10 papers
Beyond Imitation: Self-Improving Robot Policies via Off-Policy Q-Planning
Varun Giridhar, Anant Khandelwal, Jeremy A. Collins +2
Behaviour Cloning (BC) has driven remarkable progress in robot manipulation, yet it is fundamentally limited by its inability to self-improve: a policy that fails cannot learn from…
Read the Trace, Steer the Path: Trajectory-Aware Reinforcement Learning for Diffusion Language Models
Anant Khandelwal, Manish Gupta
Diffusion large language models (dLLMs) generate responses by iteratively unmasking and revising many positions in parallel. This process leaves a rich denoising trace depicting wh…
Brain alignment of reasoning and action representations from vision-language and action models during naturalistic gameplay
Subba Reddy Oota, Anant Khandelwal, Khushbu Pahwa +4
Understanding how humans and artificial intelligence systems predict and plan by interacting with their environment is a fundamental challenge at the intersection of neuroscience a…
Linguistic properties and model scale in brain encoding: from small to compressed language models
Subba Reddy Oota, Vijay Rowtula, Satya Sai Srinath Namburi +5
Recent work has shown that scaling large language models (LLMs) improves their alignment with human brain activity, yet it remains unclear what drives these gains and which represe…
How does longer temporal context enhance multimodal narrative video processing in the brain?
Prachi Jindal, Anant Khandelwal, Manish Gupta +3
Understanding how humans and artificial intelligence systems process complex narrative videos is a fundamental challenge at the intersection of neuroscience and machine learning. T…
HistoryBankQA: Multilingual Temporal Question Answering on Historical Events
Biswadip Mandal, Anant Khandelwal, Manish Gupta
Temporal reasoning about historical events is a critical skill for NLP tasks like event extraction, historical entity linking, temporal question answering, timeline summarization,…
CoCoA: Confidence and Context-Aware Adaptive Decoding for Resolving Knowledge Conflicts in Large Language Models
Anant Khandelwal, Manish Gupta, Puneet Agrawal
Faithful generation in large language models (LLMs) is challenged by knowledge conflicts between parametric memory and external context. Existing contrastive decoding methods tuned…
PromptSync: Bridging Domain Gaps in Vision-Language Models through Class-Aware Prototype Alignment and Discrimination
Anant Khandelwal
The potential for zero-shot generalization in vision-language (V-L) models such as CLIP has spurred their widespread adoption in addressing numerous downstream tasks. Previous meth…
RePoseDM: Recurrent Pose Alignment and Gradient Guidance for Pose Guided Image Synthesis
Anant Khandelwal
Pose-guided person image synthesis task requires re-rendering a reference image, which should have a photorealistic appearance and flawless pose transfer. Since person images are h…
FloCoDe: Unbiased Dynamic Scene Graph Generation with Temporal Consistency and Correlation Debiasing
Anant Khandelwal
Dynamic scene graph generation (SGG) from videos requires not only a comprehensive understanding of objects across scenes but also a method to capture the temporal motions and inte…