A well-deserved recognition for excellence in Artificial Intelligence and Computer Vision. Congratulations to our distinguished alumnus, Prof. Deepak Pathak (BT/CSE/2014), on receiving the 2026 Pattern Analysis and Machine Intelligence (PAMI) Young Researcher Award at the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). The award is among the highest honours in computer vision and recognises outstanding contributions to the field. Currently serving as the Raj Reddy Assistant Professor at Carnegie Mellon University, Prof. Pathak works in the fields of Artificial Intelligence, Computer Vision, Machine Learning, and Robotics. He is also the Co-Founder and CEO of Skild AI, where he is leading the development of an AI foundation model for robotics. We congratulate Prof. Pathak on this prestigious recognition and wish him continued success in advancing the fields of Artificial Intelligence and Computer Vision. #IITKanpur #AlumniAchievement #ArtificialIntelligence #IITKanpurAlumni #Robotics #IEEE #ResearchExcellence

Continuing its tradition of having the largest Indian research delegation, this year too, IIIT-H presented its cutting edge work at the main Computer Vision and Pattern Recognition (CVPR) conference and its associated workshops. blogs.iiit.ac.in/cvpr-2026/

国際学会でコスプレするな コミケでポスター発表するぞ (CVPRでもフリーレン居たけど、おもしろいから続いて欲しい文化)

Con datos no basta, la precisión de objetos transparentes impulsa productividad: GLINT demuestra reconocimiento de vidrio y entorno, clave para robótica y vehículos autónomos. Fuentes: ICLR, CVPR. ift.tt/ogP7dMt

How Much Future Helps? A Controlled Study of Future-Privileged Supervision for Causal Egocentric Gaze Estimation Jia Li, Wenjie Zhao, … arxiv.org/abs/2607.01437 [𝚌𝚜.𝙲𝚅] 💬Accepted to the 7th International Workshop on Eye and Gaze in Computer Vision (GAZE 2026), CVPR 2026

99.9% AUROC on MVTec sounds like a solved problem — until you deploy in a real warehouse and the numbers collapse. That's the gap Amazon's Kaputt dataset was built to expose. Read it here: hubs.ly/Q04nvHY90 * 230K images * 29K defective instances * 48K distinct objects Roughly 40x larger than MVTec, with the messy pose and appearance variation of actual retail logistics. The best state-of-the-art methods scored just 56.96% AUROC. Barely better than a coin flip. It powered the Retail Track of the VAND 4.0 Challenge at CVPR 2026, and our latest post walks through how to explore Kaputt with open source FiftyOne: grouped multimodal views, embedding-based exploration with CLIP UMAP, similarity search, and VLM captioning with FastVLM. #computervision #ai #artificialintelligence #machinevision #machinelearning #datascience #physicalai #mcp #agents

Why CLIP Stops Reading After the First Sentence | Find papers faster on arXivSub with AI summary (CVPR/ICCV/ICML/ICLR/NeurIPS/AAAI/MICCAI) medium.com/p/8e58e2b58621

Missed CVPR/ICRA? Join us for the 1st Embodied4Arts Workshop @ RSS 2026! Robotics is more than picking, placing, and chasing higher VLA success rates. We are looking for creative robotics work that explores how robots can paint, draw, perform, craft, fabricate, compose, collaborate, and participate in artistic practice. We welcome work on robot painting, embodied music, robotic craft, performance robotics, human-robot co-creation, creative manipulation, deformable materials, embodied generative systems, and anything that asks what robots can create, express, or make with us. Two tracks: • Workshop Papers & Demos • Robot Painting Challenge Submission deadline: June 24, 2026 Workshop date: July 13, 2026 Location: RSS 2026, Sydney, Australia Website: embodied4arts.github.io/ OpenReview: openreview.net/group?id=robo… If your robot does something creative, expressive, strange, beautiful, or materially interesting, we want to see it. #rss2026 #robotics #embodied

Join us on July 10 for day 3 of the “Best of CVPR” series. Register for the Zoom: hubs.ly/Q04nvSsZ0 Talks will include: * Advancing Generative Quality and Reasoning in Multimodal AI - Deepti Ghadiyaram at Boston University * HyperRealm: Hyperbolic Vision Language Models for Real-World Hierarchical Multimodal Understanding - Kathy Wu at Amazon * Cross-Modal Domain Adaptation using Semantic Parametric Mapping - Frank Bieder at FZI Forschungszentrum Informatik * WalkGPT: Pixel-Grounded Navigation Guidance for Pedestrians - Rafi Ibn Sultan at Wayne State University *********** Want to build better computer vision models? FiftyOne is an open source toolkit from Voxel51 (our Meetup sponsor) that helps you curate datasets, evaluate model performance, visualize embeddings, catch annotation errors, and eliminate duplicate images—all in one place. “pip install fiftyone” is all it takes to get started - hubs.ly/Q04nvH--0 #computervision #ai #artificialintelligence #machinevision #machinelearning #datascience #physicalai #mcp #agents

