Daily AI Papers Briefing (2026-03-12)

ずんだもんのHugging Faceニュース · Mar 11, 2026 · 4m

【本日の論文】

1. Geometry-Guided Reinforcement Learning for Multi-view Consistent 3D Scene Editing

https://huggingface.co/papers/2603.03143

2. Thinking to Recall: How Reasoning Unlocks Parametric Knowledge in LLMs

https://huggingface.co/papers/2603.09906

3. Omni-Diffusion: Unified Multimodal Understanding and Generation with Masked Discrete Diffusion

https://huggingface.co/papers/2603.06577

4. MM-Zero: Self-Evolving Multi-Model Vision Language Models From Zero Data

https://huggingface.co/papers/2603.09206

5. InternVL-U: Democratizing Unified Multimodal Models for Understanding, Reasoning…