collaborators

6 papers

cs.LG2026

Don't Let Gains FADE: Breaking Down Policy Gradient Weights in RL

Juliette Decugis, Sean O'Brien, Francis Bach +2

Reinforcement learning post-training dramatically improves LLM reasoning, but suffers from training instability and diversity collapse. Advantage functions offer an appealing fix:…

cs.LG2026

A Few Bad Neurons: Isolating and Surgically Correcting Sycophancy

Claire O'Brien, Jessica Seto, Dristi Roy +6

Behavioral alignment in large language models (LLMs) is often achieved through broad fine-tuning, which can result in undesired side effects like distributional shift and low inter…

cs.CL2025

Separate the Wheat from the Chaff: Winnowing Down Divergent Views in Retrieval Augmented Generation

Song Wang, Zihan Chen, Peng Wang +5

Retrieval-augmented generation (RAG) enhances large language models (LLMs) by integrating external knowledge sources to address their limitations in accessing up-to-date or special…

cs.CL2025

Semantic Convergence: Investigating Shared Representations Across Scaled LLMs

Daniel Son, Sanjana Rathore, Andrew Rufail +6

We investigate feature universality in Gemma-2 language models (Gemma-2-2B and Gemma-2-9B), asking whether models with a four-fold difference in scale still converge on comparable…

cs.CL2025

Introducing MAPO: Momentum-Aided Gradient Descent Prompt Optimization

Anthony Cui, Pranav Nandyalam, Andrew Rufail +4

Momentum-Aided Prompt Optimization (MAPO) enhances the efficiency and efficacy of prompt optimization for Large Language Models (LLMs). Building on ProTeGi, MAPO uses positive natu…

cs.SD2025

Are you really listening? Boosting Perceptual Awareness in Music-QA Benchmarks

Yongyi Zang, Sean O'Brien, Taylor Berg-Kirkpatrick +2

Large Audio Language Models (LALMs), where pretrained text LLMs are finetuned with audio input, have made remarkable progress in music understanding. However, current evaluation me…