6 papers
A Framework for Quantifying How Pre-Training and Context Benefit In-Context Learning
Bingqing Song, Jiaxiang Li, Rong Wang +2
Pre-trained large language models have demonstrated a strong ability to learn from context, known as in-context learning (ICL). Despite a surge of recent applications that leverage…
ADARL: Adaptive Low-Rank Structures for Robust Policy Learning under Uncertainty
Chenliang Li, Junyu Leng, Jiaxiang Li +4
Robust reinforcement learning (Robust RL) seeks to handle epistemic uncertainty in environment dynamics, but existing approaches often rely on nested min--max optimization, which i…
Muon Outperforms Adam in Tail-End Associative Memory Learning
Shuche Wang, Fengzhuo Zhang, Jiaxiang Li +6
The Muon optimizer is consistently faster than Adam in training Large Language Models (LLMs), yet the mechanism underlying its success remains unclear. This paper demystifies this…
Aligning Frozen LLMs by Reinforcement Learning: An Iterative Reweight-then-Optimize Approach
Xinnan Zhang, Chenliang Li, Siliang Zeng +6
Aligning large language models (LLMs) with human preferences usually requires fine-tuning methods such as RLHF and DPO. These methods directly optimize the model parameters, so the…
Scalable Parameter and Memory Efficient Pretraining for LLM: Recent Algorithmic Advances and Benchmarking
Athanasios Glentis, Jiaxiang Li, Qiulin Shang +4
Fueled by their remarkable ability to tackle diverse tasks across multiple domains, large language models (LLMs) have grown at an unprecedented rate, with some recent models contai…
A Note on the Convergence of Muon
Jiaxiang Li, Mingyi Hong
In this note, we inspect the convergence of a new optimizer for pretraining LLMs, namely the Muon optimizer. Such an optimizer is closely related to a specialized steepest descent…