Thomas Kim PRO

bytkim's activity

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

upvoted a paper 7 days ago

Rethinking Cross-Tokenizer On-Policy Distillation: From Alignment Coverage to Supervision Reliability

Paper • 2610.08448 • Published 14 days ago • 80

upvoted an article 19 days ago

view article

Article

Qwen3.8-27B-pi: Effort-Ordered Reasoning for Agentic Coding

• 

bytkim

•

19 days ago

• 16

upvoted a collection 20 days ago

Qwen3.8-pi

Collection

Qwen3.8 models fine-tuned for the Pi coding harness • 3 items • Updated 19 days ago • 5

upvoted 3 papers about 1 month ago

RealSWE: A Compositional Evaluation of Coding Agents under Realistic User Requests

Paper • 2608.27831 • Published Aug 31 • 34

Group Adaptive Clipping Policy Optimization

Paper • 2609.00444 • Published Aug 31 • 10

Terminal-Universe: Turning Agent Trajectories into Scalable Terminal Environments

Paper • 2609.04148 • Published Sep 3 • 134

upvoted a collection 3 months ago

Qwen3.6 Pi-Tune

Collection

Releases of Qwen3.6 family models fine tuned with the goal of improving agentic coding quality with PI • 2 items • Updated Jul 9 • 4

upvoted an article 4 months ago

view article

Article

QLORA SFT Distillation Effects on Qwen3.6 27B Agentic Coding Harness Fluency

• 

bytkim

•

Jun 15

• 10