Recommendations on Sparse Domains

Authors: Akshay Mittal, Vinay Venkatesh, Krishna Kandi, Shalini Sudarshan

Abstract: The effectiveness of single-model sequential recommendation architectures, while scalable, is often limited when catering to "power users" in sparse or niche domains. Our previous research, PinnerFormerLite, addressed this by using a fixed weighted loss to prioritize specific domains. However, this approach can be sub-optimal, as a single, uniform weight may not be sufficient for domains with very… ▽ More The effectiveness of single-model sequential recommendation architectures, while scalable, is often limited when catering to "power users" in sparse or niche domains. Our previous research, PinnerFormerLite, addressed this by using a fixed weighted loss to prioritize specific domains. However, this approach can be sub-optimal, as a single, uniform weight may not be sufficient for domains with very few interactions, where the training signal is easily diluted by the vast, generic dataset. This paper proposes a novel, data-driven approach: a Dynamic Weighted Loss function with comprehensive theoretical foundations and extensive empirical validation. We introduce an adaptive algorithm that adjusts the loss weight for each domain based on its sparsity in the training data, assigning a higher weight to sparser domains and a lower weight to denser ones. This ensures that even rare user interests contribute a meaningful gradient signal, preventing them from being overshadowed. We provide rigorous theoretical analysis including convergence proofs, complexity analysis, and bounds analysis to establish the stability and efficiency of our approach. Our comprehensive empirical validation across four diverse datasets (MovieLens, Amazon Electronics, Yelp Business, LastFM Music) with state-of-the-art baselines (SIGMA, CALRec, SparseEnNet) demonstrates that this dynamic weighting system significantly outperforms all comparison methods, particularly for sparse domains, achieving substantial lifts in key metrics like Recall at 10 and NDCG at 10 while maintaining performance on denser domains and introducing minimal computational overhead. △ Less

Submitted 5 October, 2025; originally announced October 2025.

LegalWiz: A Multi-Agent Generation Framework for Contradiction Detection in Legal Documents

Authors: Ananya Mantravadi, Shivali Dalmia, Olga Pospelova, Abhishek Mukherji, Nand Dave, Anudha Mittal

Abstract: Retrieval-Augmented Generation (RAG) integrates large language models (LLMs) with external sources, but unresolved contradictions in retrieved evidence often lead to hallucinations and legally unsound outputs. Benchmarks currently used for contradiction detection lack domain realism, cover only limited conflict types, and rarely extend beyond single-sentence pairs, making them unsuitable for legal… ▽ More Retrieval-Augmented Generation (RAG) integrates large language models (LLMs) with external sources, but unresolved contradictions in retrieved evidence often lead to hallucinations and legally unsound outputs. Benchmarks currently used for contradiction detection lack domain realism, cover only limited conflict types, and rarely extend beyond single-sentence pairs, making them unsuitable for legal applications. Controlled generation of documents with embedded contradictions is therefore essential: it enables systematic stress-testing of models, ensures coverage of diverse conflict categories, and provides a reliable basis for evaluating contradiction detection and resolution. We present a multi-agent contradiction-aware benchmark framework for the legal domain that generates synthetic legal-style documents, injects six structured contradiction types, and models both self- and pairwise inconsistencies. Automated contradiction mining is combined with human-in-the-loop validation to guarantee plausibility and fidelity. This benchmark offers one of the first structured resources for contradiction-aware evaluation in legal RAG pipelines, supporting more consistent, interpretable, and trustworthy systems. △ Less

Submitted 10 October, 2025; v1 submitted 3 October, 2025; originally announced October 2025.

