We have 4 of 6 papers
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
AIM-ZO is proposed, a ZO fine-tuning method based on Activation-Informed Subspace Maintenance that uses forward activations as local directional information and continuously integrates them into a broad, evolving subspace over training.
This work proposes Hyper-ES, a subspace-based ES framework that avoids the weakness of ES in full-parameter search while exploiting its strength in low-dimensional optimization, and consistently outperforms GRPO-LoRA while requiring 10% fewer space-consuming gradient updates.
These findings position ES as a distinct reasoning post-training paradigm rather than a less effective, memory-efficient alternative to GRPO, and study how hyperparameter design affects the effectiveness of ES, demonstrating that ES requires a smaller population size in a larger LLM.
Reinforcement Learning (RL) has been promising in single-turn LLM fine-tuning. However, long-horizon agentic reasoning introduces increasingly branching interactions and sparse rewards, exposing several limitations of RL: its heavyweight backpropagation-based training stack makes it impractical to fine-tune larger LLMs...
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
