Daily AI Papers Briefing (2026-10-02)

ずんだもんのHugging Faceニュース · Oct 2, 2026 · 3m

【本日の論文】

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

https://huggingface.co/papers/2609.36484

2. UniEvo-VL: An On-policy Self-Distillation Training Recipe for Multimodal Model Self-improvement

https://huggingface.co/papers/2609.38721

3. Rethinking Latent Visual Reasoning: Grounding Latent Reasoning in Visual Evidence

https://huggingface.co/papers/2609.34563

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

https://huggingface.co/papers/2609.39102

5. AREX-2: Advancing…