Actor as Its Own Critic: Unifying Region Understanding and Localization via CycleGRPO Paper • 2607.11581 • Published Sep 2 • 1
Generalized CycleGRPO for Fine-Grained Multimodal Understanding and Grounding Paper • 2610.29552 • Published about 1 month ago • 7
Open-o3-Video-v2: Seek, Ground, and Reason with Verifiable Spatio-Temporal Evidence Paper • 2610.17656 • Published Oct 13 • 19
PerceptionDLM: Parallel Region Perception with Multimodal Diffusion Language Models Paper • 2606.19534 • Published Jun 17 • 65
Mamba as a Bridge: Where Vision Foundation Models Meet Vision Language Models for Domain-Generalized Semantic Segmentation Paper • 2504.03193 • Published Apr 4, 2025 • 4