Liangyu Wang

ly4096

https://liangyuwang.github.io/

liangyuwang10
liangyuwang
liangyu-wang-in

AI & ML interests

Efficient reinforcement learning (RL) for LLMs reasoning Distributed training and inference of LLMs Efficient algorithm and infrastructure design for LLMs

Organizations

authored 3 papers 2 months ago

Infinite Sampling: Efficient and Stable Grouped RL Training for Large Language Models

Paper • 2506.22950 • Published Jun 28

FlashDP: Private Training Large Language Models with Efficient DP-SGD

Paper • 2507.01154 • Published Jul 1

DistZO2: High-Throughput and Memory-Efficient Zeroth-Order Fine-tuning LLMs with Distributed Parallel Computing

Paper • 2507.03211 • Published Jul 3

authored a paper 9 months ago

ZO2: Scalable Zeroth-Order Fine-Tuning for Extremely Large Language Models with Limited GPU Memory

Paper • 2503.12668 • Published Mar 16 • 1

Liangyu Wang

AI & ML interests

Organizations

ly4096's activity