Liangyu Wang
ly4096
ยท
AI & ML interests
Efficient reinforcement learning (RL) for LLMs reasoning
Distributed training and inference of LLMs
Efficient algorithm and infrastructure design for LLMs
Recent Activity
authored
a paper
7 days ago
Infinite Sampling: Efficient and Stable Grouped RL Training for Large
Language Models
authored
a paper
7 days ago
FlashDP: Private Training Large Language Models with Efficient DP-SGD
authored
a paper
7 days ago
DistZO2: High-Throughput and Memory-Efficient Zeroth-Order Fine-tuning
LLMs with Distributed Parallel Computing
Organizations