Skill, Will, or Both? Understanding Digital Inaccessibility from Accessibility Professionals' Viewpoint

Authors: P D Parthasarathy, Rachel F. Adler, Devorah Kletenik, Swaroop Joshi, Anshu M Mittal

Abstract: Digital inaccessibility continues to be a significant barrier to true inclusion and equality. WebAIM's 2024 report reveals that only 4.1% of the world's top one million website homepages are fully accessible. Furthermore, the percentage of web pages with detectable Web Content Accessibility Guidelines (WCAG) failures has only decreased by 1.9\% over the past five years, from 97.8%. To gain deeper… ▽ More Digital inaccessibility continues to be a significant barrier to true inclusion and equality. WebAIM's 2024 report reveals that only 4.1% of the world's top one million website homepages are fully accessible. Furthermore, the percentage of web pages with detectable Web Content Accessibility Guidelines (WCAG) failures has only decreased by 1.9\% over the past five years, from 97.8%. To gain deeper insights into the persistent challenges of digital accessibility, we conducted a comprehensive survey with 160 accessibility professionals. Unlike previous studies, which often focused on technology professionals, our research examines inaccessibility through the lens of dedicated accessibility professionals, offering a more detailed analysis of the barriers they face. Our investigation explores (a) organizations' willingness to prioritize accessibility, (b) the challenges in ensuring accessibility, and (c) the current accessibility training practices in technology workspaces. This study aims to provide an updated perspective on the state of digital accessibility from the point of view of accessibility professionals. △ Less

Submitted 27 September, 2025; originally announced September 2025.

Comments: Accepted and published at Extended Abstracts of the CHI Conference on Human Factors in Computing Systems (CHI EA '25), April 26-May 1, 2025, Yokohama, Japan

MSC Class: acmart

Journal ref: In Proceedings of the Extended Abstracts of the CHI Conference on Human Factors in Computing Systems. Yokohama Japan: ACM, Apr. 2025, pp. 1-9

Scaling Accessibility Education: Reflections from a Workshop Targeting CS Educators and Software Professionals

Authors: P D Parthasarathy, Anshu M Mittal, Swaroop Joshi

Abstract: Despite growing global attention to digital accessibility, research from India highlights a significant gap in accessibility training for both computing educators and software professionals. To address this need, we designed and conducted an experiential workshop aimed at building foundational capacity in accessibility practices among 77 participants, including computer science (CS) faculty and in… ▽ More Despite growing global attention to digital accessibility, research from India highlights a significant gap in accessibility training for both computing educators and software professionals. To address this need, we designed and conducted an experiential workshop aimed at building foundational capacity in accessibility practices among 77 participants, including computer science (CS) faculty and industry practitioners. The one-day workshop combined hands-on activities, tool demonstrations, and case studies to foster practical understanding and engagement. Post-workshop feedback showed that a majority of participants rated the workshop positively, with many reporting increased confidence and a shift in their perception of accessibility as a shared responsibility. Additionally, participants expressed a strong interest in applying accessibility principles within their workplaces, underscoring the workshop's practical relevance and impact. In this experience report, we detail the workshop's design, implementation, and evaluation, and offer actionable insights to guide future initiatives aimed at strengthening accessibility capacity across India's computing education and professional landscape. △ Less

Submitted 26 September, 2025; originally announced September 2025.

Comments: Accepted for publication at ACM Compute 2025 - https://isigcse.acm.org/compute/2025/

AI Ethics Education in India: A Syllabus-Level Review of Computing Courses

Authors: Anshu M Mittal, P D Parthasarathy, Swaroop Joshi

Abstract: The pervasive integration of artificial intelligence (AI) across domains such as healthcare, governance, finance, and education has intensified scrutiny of its ethical implications, including algorithmic bias, privacy risks, accountability, and societal impact. While ethics has received growing attention in computer science (CS) education more broadly, the specific pedagogical treatment of {AI eth… ▽ More The pervasive integration of artificial intelligence (AI) across domains such as healthcare, governance, finance, and education has intensified scrutiny of its ethical implications, including algorithmic bias, privacy risks, accountability, and societal impact. While ethics has received growing attention in computer science (CS) education more broadly, the specific pedagogical treatment of {AI ethics} remains under-examined. This study addresses that gap through a large-scale analysis of 3,395 publicly accessible syllabi from CS and allied areas at leading Indian institutions. Among them, only 75 syllabi (2.21%) included any substantive AI ethics content. Three key findings emerged: (1) AI ethics is typically integrated as a minor module within broader technical courses rather than as a standalone course; (2) ethics coverage is often limited to just one or two instructional sessions; and (3) recurring topics include algorithmic fairness, privacy and data governance, transparency, and societal impact. While these themes reflect growing awareness, current curricular practices reveal limited depth and consistency. This work highlights both the progress and the gaps in preparing future technologists to engage meaningfully with the ethical dimensions of AI, and it offers suggestions to strengthen the integration of AI ethics within computing curricula. △ Less

Submitted 26 September, 2025; originally announced September 2025.

