Liangyu Wang

ly4096

https://liangyuwang.github.io/

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 about 1 month ago

Canzona: A Unified, Asynchronous, and Load-Balanced Framework for Distributed Matrix-based Optimizers

submitted a paper about 1 month ago

Canzona: A Unified, Asynchronous, and Load-Balanced Framework for Distributed Matrix-based Optimizers

upvoted a paper about 1 month ago

Canzona: A Unified, Asynchronous, and Load-Balanced Framework for Distributed Matrix-based Optimizers

View all activity

Organizations

upvoted 3 papers about 1 month ago

Canzona: A Unified, Asynchronous, and Load-Balanced Framework for Distributed Matrix-based Optimizers

Paper • 2602.06079 • Published Feb 4 • 18

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

Paper • 2507.01154 • Published Jul 1, 2025 • 1

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

Paper • 2506.22950 • Published Jun 28, 2025 • 1

upvoted a paper 11 months ago

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

Paper • 2503.12668 • Published Mar 16, 2025 • 1

Liangyu Wang

AI & ML interests

Recent Activity

Organizations

ly4096's activity