DeepGen 1.0: A Lightweight Unified Multimodal Model for Advancing Image Generation and Editing Paper • 2602.12205 • Published 5 days ago • 76
UniReason 1.0: A Unified Reasoning Framework for World Knowledge Aligned Image Generation and Editing Paper • 2602.02437 • Published 15 days ago • 76
PhysBrain: Human Egocentric Data as a Bridge from Vision Language Models to Physical Intelligence Paper • 2512.16793 • Published Dec 18, 2025 • 75
Euclid's Gift: Enhancing Spatial Perception and Reasoning in Vision-Language Models via Geometric Surrogate Tasks Paper • 2509.24473 • Published Sep 29, 2025 • 18