Article
A Role Shift for AI Infra: From Foundational Support to a Core Engine of Innovation
NormalUhr
• • 1Yihua Zhang
NormalUhr
AI & ML interests
None yet
Organizations
published an article 7 months ago
published an article 9 months ago
Article
Re-understanding KL Approximation from an RL-for-LLM Lens: Notes on “Approximating KL Divergence”
NormalUhr
• • 10 published an article 9 months ago
Article
From GRPO to DAPO and GSPO: What, Why, and How
NormalUhr
• • 118 published an article 11 months ago
Article
Decorators in Machine Learning
NormalUhr
• • 1 published an article about 1 year ago
Article
DualPipe Explained: A Comprehensive Guide to DualPipe That Anyone Can Understand—Even Without a Distributed Training Background
NormalUhr
• • 18 published an article over 1 year ago
Article
Navigating the RLHF Landscape: From Policy Gradients to PPO, GAE, and DPO for LLM Alignment
NormalUhr
• • 119 published an article over 1 year ago
Article
DeepSeek-R1 Dissection: Understanding PPO & GRPO Without Any Prior Reinforcement Learning Knowledge
NormalUhr
• • 292 published an article over 1 year ago
Article
A Review on the Evolvement of Load Balancing Strategy in MoE LLMs: Pitfalls and Lessons
NormalUhr
• • 35 published an article over 1 year ago
Article
From Zero to Reasoning Hero: How DeepSeek-R1 Leverages Reinforcement Learning to Master Complex Reasoning
NormalUhr
• • 17 published an article over 1 year ago
Article
MLA: Redefining KV-Cache Through Low-Rank Projections and On-Demand Decompression
NormalUhr
• • 23