collaborators

14 papers

cs.CV2026

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…

cs.LG2026

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…

cs.CL2026

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…

cs.CV2026

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…

cs.LG2026

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…

cs.LG2026

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…