Jason Garcia

garciajason

3

AI & ML interests

I run marathons and train models. Both are painful.

Recent Activity

upvoted a paper 19 days ago

WorkRover: Scaling Long-Horizon Cowork Agent Training Via Recursive Environment Evolution

updated a model 28 days ago

garciajason/efficient-attention

published a model 28 days ago

garciajason/efficient-attention

View all activity

Organizations

None yet

upvoted a paper 19 days ago

WorkRover: Scaling Long-Horizon Cowork Agent Training Via Recursive Environment Evolution

Paper • 2610.18067 • Published 21 days ago • 41

upvoted 2 papers 28 days ago

FrameMorrow: Future-guided Frame Selection with Prospective Tokens for Long-Horizon Video Generation

Paper • 2609.38839 • Published Sep 30 • 56

False Frontiers: Diagnosing and Mitigating Co-Cheating in Self-Evolving Search Agents

Paper • 2609.39102 • Published Sep 30 • 159