Comments: Accepted for publication at ACM Compute-2025 https://isigcse.acm.org/compute/2025/

PHD: Personalized 3D Human Body Fitting with Point Diffusion

Authors: Hsuan-I Ho, Chen Guo, Po-Chen Wu, Ivan Shugurov, Chengcheng Tang, Abhay Mittal, Sizhe An, Manuel Kaufmann, Linguang Zhang

Abstract: We introduce PHD, a novel approach for personalized 3D human mesh recovery (HMR) and body fitting that leverages user-specific shape information to improve pose estimation accuracy from videos. Traditional HMR methods are designed to be user-agnostic and optimized for generalization. While these methods often refine poses using constraints derived from the 2D image to improve alignment, this proce… ▽ More We introduce PHD, a novel approach for personalized 3D human mesh recovery (HMR) and body fitting that leverages user-specific shape information to improve pose estimation accuracy from videos. Traditional HMR methods are designed to be user-agnostic and optimized for generalization. While these methods often refine poses using constraints derived from the 2D image to improve alignment, this process compromises 3D accuracy by failing to jointly account for person-specific body shapes and the plausibility of 3D poses. In contrast, our pipeline decouples this process by first calibrating the user's body shape and then employing a personalized pose fitting process conditioned on that shape. To achieve this, we develop a body shape-conditioned 3D pose prior, implemented as a Point Diffusion Transformer, which iteratively guides the pose fitting via a Point Distillation Sampling loss. This learned 3D pose prior effectively mitigates errors arising from an over-reliance on 2D constraints. Consequently, our approach improves not only pelvis-aligned pose accuracy but also absolute pose accuracy -- an important metric often overlooked by prior work. Furthermore, our method is highly data-efficient, requiring only synthetic data for training, and serves as a versatile plug-and-play module that can be seamlessly integrated with existing 3D pose estimators to enhance their performance. Project page: https://phd-pose.github.io/ △ Less

Submitted 28 August, 2025; originally announced August 2025.

Comments: ICCV 2025, 19 pages, 18 figures

Mathematics Isn't Culture-Free: Probing Cultural Gaps via Entity and Scenario Perturbations

Authors: Aditya Tomar, Nihar Ranjan Sahoo, Ashish Mittal, Rudra Murthy, Pushpak Bhattacharyya

Abstract: Although mathematics is often considered culturally neutral, the way mathematical problems are presented can carry implicit cultural context. Existing benchmarks like GSM8K are predominantly rooted in Western norms, including names, currencies, and everyday scenarios. In this work, we create culturally adapted variants of the GSM8K test set for five regions Africa, India, China, Korea, and Japan u… ▽ More Although mathematics is often considered culturally neutral, the way mathematical problems are presented can carry implicit cultural context. Existing benchmarks like GSM8K are predominantly rooted in Western norms, including names, currencies, and everyday scenarios. In this work, we create culturally adapted variants of the GSM8K test set for five regions Africa, India, China, Korea, and Japan using prompt-based transformations followed by manual verification. We evaluate six large language models (LLMs), ranging from 8B to 72B parameters, across five prompting strategies to assess their robustness to cultural variation in math problem presentation. Our findings reveal a consistent performance gap: models perform best on the original US-centric dataset and comparatively worse on culturally adapted versions. However, models with reasoning capabilities are more resilient to these shifts, suggesting that deeper reasoning helps bridge cultural presentation gaps in mathematical tasks △ Less

Submitted 31 October, 2025; v1 submitted 1 July, 2025; originally announced July 2025.

