80 citations · 211 across the 42 of their papers we have counts for
13 papers · 1 filter
ARMOR: Stabilizing On-Policy LLM RL with Off-Policy Anchor Samples
Kexin Huang, Junkang Wu, Jinda Lu +7
Reinforcement learning (RL) has significantly enhanced the reasoning capabilities of large language models (LLMs), yet the training process remains notoriously fragile. In this wor…
On the Direction of RLVR Updates for LLM Reasoning: Identification and Exploitation
Kexin Huang, Haoming Meng, Junkang Wu +10
Reinforcement learning with verifiable rewards (RLVR) has substantially improved the reasoning capabilities of large language models. While existing analyses identify that RLVR-ind…
NExT-Guard: Training-Free Streaming Safeguard without Token-Level Labels
Junfeng Fang, Nachuan Chen, Houcheng Jiang +5
Large language models are increasingly deployed in streaming scenarios, rendering conventional post-hoc safeguards ineffective as they fail to interdict unsafe content in real-time…
MLLMEraser: Achieving Test-Time Unlearning in Multimodal Large Language Models through Activation Steering
Chenlu Ding, Jiancan Wu, Leheng Sheng +4
Multimodal large language models (MLLMs) have demonstrated remarkable capabilities across vision-language tasks, yet their large-scale deployment raises pressing concerns about mem…
Quantile Advantage Estimation: Stabilizing RLVR for LLM Reasoning
Junkang Wu, Kexin Huang, Jiancan Wu +3
Reinforcement Learning with Verifiable Rewards (RLVR) strengthens LLM reasoning, but training often oscillates between {entropy collapse} and {entropy explosion}. We trace both haz…
Route Sparse Autoencoder to Interpret Large Language Models
Wei Shi, Sihang Li, Tao Liang +4
Mechanistic interpretability of large language models (LLMs) aims to uncover the internal processes of information propagation and reasoning. Sparse autoencoders (SAEs) have demons…
RePO: Understanding Preference Learning Through ReLU-Based Optimization
Junkang Wu, Kexin Huang, Xue Wang +5
Aligning large language models (LLMs) with human preferences is critical for real-world deployment, yet existing methods like RLHF face computational and stability challenges. Whil…
Larger or Smaller Reward Margins to Select Preferences for Alignment?
Kexin Huang, Junkang Wu, Ziqian Chen +6
Preference learning is critical for aligning large language models (LLMs) with human values, with the quality of preference datasets playing a crucial role in this process. While e…
AlphaDPO: Adaptive Reward Margin for Direct Preference Optimization
Junkang Wu, Xue Wang, Zhengyi Yang +5
Aligning large language models (LLMs) with human values and intentions is crucial for their utility, honesty, and safety. Reinforcement learning from human feedback (RLHF) is a pop…
Towards Robust Alignment of Language Models: Distributionally Robustifying Direct Preference Optimization
Junkang Wu, Yuexiang Xie, Zhengyi Yang +6
This study addresses the challenge of noise in training datasets for Direct Preference Optimization (DPO), a method for aligning Large Language Models (LLMs) with human preferences…
EXGC: Bridging Efficiency and Explainability in Graph Condensation
Junfeng Fang, Xinglin Li, Yongduo Sui +5
Graph representation learning on vast datasets, like web data, has made significant strides. However, the associated computational and storage overheads raise concerns. In sight of…
Towards 3D Molecule-Text Interpretation in Language Models
Sihang Li, Zhiyuan Liu, Yanchen Luo +5
Language Models (LMs) have greatly influenced diverse domains. However, their inherent limitation in comprehending 3D molecular structures has considerably constrained their potent…
Understanding Contrastive Learning via Distributionally Robust Optimization
Junkang Wu, Jiawei Chen, Jiancan Wu +3
This study reveals the inherent tolerance of contrastive learning (CL) towards sampling bias, wherein negative samples may encompass similar semantics (\eg labels). However, existi…