Tokenlight Cvpr 2026

TokenLight

Disentangle-then-Align: Non-Iterative Hybrid Multimodal Image Registration via Cross-Scale Feature Disentanglement.

Hyun Lee, Hyemin Jeong, Yejin Kim, Hyungwook Choi, Hyunsoo Cho, Soo Kyung Kim, Joonseok Lee. A More Word-like Image ...

[

In this video, we introduce a novel video object detection framework called D2FANet. D2FANet is the first framework to jointly ...

We introduce our

The 5-minute introduction video of IntrinsicWeather.

[CVPR 2026] VGent: Visual Grounding via Modular Design for Disentangling Reasoning and Prediction

[CVPR 2026] Hear What You See: Video-to-Audio Generation with Diffusion Transformer and STAR-DPO

COinCO: Common Inpainted Objects In-N-Out of Context (CVPR 2026)

Dynamic Token Reweighting for Robust Vision-Language Models Tanqiu Jiang, Jiacheng Liang, Rongyi Zhu, Jiawei Zhou, ...

GeoRelight: Learning Joint Geometrical Relighting and Reconstruction with Flexible Multi-Modal Diffusion Transformers Y. Xue, ...

UniPR: Unified Object-level Real-to-Sim Perception and Reconstruction from a Single Stereo Pair Project Page: ...

DiffusionFF: A Diffusion-based Framework for Joint Face Forgery Detection and Fine-Grained Artifact Localization (

Leon Liangyu Chen, Haoyu Ma, Zhipeng Fan, Ziqi Huang, Animesh Sinha, Xiaoliang Dai, Jialiang Wang, Zecheng He, Jianwei ...

T. Koleilat, H. Asgariandehkordi, O. Nejatimanzari, B. Barile, Y. Xiao*, H. Rivaz*, "MedCLIPSeg: Probabilistic Vision-Language ...

Reinforcement Learning (RL) has achieved remarkable success in various domains, yet it often relies on carefully designed ...

[

CVPR 2026 TAR presentation