Revisiting CroPA: A Reproducibility Study and Enhancements for Cross-Prompt Adversarial Transferability in Vision-Language Models

Authors: Atharv Mittal, Agam Pandey, Amritanshu Tiwari, Sukrit Jindal, Swadesh Swain

Abstract: Large Vision-Language Models (VLMs) have revolutionized computer vision, enabling tasks such as image classification, captioning, and visual question answering. However, they remain highly vulnerable to adversarial attacks, particularly in scenarios where both visual and textual modalities can be manipulated. In this study, we conduct a comprehensive reproducibility study of "An Image is Worth 100… ▽ More Large Vision-Language Models (VLMs) have revolutionized computer vision, enabling tasks such as image classification, captioning, and visual question answering. However, they remain highly vulnerable to adversarial attacks, particularly in scenarios where both visual and textual modalities can be manipulated. In this study, we conduct a comprehensive reproducibility study of "An Image is Worth 1000 Lies: Adversarial Transferability Across Prompts on Vision-Language Models" validating the Cross-Prompt Attack (CroPA) and confirming its superior cross-prompt transferability compared to existing baselines. Beyond replication we propose several key improvements: (1) A novel initialization strategy that significantly improves Attack Success Rate (ASR). (2) Investigate cross-image transferability by learning universal perturbations. (3) A novel loss function targeting vision encoder attention mechanisms to improve generalization. Our evaluation across prominent VLMs -- including Flamingo, BLIP-2, and InstructBLIP as well as extended experiments on LLaVA validates the original results and demonstrates that our improvements consistently boost adversarial effectiveness. Our work reinforces the importance of studying adversarial vulnerabilities in VLMs and provides a more robust framework for generating transferable adversarial examples, with significant implications for understanding the security of VLMs in real-world applications. △ Less

Submitted 28 June, 2025; originally announced June 2025.

Comments: Accepted to MLRC 2025

Journal ref: Transactions on Machine Learning Research (TMLR), 2025. Available at OpenReview: https://openreview.net/forum?id=5L90cl0xtf

Cardiovascular disease classification using radiomics and geometric features from cardiac CT

Authors: Ajay Mittal, Raghav Mehta, Omar Todd, Philipp Seeböck, Georg Langs, Ben Glocker

Abstract: Automatic detection and classification of Cardiovascular disease (CVD) from Computed Tomography (CT) images play an important part in facilitating better-informed clinical decisions. However, most of the recent deep learning based methods either directly work on raw CT data or utilize it in pair with anatomical cardiac structure segmentation by training an end-to-end classifier. As such, these app… ▽ More Automatic detection and classification of Cardiovascular disease (CVD) from Computed Tomography (CT) images play an important part in facilitating better-informed clinical decisions. However, most of the recent deep learning based methods either directly work on raw CT data or utilize it in pair with anatomical cardiac structure segmentation by training an end-to-end classifier. As such, these approaches become much more difficult to interpret from a clinical perspective. To address this challenge, in this work, we break down the CVD classification pipeline into three components: (i) image segmentation, (ii) image registration, and (iii) downstream CVD classification. Specifically, we utilize the Atlas-ISTN framework and recent segmentation foundational models to generate anatomical structure segmentation and a normative healthy atlas. These are further utilized to extract clinically interpretable radiomic features as well as deformation field based geometric features (through atlas registration) for CVD classification. Our experiments on the publicly available ASOCA dataset show that utilizing these features leads to better CVD classification accuracy (87.50\%) when compared against classification model trained directly on raw CT images (67.50\%). Our code is publicly available: https://github.com/biomedia-mira/grc-net △ Less

Submitted 6 May, 2026; v1 submitted 27 June, 2025; originally announced June 2025.

