Seven Papers Accepted by CVPR 2026
- Cross-Domain Few-Shot Segmentation via Multi-view Progressive Adaptation.
- LongVT: Incentivizing" thinking with long videos" via native tool calling.
- Boosting Reasoning in Large Multimodal Models via Activation Replay.
- A Comprehensive Study on Visual Token Redundancy for Discrete Diffusion-based Multimodal Large Language Models. [Findings]
- Mmr1: Advancing the frontiers of multimodal reasoning. [Findings]
- L3DR: 3D-aware LiDAR Diffusion and Rectification.
- Direction-aware 3D Large Multimodal Models.