3 citations · 3 across the 10 of their papers we have counts for
10 papers
STU: Stateful Test-Time Unlearning via Restricted Knowledge Boundary Control
Xunlei Chen, Qinghui Gong, Ruini Xue +3
Controlling restricted knowledge in large language models is essential for model alignment and safe deployment. Test-time unlearning avoids costly retraining and parameter updates…
UAM: A Dual-Stream Perspective on Forgetting in VLA Training
Jianke Zhang, Yuanfei Luo, Yucheng Hu +6
Vision--language--action (VLA) models are typically built by fine-tuning a pretrained vision--language model (VLM) on action data. However, we show that this standard recipe system…
Improving Multi-turn Dialogue Consistency with Self-Recall Thinking
Renning Pang, Tian Lan, Leyuan Liu +3
Large language model (LLM) based multi-turn dialogue systems often struggle to track dependencies across non-adjacent turns, undermining both consistency and scalability. As conver…
Case-Based Calibration of Adaptive Reasoning and Execution for LLM Tool Use
Renning Pang, Tian Lan, Leyuan Liu +3
Tool use extends large language models beyond parametric knowledge, but reliable execution requires balancing appropriate reasoning depth with strict structural validity. We approa…
Matrix-Space Reinforcement Learning for Reusing Local Transition Geometry
Zuyuan Zhang, Carlee Joe-Wong, Tian Lan
Compositional generalization in sequential decision-making requires identifying which parts of prior rollouts remain useful for new tasks. Existing methods reuse skills or predicti…
Interactive Critique-Revision Training for Reliable Structured LLM Generation
Fei Xu Yu, Zuyuan Zhang, Mahdi Imani +2
In structured decision-making workflows such as form filling, compliance checking, and maintenance reporting, LLM outputs must be locally correct, globally consistent, and auditabl…
Diff-Feat: Diffusion-Based Cross-Modal Feature Extraction for Multi-Label Classification
Tian Lan, Yiming Zheng, Jianxin Yin
Multi-label classification has broad applications and depends on powerful representations capable of capturing multiple interactions. We introduce Diff-Feat, a simple yet effective…
Learning from Random Demonstrations: Offline Reinforcement Learning with Importance-Sampled Diffusion Models
Zeyu Fang, Tian Lan
Generative models such as diffusion have been employed as world models in offline reinforcement learning to generate synthetic data for more effective learning. Existing work eithe…
Repetition In Repetition Out: Towards Understanding Neural Text Degeneration from the Data Perspective
Huayang Li, Tian Lan, Zihao Fu +5
There are a number of diverging hypotheses about the neural text degeneration problem, i.e., generating repetitive and dull loops, which makes this problem both interesting and con…
Advantage Actor-Critic with Reasoner: Explaining the Agent's Behavior from an Exploratory Perspective
Muzhe Guo, Feixu Yu, Tian Lan +1
Reinforcement learning (RL) is a powerful tool for solving complex decision-making problems, but its lack of transparency and interpretability has been a major challenge in domains…