Comments: Accepted at STACOM 2025 workshop held in conjunction with MICCAI 2025 conference

DELPHYNE: A Pre-Trained Model for General and Financial Time Series

Authors: Xueying Ding, Aakriti Mittal, Achintya Gopal

Abstract: Time-series data is a vital modality within data science communities. This is particularly valuable in financial applications, where it helps in detecting patterns, understanding market behavior, and making informed decisions based on historical data. Recent advances in language modeling have led to the rise of time-series pre-trained models that are trained on vast collections of datasets and app… ▽ More Time-series data is a vital modality within data science communities. This is particularly valuable in financial applications, where it helps in detecting patterns, understanding market behavior, and making informed decisions based on historical data. Recent advances in language modeling have led to the rise of time-series pre-trained models that are trained on vast collections of datasets and applied to diverse tasks across financial domains. However, across financial applications, existing time-series pre-trained models have not shown boosts in performance over simple finance benchmarks in both zero-shot and fine-tuning settings. This phenomenon occurs because of a i) lack of financial data within the pre-training stage, and ii) the negative transfer effect due to inherently different time-series patterns across domains. Furthermore, time-series data is continuous, noisy, and can be collected at varying frequencies and with varying lags across different variables, making this data more challenging to model than languages. To address the above problems, we introduce a Pre-trained MoDEL for FINance TimE-series (Delphyne). Delphyne achieves competitive performance to existing foundation and full-shot models with few fine-tuning steps on publicly available datasets, and also shows superior performances on various financial tasks. △ Less

Submitted 12 May, 2025; originally announced June 2025.

CLAIM: An Intent-Driven Multi-Agent Framework for Analyzing Manipulation in Courtroom Dialogues

Authors: Disha Sheshanarayana, Tanishka Magar, Ayushi Mittal, Neelam Chaplot

Abstract: Courtrooms are places where lives are determined and fates are sealed, yet they are not impervious to manipulation. Strategic use of manipulation in legal jargon can sway the opinions of judges and affect the decisions. Despite the growing advancements in NLP, its application in detecting and analyzing manipulation within the legal domain remains largely unexplored. Our work addresses this gap by… ▽ More Courtrooms are places where lives are determined and fates are sealed, yet they are not impervious to manipulation. Strategic use of manipulation in legal jargon can sway the opinions of judges and affect the decisions. Despite the growing advancements in NLP, its application in detecting and analyzing manipulation within the legal domain remains largely unexplored. Our work addresses this gap by introducing LegalCon, a dataset of 1,063 annotated courtroom conversations labeled for manipulation detection, identification of primary manipulators, and classification of manipulative techniques, with a focus on long conversations. Furthermore, we propose CLAIM, a two-stage, Intent-driven Multi-agent framework designed to enhance manipulation analysis by enabling context-aware and informed decision-making. Our results highlight the potential of incorporating agentic frameworks to improve fairness and transparency in judicial processes. We hope that this contributes to the broader application of NLP in legal discourse analysis and the development of robust tools to support fairness in legal decision-making. Our code and data are available at https://github.com/Disha1001/CLAIM. △ Less

Submitted 4 June, 2025; originally announced June 2025.

Comments: Accepted to SICon 2025 ACL

Memory-efficient Streaming VideoLLMs for Real-time Procedural Video Understanding

Authors: Dibyadip Chatterjee, Edoardo Remelli, Yale Song, Bugra Tekin, Abhay Mittal, Bharat Bhatnagar, Necati Cihan Camgöz, Shreyas Hampali, Eric Sauser, Shugao Ma, Angela Yao, Fadime Sener

Abstract: We introduce ProVideLLM, an end-to-end framework for real-time procedural video understanding. ProVideLLM integrates a multimodal cache configured to store two types of tokens - verbalized text tokens, which provide compressed textual summaries of long-term observations, and visual tokens, encoded with DETR-QFormer to capture fine-grained details from short-term observations. This design reduces t… ▽ More We introduce ProVideLLM, an end-to-end framework for real-time procedural video understanding. ProVideLLM integrates a multimodal cache configured to store two types of tokens - verbalized text tokens, which provide compressed textual summaries of long-term observations, and visual tokens, encoded with DETR-QFormer to capture fine-grained details from short-term observations. This design reduces token count by 22x over existing methods in representing one hour of long-term observations while effectively encoding fine-granularity of the present. By interleaving these tokens in our multimodal cache, ProVideLLM ensures sub-linear scaling of memory and compute with video length, enabling per-frame streaming inference at 10 FPS and streaming dialogue at 25 FPS, with a minimal 2GB GPU memory footprint. ProVideLLM also sets new state-of-the-art results on six procedural tasks across four datasets. △ Less

Submitted 10 April, 2025; originally announced April 2025.

