collaborators

6 papers

cs.LG2026

Mitigating Forgetting in Continual Learning with Selective Gradient Projection

Anika Singh, Aayush Dhaulakhandi, Varun Chopade +3

As neural networks are increasingly deployed in dynamic environments, they face the challenge of catastrophic forgetting, the tendency to overwrite previously learned knowledge whe…

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.MA2025

From Competition to Coordination: Market Making as a Scalable Framework for Safe and Aligned Multi-Agent LLM Systems

Brendan Gho, Suman Muppavarapu, Afnan Shaik +6

As foundation models are increasingly deployed as interacting agents in multi-agent systems, their collective behavior raises new challenges for trustworthiness, transparency, and…

cs.AI2025

FRIT: Using Causal Importance to Improve Chain-of-Thought Faithfulness

Anand Swaroop, Akshat Nallani, Saksham Uboweja +7

Chain-of-thought (CoT) reasoning has emerged as a powerful tool for improving large language model performance on complex tasks, but recent work shows that reasoning steps often fa…

cs.AI2025

Evaluation Awareness Scales Predictably in Open-Weights Large Language Models

Maheep Chaudhary, Ian Su, Nikhil Hooda +6

Large language models (LLMs) can internally distinguish between evaluation and deployment contexts, a behaviour known as \emph{evaluation awareness}. This undermines AI safety eval…

cs.CL2025

Probe-Rewrite-Evaluate: A Workflow for Reliable Benchmarks and Quantifying Evaluation Awareness

Lang Xiong, Nishant Bhargava, Jianhang Hong +4

Large Language Models (LLMs) often exhibit significant behavioral shifts when they perceive a change from a real-world deployment context to a controlled evaluation setting, a phen…