14 papers
When RAG Hurts: Diagnosing and Mitigating Attention Distraction in Retrieval-Augmented LVLMs
Beidi Zhao, Wenlong Deng, Xinting Liao +4
While Retrieval-Augmented Generation (RAG) is one of the dominant paradigms for enhancing Large Vision-Language Models (LVLMs) on knowledge-based VQA tasks, recent work attributes…
Directional Alignment Mitigates Reward Hacking in Reinforcement Learning for Language Models
Wenlong Deng, Jiaji Huang, Kaan Ozkara +4
Reward hacking arises when a model improves a proxy reward by exploiting shortcuts rather than solving the intended task. We study this failure mode through the geometry of reinfor…
For-Value: Efficient Forward-Only Data Valuation for finetuning LLMs and VLMs
Wenlong Deng, Qi Zeng, Jiaming Zhang +5
Data valuation is essential for enhancing the transparency and accountability of large language models (LLMs) and vision-language models (VLMs). However, existing methods typically…
MetaDent: Labeling Clinical Images for Vision-Language Models in Dentistry
Meng-Xun Li, Wen-Hui Deng, Zhi-Xing Wu +6
Vision-Language Models (VLMs) have demonstrated significant potential in medical image analysis, yet their application in intraoral photography remains largely underexplored due to…
Textual Equilibrium Propagation for Deep Compound AI Systems
Minghui Chen, Wenlong Deng, James Zou +2
Large language models (LLMs) are increasingly deployed as part of compound AI systems that coordinate multiple modules (e.g., retrievers, tools, verifiers) over long-horizon workfl…
Advantage Shaping as Surrogate Reward Maximization: Unifying Pass@K Policy Gradients
Christos Thrampoulidis, Sadegh Mahdavi, Wenlong Deng
This note reconciles two seemingly distinct approaches to policy gradient optimization for the Pass@K objective in reinforcement learning with verifiable rewards: (1) direct REINFO…