Sravan Babu Bodapati

Beyond correlation: The impact of human uncertainty in measuring the effectiveness of automatic evaluation and LLM-as-a-judge

SeRA: Self-Reviewing and Alignment of LLMs using Implicit Reward Margins

Compress, Gather, and Recompute: REFORMing Long-Context Processing in Transformers

Adaptive Video Understanding Agent: Enhancing Efficiency with Dynamic Frame Sampling and Feedback-driven Reasoning

Exposing Privacy Gaps: Membership Inference Attack on Preference Data for LLM Alignment