Joseph Martin

JosephMartin123

4

AI & ML interests

None yet

Recent Activity

upvoted a paper 3 days ago

Waypoint-OPD: Transferring RL-Induced Policy Shifts via Gated On-Policy Distillation

upvoted a paper 12 days ago

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

upvoted a paper about 1 month ago

LLaDA-Image: Building Strong Image Generators with Fully Open Training Recipes

View all activity

Organizations

None yet

upvoted a paper 3 days ago

Waypoint-OPD: Transferring RL-Induced Policy Shifts via Gated On-Policy Distillation

Paper • 2610.21601 • Published 4 days ago • 669

upvoted a paper 12 days ago

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

Paper • 2610.08448 • Published 13 days ago • 213

upvoted 2 papers about 1 month ago

LLaDA-Image: Building Strong Image Generators with Fully Open Training Recipes

Paper • 2609.03796 • Published Sep 3 • 183

Terminal-Universe: Turning Agent Trajectories into Scalable Terminal Environments

Paper • 2609.04148 • Published Sep 3 • 212