10 papers
Agentic Recommender System with Hierarchical Belief-State Memory
Xiang Shen, Yuhang Zhou, Yifan Wu +8
Memory-augmented LLM agents have advanced personalized recommendation, yet existing approaches universally adopt flat memory representations that conflate ephemeral signals with st…
Enjoy Your Layer Normalization with the Computational Efficiency of RMSNorm
Yuxin Guo, Yihao Yue, Yunhao Ni +4
Layer normalization (LN) is a fundamental component in modern deep learning, but its per-sample centering and scaling introduce non-negligible inference overhead. RMSNorm improves…
From Generic Correlation to Input-Specific Credit in On-Policy Self Distillation
Guobin Shen, Lei Huang, Xiang Cheng +4
On-policy self-distillation has emerged as a promising paradigm for post-training language models, in which the model conditions on environment feedback to serve as its own teacher…
Anti-Self-Distillation for Reasoning RL via Pointwise Mutual Information
Guobin Shen, Xiang Cheng, Chenxiao Zhao +4
On-policy self-distillation, where a student is pulled toward a copy of itself conditioned on privileged context (e.g., a verified solution or feedback), offers a promising directi…
VESPO: Variational Sequence-Level Soft Policy Optimization for Stable Off-Policy LLM Training
Guobin Shen, Chenxiao Zhao, Xiang Cheng +2
Off-policy updates are inevitable in reinforcement learning (RL) for large language models (LLMs) due to rollout staleness from asynchronous training and mismatches between trainin…
Watermark Robustness and Radioactivity May Be at Odds in Federated Learning
Leixu Huang, Zedian Shao, Teodora Baluta
Federated learning (FL) enables fine-tuning large language models (LLMs) across distributed data sources. As these sources increasingly include LLM-generated text, provenance track…