Yixin Dong

ubospica's activity

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

upvoted a paper about 1 month ago

AstraFlow: Dataflow-Oriented Reinforcement Learning for Agentic LLMs

Paper • 2605.15565 • Published May 15 • 17

upvoted 2 papers 8 months ago

When "Correct" Is Not Safe: Can We Trust Functionally Correct Patches Generated by Code Agents?

Paper • 2510.17862 • Published Oct 15, 2025 • 7

Efficient Long-context Language Model Training by Core Attention Disaggregation

Paper • 2510.18121 • Published Oct 20, 2025 • 124

upvoted a paper 9 months ago

Prosperity before Collapse: How Far Can Off-Policy RL Reach with Stale Data on LLMs?

Paper • 2510.01161 • Published Oct 1, 2025 • 14

upvoted a paper about 1 year ago

Multiverse: Your Language Models Secretly Decide How to Parallelize and Merge Generation

Paper • 2506.09991 • Published Jun 11, 2025 • 55