False Frontiers: Diagnosing and Mitigating Co-Cheating in Self-Evolving Search Agents
Paper • 2609.39102 • Published • 159
Daniel Jones
danieljones5
AI & ML interests
None yet
Recent Activity
updated a dataset 16 days ago
danieljones5/learn-food published a dataset 16 days ago
danieljones5/learn-food updated a model 16 days ago
danieljones5/review-image-captioningOrganizations
None yet
upvoted 5
papers about 1 month ago
MaLiang-Harness: A Programmable Path to Image and Video Generation
Paper • 2609.34309 • Published • 98
UniEvo-VL: An On-policy Self-Distillation Training Recipe for Multimodal Model Self-improvement
Paper • 2609.38721 • Published • 143
The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation
Paper • 2609.36484 • Published • 179
Training Object Permanence in World Models
Paper • 2609.28654 • Published • 115