2 citations · 4 across the 18 of their papers we have counts for
21 papers
Self-Evolving Agents via Likelihood-Guided Tool-Space Optimization
Xuanqi Zhang, Ruinan Jin, Running Yang +4
Self-evolving agents can continually improve their behavior, while tools define the executable action space through which they interact with the environment. However, exposing the…
Learning Dynamics of Continual Learning: A Unified View of Data Attribution, Forgetting, and Plasticity Loss
Yi Ren, Wenlong Deng, Guanzhe Hong +2
Modern language models are likely to be updated throughout their lifetime rather than trained once and frozen. Each update therefore participates in a recurring cycle: decide which…
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…
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…
Spend Less, Reason Better: Budget-Aware Value Tree Search for LLM Agents
Yushu Li, Wenlong Deng, Jiajin Li +1
Test-time scaling has become a dominant paradigm for improving LLM agent reliability, yet current approaches treat compute as an abundant resource, allowing agents to exhaust token…
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…
On Group Relative Policy Optimization Collapse in Agent Search: The Lazy Likelihood-Displacement
Wenlong Deng, Yushu Li, Boying Gong +3
Tool-integrated (TI) reinforcement learning (RL) enables large language models (LLMs) to perform multi-step reasoning by interacting with external tools such as search engines and…
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…
Token Hidden Reward: Steering Exploration-Exploitation in Group Relative Deep Reinforcement Learning
Wenlong Deng, Yi Ren, Yushu Li +4
Reinforcement learning with verifiable rewards has significantly advanced the reasoning capabilities of large language models, yet how to explicitly steer training toward explorati…
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…
Enhancing Clinical Multiple-Choice Questions Benchmarks with Knowledge Graph Guided Distractor Generation
Running Yang, Wenlong Deng, Minghui Chen +2
Clinical tasks such as diagnosis and treatment require strong decision-making abilities, highlighting the importance of rigorous evaluation benchmarks to assess the reliability of…
On the Effect of Negative Gradient in Group Relative Deep Reinforcement Optimization
Wenlong Deng, Yi Ren, Muchen Li +3
Reinforcement learning (RL) has become popular in enhancing the reasoning capabilities of large language models (LLMs), with Group Relative Policy Optimization (GRPO) emerging as a…
MedReason: Eliciting Factual Medical Reasoning Steps in LLMs via Knowledge Graphs
Juncheng Wu, Wenlong Deng, Xingxuan Li +12
Medical tasks such as diagnosis and treatment planning require precise and complex reasoning, particularly in life-critical domains. Unlike mathematical reasoning, medical reasonin…
Can Textual Gradient Work in Federated Learning?
Minghui Chen, Ruinan Jin, Wenlong Deng +4
Recent studies highlight the promise of LLM-based prompt optimization, especially with TextGrad, which automates differentiation'' via texts and backpropagates textual feedback. Th…
DARE the Extreme: Revisiting Delta-Parameter Pruning For Fine-Tuned Models
Wenlong Deng, Yize Zhao, Vala Vakilian +3
Storing open-source fine-tuned models separately introduces redundancy and increases response times in applications utilizing multiple models. Delta-parameter pruning (DPP), partic…
Debiased Noise Editing on Foundation Models for Fair Medical Image Classification
Ruinan Jin, Wenlong Deng, Minghui Chen +1
In the era of Foundation Models' (FMs) rising prominence in AI, our study addresses the challenge of biases in medical images while the model operates in black-box (e.g., using FM…
LLM-Assisted Content Conditional Debiasing for Fair Text Embedding
Wenlong Deng, Blair Chen, Beidi Zhao +3
Mitigating biases in machine learning models has become an increasing concern in Natural Language Processing (NLP), particularly in developing fair text embeddings, which are cruci…
Unlocking the Potential of Prompt-Tuning in Bridging Generalized and Personalized Federated Learning
Wenlong Deng, Christos Thrampoulidis, Xiaoxiao Li
Vision Transformers (ViT) and Visual Prompt Tuning (VPT) achieve state-of-the-art performance with improved efficiency in various computer vision tasks. This suggests a promising p…
LESS: Label-efficient Multi-scale Learning for Cytological Whole Slide Image Screening
Beidi Zhao, Wenlong Deng, Zi Han +5
In computational pathology, multiple instance learning (MIL) is widely used to circumvent the computational impasse in giga-pixel whole slide image (WSI) analysis. It usually consi…
GMValuator: Similarity-based Data Valuation for Generative Models
Jiaxi Yang, Wenglong Deng, Benlin Liu +3
Data valuation plays a crucial role in machine learning. Existing data valuation methods, mainly focused on discriminative models, overlook generative models that have gained atten…