Big congrats to our SAM 3D team for receiving a Best Paper Honorable Mention at #CVPR26! This prestigious recognition underscores their incredible work pushing the boundaries of computer vision. Read the paper here: arxiv.org/abs/2511.16624

Happy to announce that our paper "MIBURI: Towards Expressive Interactive Gesture Synthesis" by @mhamzamughal09 received two awards at #CVPR2026 🎉 🏆 Best Demo Award at #CVPR26 Main Conference 🏆 Best Paper Award at the Interactive Physical AI Workshop, organized by NVIDIA AI

this is not a comment on award-open code discussion but here are two examples in favor of open all the way: - because of a no-code, no-data baseline, we don't know what to do about a closely related CVPR26 work. - a truly borderline case in my AC batch with a few unclear details could be accepted because code is promised.

Great to chat with researchers about their work at CVPR 2026 in Denver! Here are some paper highlights ✨ NitroGen (@loicmagne_): a gaming foundation model trained on 40k hours of data. Interesting to see how these agents can generalize across games. SoccerMaster (Haolin Yang): a soccer foundation model that combines many soccer understanding tasks. Rather than many bespoke models, SoccerMaster unifies these tasks into one model. Particulate (Yuxin Yao): model to predict 3D articulations of an object given a 3D mesh. I see many practical use cases in digital/simulation environments. EgoAVU (Ashish Seth): data engine for greater egocentric audio-visual understanding. Great chatting about how we can improve video descriptions via a multimodal context graph. Thanks again to these researchers for sharing about their work! Paper links in the comments 👇 #cvpr #cvpr26 #computervision

#CVPR26 Best Paper Finalists (including winners) Mapping Networks cvpr.thecvf.com/virtual/2026… VGGT-Ω cvpr.thecvf.com/virtual/2026… Towards Photorealistic and Efficient Bokeh Rendering via Diffusion Framework cvpr.thecvf.com/virtual/2026… (Cont'd)

#CVPR26 Best Student Paper Honorable Mention ChordEdit: One-Step Low-Energy Transport for Image Editing cvpr.thecvf.com/virtual/2026…

#CVPR26 Best Paper Honorable Mention SAM 3D: 3Dfy Anything in Images cvpr.thecvf.com/virtual/2026… github.com/facebookresearch/… Best Student Paper Native and Compact Structured Latents for 3D Generation cvpr.thecvf.com/virtual/2026…

#CVPR26 Best Paper Efficiently Reconstructing Dynamic Scenes One D4RT at a Time cvpr.thecvf.com/virtual/2026… d4rt-paper.github.io/ Best Paper Honorable Mention NitroGen: An Open Foundation Model for Generalist Gaming Agents cvpr.thecvf.com/virtual/2026…

ShapeR at #CVPR26! Come visit the poster in the Saturday afternoon session, Jun 6, 2026, 3:45 PM – 5:45 PM PDT, ExHall A & F, Poster No. 534.

We are presenting at #CVPR over the weekend our research on “Watermarking AI Generated Content” I would not be attending this year, but some of my talented co-authors will be presenting. Would love to hear your thoughts and suggestions on the paper or just stop by for saying hi or DM ! @i_amanchadha @sharmavasu55 @amitava_santu @VinijaJain @shashwatb1729 youtu.be/-4oS_yo7MY4?si=_e3s… #CVPR26 #PECCAVI

We were amazed by @AnthropicAI circuit tracing work for LLM and started exploring how to build similar tools for vision-language models. We introduce the first framework for transparent circuit tracing in VLMs, enabling systematic analysis of multimodal reasoning. #CVPR26 findings paper. Circuit Tracing in Vision-Language Models: Understanding the Internal Mechanisms of Multimodal Thinking June 6, 7:30AM to 9:00 AM Poster No. 6

Fun fact: the apartment we rented in Oxford Summertown from 2021-2023 has accommodated @elliottszwu (CVPR20 best paper awardee) and @jianyuan_wang (CVPR25 best paper awardee) as subletters. Now also @ChuhanZhang5 - new CVPR26 best paper awardee. Grateful to be at @Oxford_VGG !!

CVPR26の統計情報。参加者12K、投稿16K、採択4K (採択率25.3%)

everybody's talking about world models at #CVPR26 and no one knows exactly what they are

Nataniel @natanielruizg is giving an amazing talk at #P13N workshop @CVPR #CVPR26

My students and collaborators are presenting posters at the #CVPR26 #CV4Animals workshop today from 11:30-12:30! @AntoineScience is presenting interactive Elephant Re-Identification @mridulk97 is presenting taxonomic-aligned image generation of fine-grained species (More 👇)

I will be presenting some of my team's recent work thinking about how to target human verification for robustAI deployment at #CVPR26 today at the Domain Generalization workshop! 1:35pm in 103 🤩

Tessera, the AI tool that lets anyone monitor environmental change from a laptop, is to be presented at #CVPR26, the world's leading AI and computer vision conference! 🛰️ geotessera.org/blog/2026-06-… @CVPR @Cambridge_CL @esa #EarthObservation #RemoteSensing

CVPR26 ＠コロラドに来ました！