Rethinking Cross-Tokenizer On-Policy Distillation: From Alignment Coverage to Supervision Reliability
Paper • 2610.08448 • Published • 151
Mark Miller
Mark1Miller
AI & ML interests
None yet
Recent Activity
upvoted a paper about 13 hours ago
Rethinking Cross-Tokenizer On-Policy Distillation: From Alignment Coverage to Supervision Reliability upvoted a paper about 1 month ago
Compile by Training: Turning Natural-Language Specifications into Local Neural Functions upvoted a paper about 1 month ago
LatentPress: Context Compression Beyond Text and VisionOrganizations
None yet
upvoted a paper about 13 hours ago
upvoted 4
papers about 1 month ago
Compile by Training: Turning Natural-Language Specifications into Local Neural Functions
Paper • 2609.04199 • Published • 333
LatentPress: Context Compression Beyond Text and Vision
Paper • 2609.01507 • Published • 122
LLaDA-Image: Building Strong Image Generators with Fully Open Training Recipes
Paper • 2609.03796 • Published • 186
Terminal-Universe: Turning Agent Trajectories into Scalable Terminal Environments
Paper • 2609.04148 • Published • 248