Daily AI Papers Briefing (2026-10-03)

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

【本日の論文】

1. OneStreamer: Unifying Perception, Memory, and Proactive Response in Streaming Video Interaction

https://huggingface.co/papers/2610.01762

2. Adaptive Reward Routing: Dynamic Multi-Reward Optimization for Joint Audio-Video Diffusion via Forward-Process RL

https://huggingface.co/papers/2609.37200

3. On-Policy or Off-Policy Learning? A Systematic Study of Distillation Dynamics

https://huggingface.co/papers/2609.35259

4. Beyond Memory: Harnessing Long-Horizon Agents with Explicit Belief States

https://huggingface.co/papers/2610.01415

5. Hierarchical Continuous Diffusion Language Models…