Chain-of-Visual-Thought: Teaching VLMs to See and Think Better with Continuous Visual Tokens Paper • 2511.19418 • Published Nov 24, 2025 • 29
UnSAMv2: Self-Supervised Learning Enables Segment Anything at Any Granularity Paper • 2511.13714 • Published Nov 17, 2025 • 12
Reconstruction Alignment Improves Unified Multimodal Models Paper • 2509.07295 • Published Sep 8, 2025 • 40