collaborators

11 papers

cs.AI2026

Waking Up Blind: Cold-Start Optimization of Supervision-Free Agentic Trajectories for Grounded Visual Perception

Ashutosh Bajpai, Tamal Majumder, Akshay Nambi +1

Small Vision-Language Models (SVLMs) are efficient task controllers but often suffer from visual brittleness and poor tool orchestration. They typically require expensive supervise…

cs.CL2026

Markovian ODE-guided scoring can assess the quality of offline reasoning traces in language models

Arghodeep Nandi, Ojasva Saxena, Tanmoy Chakraborty

Reasoning traces produced by generative language models are increasingly used for tasks ranging from mathematical problem solving to automated fact checking. However, existing eval…

cs.CL2026

Understanding the Physics of Key-Value Cache Compression for LLMs through Attention Dynamics

Samhruth Ananthanarayanan, Ayan Sengupta, Tanmoy Chakraborty

As context windows in LLMs scale to 100K+ tokens, the key-value (KV) cache becomes the dominant memory bottleneck, with recent methods claiming 80-90% savings and minimal benchmark…

cs.CL2025

Do You Know About My Nation? Investigating Multilingual Language Models' Cultural Literacy Through Factual Knowledge

Eshaan Tanwar, Anwoy Chatterjee, Michael Saxon +3

Most multilingual question-answering benchmarks, while covering a diverse pool of languages, do not factor in regional diversity in the information they capture and tend to be West…

cs.CL2025

HIDE and Seek: Detecting Hallucinations in Language Models via Decoupled Representations

Anwoy Chatterjee, Yash Goel, Tanmoy Chakraborty

Contemporary Language Models (LMs), while impressively fluent, often generate content that is factually incorrect or unfaithful to the input context - a critical issue commonly ref…

cs.CL2025

Rank, Chunk and Expand: Lineage-Oriented Reasoning for Taxonomy Expansion

Sahil Mishra, Kumar Arjun, Tanmoy Chakraborty

Taxonomies are hierarchical knowledge graphs crucial for recommendation systems, and web applications. As data grows, expanding taxonomies is essential, but existing methods face k…