most citedDistill CLIP (DCLIP): Enhancing Image-Text Retrieval via Cross-Modal Transformer Distillation

1 citations · 1 across the 16 of their papers we have counts for

collaborators

27 papers

cs.AI2025

Reasoning Relay: Evaluating Stability and Interchangeability of Large Language Models in Mathematical Reasoning

Leo Lu, Jonathan Zhang, Sean Chua +4

Chain-of-Thought (CoT) prompting has significantly advanced the reasoning capabilities of large language models (LLMs). While prior work focuses on improving model performance thro…

cs.MA2025

WOLF: Werewolf-based Observations for LLM Deception and Falsehoods

Mrinal Agarwal, Saad Rana, Theo Sundoro +5

Deception is a fundamental challenge for multi-agent reasoning: effective systems must strategically conceal information while detecting misleading behavior in others. Yet most eva…

cs.LG2025

Peek-a-Boo Reasoning: Contrastive Region Masking in MLLMs

Isha Chaturvedi, Anjana Nair, Yushen Li +5

We introduce Contrastive Region Masking (CRM), a training free diagnostic that reveals how multimodal large language models (MLLMs) depend on specific visual regions at each step o…

cs.CR2025

SALT: Steering Activations towards Leakage-free Thinking in Chain of Thought

Shourya Batra, Pierce Tillman, Samarth Gaggar +6

As Large Language Models (LLMs) evolve into personal assistants with access to sensitive user data, they face a critical privacy challenge: while prior work has addressed output-le…

cs.CL2025

Interpreting the Latent Structure of Operator Precedence in Language Models

Dharunish Yugeswardeenoo, Harshil Nukala, Ved Shah +4

Large Language Models (LLMs) have demonstrated impressive reasoning capabilities but continue to struggle with arithmetic tasks. Prior works largely focus on outputs or prompting s…

cs.AI2025

SMAGDi: Socratic Multi Agent Interaction Graph Distillation for Efficient High Accuracy Reasoning

Aayush Aluru, Myra Malik, Samarth Patankar +4

Multi-agent systems (MAS) often achieve higher reasoning accuracy than single models, but their reliance on repeated debates across agents makes them computationally expensive. We…