Haizhou Zhao

hydrozhao's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a paper 22 days ago

The Mirage of Optimizing Training Policies: Monotonic Inference Policies as the Real Objective for LLM Reinforcement Learning

Paper • 2606.29526 • Published Jun 28 • 170

upvoted a paper 2 months ago

Full Attention Strikes Back: Transferring Full Attention into Sparse within Hundred Training Steps

Paper • 2605.16928 • Published May 16 • 99

upvoted 2 articles 4 months ago

view article

Article

Ultra-Long Sequence Parallelism: Ulysses + Ring-Attention Technical Principles and Implementation

• 

exploding-gradients

•

Sep 16, 2025

• 21

view article

Article

Forge: Scalable Agent RL Framework and Algorithm

• 

MiniMax-AI

•

Feb 13

• 156

upvoted a paper 4 months ago

Complementary Reinforcement Learning

Paper • 2603.17621 • Published Mar 18 • 37

liked a Space 7 months ago

Running

34

Megatron Memory Estimator

👁

34

Estimate GPU memory usage for Megatron models

upvoted a paper 7 months ago

Let It Flow: Agentic Crafting on Rock and Roll, Building the ROME Model within an Open Agentic Learning Ecosystem

Paper • 2512.24873 • Published Dec 31, 2025 • 110

upvoted a paper 10 months ago

Attention Illuminates LLM Reasoning: The Preplan-and-Anchor Rhythm Enables Fine-Grained Policy Optimization

Paper • 2510.13554 • Published Oct 15, 2025 • 59

upvoted a paper 11 months ago

Ovis2.5 Technical Report

Paper • 2508.11737 • Published Aug 15, 2025 • 116

upvoted a paper 12 months ago

Part I: Tricks or Traps? A Deep Dive into RL for LLM Reasoning

Paper • 2508.08221 • Published Aug 11, 2025 • 50

upvoted a paper about 1 year ago

Reinforcement Learning Optimization for Large-Scale Learning: An Efficient and User-Friendly Scaling Library

Paper • 2506.06122 • Published Jun 6, 2025 • 7

liked a model over 1 year ago

Qwen/Qwen2.5-7B-Instruct

Text Generation • 8B • Updated Jan 12, 2025 • 12.1M • • 1.44k