3 citations · 3 across the 5 of their papers we have counts for
5 papers · 1 filter
Allspark: Weak to Strong Transfer via Alternating Chain of Thought
Kaizhao Liang, Junxiong Wang, Chen Liang +2
Recent progress in frontier models has renewed interest in large-scale reinforcement learning (RL), but the cost of generating large-model rollouts makes even testing RL recipes ex…
Cautious Weight Decay
Lizhang Chen, Jonathan Li, Kaizhao Liang +6
We introduce Cautious Weight Decay (CWD), a one-line, optimizer-agnostic modification that applies weight decay only to parameter coordinates whose signs align with the optimizer u…
Cautious Optimizers: Improving Training with One Line of Code
Kaizhao Liang, Lizhang Chen, Bo Liu +1
AdamW has been the default optimizer for transformer pretraining. For many years, our community searched for faster and more stable optimizers with only constrained positive outcom…
Memory-Efficient LLM Training with Online Subspace Descent
Kaizhao Liang, Bo Liu, Lizhang Chen +1
Recently, a wide range of memory-efficient LLM training algorithms have gained substantial popularity. These methods leverage the low-rank structure of gradients to project optimiz…
Lion Secretly Solves Constrained Optimization: As Lyapunov Predicts
Lizhang Chen, Bo Liu, Kaizhao Liang +1
Lion (Evolved Sign Momentum), a new optimizer discovered through program search, has shown promising results in training large AI models. It performs comparably or favorably to Ada…