Tag
Sergey Levine announces he will be speaking at CVPR workshops on test-time scaling for computer vision and robot policy generalization, as well as on deployment of foundation models.
NVIDIA Research presents three papers at CVPR: GraspGen-X (zero-shot grasping foundation model), LCDrive (efficient autonomous driving reasoning), and NitroGen (generalized gameplay AI foundation model), highlighting training at scale for physical AI systems.
NVIDIA announced new physical AI agent skills at CVPR to accelerate research in autonomous vehicles, robotics, and vision AI, including tools for neural reconstruction, simulation, and reinforcement learning.
NielsRogge tweets a link to all CVPR papers.
A Hugging Face team member announces the addition of conference support to the revived PapersWithCode website, allowing users to browse all CVPR 2026 papers with arXiv IDs, categorized by task and linked to GitHub, project pages, and Hugging Face artifacts.
Papers With Code introduces a feature to browse all CVPR 2026 accepted papers by domain, with links to code, project pages, and Hugging Face artifacts, including Oral and Spotlight papers.
NVIDIA's LocateAnything, a vision-language detection model rethinking bounding box prediction, is now available as a Hugging Face Space and trending #1 on the platform. The space template was created by @_akhaliq.
NVIDIA introduces LocateAnything, a unified generative grounding and detection framework that uses Parallel Box Decoding to improve decoding throughput and localization accuracy. This work will be presented at CVPR 2026.
A CVPR 2026 accepted paper is accused of copying equations, figures and key ideas from an earlier arXiv submission without citation, highlighting gaps in conference plagiarism checks.