Hao Wang

K1zE's activity

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

upvoted 2 papers about 2 months ago

Stealing Reasoning Traces from Proprietary LLM APIs

Paper • 2608.09867 • Published Aug 10 • 122

Single-Rollout Asynchronous Optimization for Agentic Reinforcement Learning

Paper • 2607.07508 • Published Jul 8 • 34

upvoted an article about 2 months ago

view article

Article

Agentic RL: Token-In, Token-Out Done Right

• 

huggingface

•

May 29

• 33

authored a paper 2 months ago

Cross-Tokenizer On-Policy Distillation via Byte-Prefix Marginalization

Paper • 2607.22334 • Published Jul 24

updated a dataset 2 months ago

K1zE/BPM

Viewer • Updated Jul 27 • 20k • 69

updated a model 2 months ago

K1zE/BPM

Text Generation • 2B • Updated Jul 27 • 18

published a dataset 2 months ago

K1zE/BPM

Viewer • Updated Jul 27 • 20k • 69

published a model 2 months ago

K1zE/BPM

Text Generation • 2B • Updated Jul 27 • 18

liked a dataset 4 months ago

open-r1/DAPO-Math-17k-Processed

Viewer • Updated Nov 10, 2025 • 34.8k • 6.49k • 88

liked a Space 6 months ago

Running

99

TorchCode

🔥

99

Run and edit interactive notebooks in your browser