Comments: 13 pages, 5 figures; https://dibschat.github.io/ProVideLLM

Rubric Is All You Need: Enhancing LLM-based Code Evaluation With Question-Specific Rubrics

Authors: Aditya Pathak, Rachit Gandhi, Vaibhav Uttam, Arnav Ramamoorthy, Pratyush Ghosh, Aaryan Raj Jindal, Shreyash Verma, Aditya Mittal, Aashna Ased, Chirag Khatri, Yashwanth Nakka, Devansh, Jagat Sesh Challa, Dhruv Kumar

Abstract: Since the emergence of Large Language Models (LLMs) popularized by the release of GPT-3 and ChatGPT, LLMs have shown remarkable promise in programming-related tasks. While code generation using LLMs has become a popular field of research, code evaluation using LLMs remains under-explored. In this paper, we focus on LLM-based code evaluation and attempt to fill in the existing gaps. We propose mult… ▽ More Since the emergence of Large Language Models (LLMs) popularized by the release of GPT-3 and ChatGPT, LLMs have shown remarkable promise in programming-related tasks. While code generation using LLMs has become a popular field of research, code evaluation using LLMs remains under-explored. In this paper, we focus on LLM-based code evaluation and attempt to fill in the existing gaps. We propose multi-agentic novel approaches using \emph{question-specific rubrics} tailored to the problem statement, arguing that these perform better for logical assessment than the existing approaches that use \emph{question-agnostic rubrics}. To address the lack of suitable evaluation datasets, we introduce two datasets: a Data Structures and Algorithms dataset containing 150 student submissions from a popular Data Structures and Algorithms practice website, and an Object Oriented Programming dataset comprising 80 student submissions from undergraduate computer science courses. In addition to using standard metrics (Spearman Correlation, Cohen's Kappa), we additionally propose a new metric called as Leniency, which quantifies evaluation strictness relative to expert assessment. Our comprehensive analysis demonstrates that \emph{question-specific rubrics} significantly enhance logical assessment of code in educational settings, providing better feedback aligned with instructional goals beyond mere syntactic correctness. △ Less

Submitted 6 August, 2025; v1 submitted 31 March, 2025; originally announced March 2025.

Comments: Accepted in ICER 2025

Small-Scale Testbeds for Connected and Automated Vehicles and Robot Swarms: Challenges and a Roadmap

Authors: Jianye Xu, Johannes Betz, Armin Mokhtarian, Archak Mittal, Mengchi Cai, Rahul Mangharam, Omar M. Shehata, Catherine M. Elias, Jan-Nico Zaech, Patrick Scheffe, Felix Jahncke, Sangeet Sankaramangalam Ulhas, Kaj Munhoz Arfvidsson, Bassam Alrifaee

Abstract: This article proposes a roadmap to address the current challenges in small-scale testbeds for Connected and Automated Vehicles (CAVs) and robot swarms. The roadmap is a joint effort of participants in the workshop "1st Workshop on Small-Scale Testbeds for Connected and Automated Vehicles and Robot Swarms," held on June 2 at the IEEE Intelligent Vehicles Symposium (IV) 2024 in Jeju, South Korea. Th… ▽ More This article proposes a roadmap to address the current challenges in small-scale testbeds for Connected and Automated Vehicles (CAVs) and robot swarms. The roadmap is a joint effort of participants in the workshop "1st Workshop on Small-Scale Testbeds for Connected and Automated Vehicles and Robot Swarms," held on June 2 at the IEEE Intelligent Vehicles Symposium (IV) 2024 in Jeju, South Korea. The roadmap contains three parts: 1) enhancing accessibility and diversity, especially for underrepresented communities, 2) sharing best practices for the development and maintenance of testbeds, and 3) connecting testbeds through an abstraction layer to support collaboration. The workshop features eight invited speakers, four contributed papers [1]-[4], and a presentation of a survey paper on testbeds [5]. The survey paper provides an online comparative table of more than 25 testbeds, available at https://bassamlab.github.io/testbeds-survey. The workshop's own website is available at https://cpm-remote.lrt.unibw-muenchen.de/iv24-workshop. △ Less

