Reasoning Path and Latent State Analysis for Multi-view Visual Spatial Reasoning: A Cognitive Science Perspective Paper • 2512.02340 • Published Dec 2, 2025 • 1
Solaris: Building a Multiplayer Video World Model in Minecraft Paper • 2602.22208 • Published 3 days ago • 21
DreamID-Omni: Unified Framework for Controllable Human-Centric Audio-Video Generation Paper • 2602.12160 • Published 16 days ago • 36 • 4
OPUS: Towards Efficient and Principled Data Selection in Large Language Model Pre-training in Every Iteration Paper • 2602.05400 • Published 23 days ago • 341