Publications (18)
Are Full Rollouts Necessary for On-Policy Distillation?
Yaocheng Zhang, Jiajun Chai, Yuqian Fu +7
On-policy distillation (OPD) provides dense teacher feedback along student-generated rollouts rather than fixed teacher traces and has emerged as a promising post-training paradigm…
Saliency-Guided Representation with Consistency Policy Learning for Visual Unsupervised Reinforcement Learning
Jingbo Sun, Qichao Zhang, Songjun Tu +5
Zero-shot unsupervised reinforcement learning (URL) offers a promising direction for building generalist agents capable of generalizing to unseen tasks without additional supervisi…
One LR Doesn't Fit All: Heavy-Tail Guided Layerwise Learning Rates for LLMs
Di He, Songjun Tu, Keyu Wang +2
Learning rate configuration is a fundamental aspect of modern deep learning. The prevailing practice of applying a uniform learning rate across all layers overlooks the structural…
AutoSearch: Adaptive Search Depth for Efficient Agentic RAG via Reinforcement Learning
Jingbo Sun, Wenyue Chong, Songjun Tu +7
Agentic retrieval-augmented generation (RAG) systems enable large language models (LLMs) to solve complex tasks through multi-step interaction with external retrieval tools. Howeve…
MemChain: Learning Interpretable Memory Traces for Memory-Augmented LLM Agents
Yiwen Ma, Songjun Tu, Qichao Zhang +3
Memory-augmented LLM agents typically answer queries by retrieving relevant memories and feeding them directly to an answer model. This retrieval-as-evidence paradigm assumes retri…
Enhancing LLM Reasoning with Iterative DPO: A Comprehensive Empirical Investigation
Songjun Tu, Jiahao Lin, Xiangyu Tian +8
Recent advancements in post-training methodologies for large language models (LLMs) have highlighted reinforcement learning (RL) as a critical component for enhancing reasoning. Ho…