Camille Dupont

cam-dupo's activity

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

upvoted a paper 1 day ago

Scoring Higher, Answering Worse: Mitigating Reward Hacking in Rubric-Based RL via Protocol-Level Rubrics

Paper • 2609.38847 • Published 16 days ago • 47

upvoted 2 papers 14 days ago

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

Paper • 2609.39102 • Published 16 days ago • 664

The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation

Paper • 2609.36484 • Published 17 days ago • 562

upvoted a paper 22 days ago

LimiX-2: A Contextual Mechanism Network Towards General Structured-Data Intelligence

Paper • 2609.17488 • Published about 1 month ago • 865