Submitted 24 March, 2026; v1 submitted 7 March, 2025; originally announced March 2025.

Comments: Published version

Copilot Arena: A Platform for Code LLM Evaluation in the Wild

Authors: Wayne Chi, Valerie Chen, Anastasios Nikolas Angelopoulos, Wei-Lin Chiang, Aditya Mittal, Naman Jain, Tianjun Zhang, Ion Stoica, Chris Donahue, Ameet Talwalkar

Abstract: Evaluating in-the-wild coding capabilities of large language models (LLMs) is a challenging endeavor with no clear solution. We introduce Copilot Arena, a platform to collect user preferences for code generation through native integration into a developer's working environment. Copilot Arena comprises a novel interface for comparing pairs of model outputs, a sampling strategy optimized to reduce l… ▽ More Evaluating in-the-wild coding capabilities of large language models (LLMs) is a challenging endeavor with no clear solution. We introduce Copilot Arena, a platform to collect user preferences for code generation through native integration into a developer's working environment. Copilot Arena comprises a novel interface for comparing pairs of model outputs, a sampling strategy optimized to reduce latency, and a prompting scheme to enable code completion functionality. Copilot Arena has served over 4.5 million suggestions from 10 models and collected over 11k pairwise judgements. Our results highlight the importance of model evaluations in integrated settings. We find that model rankings from Copilot Arena differ from those of existing evaluations, which we attribute to the more realistic distribution of data and tasks contained in Copilot Arena. We also identify novel insights into human preferences on code such as an observed consistency in user preference across programming languages yet significant variation in preference due to task category. We open-source Copilot Arena and release data to enable human-centric evaluations and improve understanding of coding assistants. △ Less

Submitted 13 February, 2025; originally announced February 2025.

End-to-end Training for Text-to-Image Synthesis using Dual-Text Embeddings

Authors: Yeruru Asrar Ahmed, Anurag Mittal

Abstract: Text-to-Image (T2I) synthesis is a challenging task that requires modeling complex interactions between two modalities ( i.e., text and image). A common framework adopted in recent state-of-the-art approaches to achieving such multimodal interactions is to bootstrap the learning process with pre-trained image-aligned text embeddings trained using contrastive loss. Furthermore, these embeddings are… ▽ More Text-to-Image (T2I) synthesis is a challenging task that requires modeling complex interactions between two modalities ( i.e., text and image). A common framework adopted in recent state-of-the-art approaches to achieving such multimodal interactions is to bootstrap the learning process with pre-trained image-aligned text embeddings trained using contrastive loss. Furthermore, these embeddings are typically trained generically and reused across various synthesis models. In contrast, we explore an approach to learning text embeddings specifically tailored to the T2I synthesis network, trained in an end-to-end fashion. Further, we combine generative and contrastive training and use two embeddings, one optimized to enhance the photo-realism of the generated images, and the other seeking to capture text-to-image alignment. A comprehensive set of experiments on three text-to-image benchmark datasets (Oxford-102, Caltech-UCSD, and MS-COCO) reveal that having two separate embeddings gives better results than using a shared one and that such an approach performs favourably in comparison with methods that use text representations from a pre-trained text encoder trained using a discriminative approach. Finally, we demonstrate that such learned embeddings can be used in other contexts as well, such as text-to-image manipulation. △ Less

Submitted 3 February, 2025; originally announced February 2025.