Cvpr 26 R2vlm

CVPR26 Poster: Recurrent Reasoning with Vision-Language Models for Estimating Long-Horizon Embodied Task Progress.

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

VIMCAN: Visual-Inertial 3D Human Pose Estimation with Hybrid Mamba-Cross-Attention Network.

Kiseok Choi, Hyeongjun Cho, Inchul Kim, Min H. Kim (2026) “Revisiting Pose Sensitivity in Splat-based Computed Tomography ...

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

This is our

[

[CVPR 2026] tttLRM: Test-Time Training for Long Context and Autoregressive 3D Reconstruction

Video2Robo: 3DGS-based Synthetic Data from One Video Enables Scalable Robot Learning Project page: ...

[

Paper: https://arxiv.org/abs/2512.01390 Project Page: https://cmlab-korea.github.io/FRAMER/ Authors/Affiliations: [Seungho ...

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

Hakyeong Kim, Ruicheng Wang, Chengtang Yao, Jiaolong Yang, Min H. Kim (2026) “Dense Metric Depth Completion from ...

iLRM explanation video (

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

[

Hakyeong Kim, Ruicheng Wang, Chengtang Yao, Jiaolong Yang, Min H. Kim (2026) “Dense Metric Depth Completion from ...