Boris Yangel

hr0nix's activity

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

New activity in Qwen/Qwen3-32B about 1 year ago

The correct way of fine-tuning on multi-turn trajectories

👍 12

3

#11 opened about 1 year ago by

hr0nix

commented a paper about 1 year ago

SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution

Paper • 2502.18449 • Published Feb 25, 2025 • 75 •

5