Join us on July 9 for day 2 of the “Best of CVPR” series. Register for the Zoom: hubs.ly/Q04nsTjg0 Talks will include: * Efficient Representation and Coding of Dynamic Light Fields - Joshitha Ravishanker at Indian Institute of Technology Madras * PHANTOM: Physics-Infused Video Generation via Joint Modeling of Visual and Latent Physical Dynamic - Ismini Lourentzou at University of Illinois Urbana-Champaign * LoST: Level of Semantics Tokenization for 3D Shapes - Niladri Dutt at UCL | Adobe * 3D Reconstruction Improves Weakly-Supervised Semantic Segmentation - Wolfgang Boettcher at Max Planck Institute for Informatics *********** Want to build better computer vision models? FiftyOne is an open source toolkit from Voxel51 (our Meetup sponsor) that helps you curate datasets, evaluate model performance, visualize embeddings, catch annotation errors, and eliminate duplicate images—all in one place. “pip install fiftyone” is all it takes to get started - hubs.ly/Q04nsWzt0 #computervision #ai #artificialintelligence #machinevision #machinelearning #datascience #physicalai #mcp #agents

Four months ago, when I applied to the #YC 2026 Summer School, I never imagined I'd be accepted. 🎉 The only thing that pushed me forward was a piece of wisdom I keep coming back to: "Do it first." One week later, the offer arrived. It's a genuine privilege to join a community of people who share the same passion for building, and to learn firsthand from some of the most influential voices in the AI era, including #JensenHuang, #SamAltman, #PatrickCollison, #JeffDean, and #AlexandrWang. Rewind to early 2026: I set out to design an AI workflow that could recommend and archive research papers every day. As researchers living through the rise of general AI, we're seeing publication volumes grow to 50x what they were just a few years ago. Top conferences like #CVPR and #NeurIPS have gone from thousands of submissions to more than 30,000. 📑 The bottleneck is no longer keeping up with the latest progress, it's filtering out the noise to surface the most insightful work. That's exactly what #Paperinder is built for. 💡 Over the past four months, #Paperinder has evolved into an agentic system with a purpose-built harness 🤖: a research-specific #Environment, paper-centric #Tools and #Skills, and an abstracted #Constitution that guides every foundation model, from open-source #Qwen to frontier models like #GPT and #Claude. We never really know how far an idea can go, and I think that's the heart of "Do it first." What began as a personal tool has grown into an agentic system for research work at large. That journey has led us to launch #LumeLab, our initiative focused on autonomous research. It stands on two legs. The first, #Paperinder, organizes information and helps structure thinking. The second, #Northstar (a name inspired by #FeifeiLi's philosophy on life), is just getting started, designed to take a core idea and then design, run, and analyze experiments in a continuous loop. I believe the autonomous research agent is already on its way. With gratitude and anticipation, I look forward to meeting and connecting with everyone at the venue this July! #AIAgents #Startups #YCombinator #Research #26SummerSchool

Join us on July 8 for day one of the “Best of CVPR” series Register for the Zoom: hubs.ly/Q04nsHlz0 Talks will include: * CylinderDepth: Cylindrical Spatial Attention for Multi-View Consistent Self-Supervised Surround Depth Estimation - Samer Abualhanud at Leibniz University Hannover * Your ViT is Secretly Also a Video Segmentation Model - Daan de Geus at Eindhoven University of Technology * LinkedOut: Linking World Knowledge Out of Video LLMs for Next-Generation Video Recommendation - Haichao Zhang at Northeastern University * Some Modalities Are More Equal Than Others: Understanding and Improving Multimodal Integration in MLLMs - Tianle Chen at Boston University *********** Want to build better computer vision models? FiftyOne is an open source toolkit from Voxel51 (our Meetup sponsor) that helps you curate datasets, evaluate model performance, visualize embeddings, catch annotation errors, and eliminate duplicate images—all in one place. “pip install fiftyone” is all it takes to get started - hubs.ly/Q04nsNlQ0 #computervision #ai #artificialintelligence #machinevision #machinelearning #datascience #physicalai #mcp #agents

Join us on July 8 for day one of the “Best of CVPR” series Register for the Zoom: hubs.ly/Q04nvr3k0 Talks will include: * CylinderDepth: Cylindrical Spatial Attention for Multi-View Consistent Self-Supervised Surround Depth Estimation - Samer Abualhanud at Leibniz University Hannover * Your ViT is Secretly Also a Video Segmentation Model - Daan de Geus at Eindhoven University of Technology * LinkedOut: Linking World Knowledge Out of Video LLMs for Next-Generation Video Recommendation - Haichao Zhang at Northeastern University * Some Modalities Are More Equal Than Others: Understanding and Improving Multimodal Integration in MLLMs - Tianle Chen at Boston University *********** Want to build better computer vision models? FiftyOne is an open source toolkit from Voxel51 (our Meetup sponsor) that helps you curate datasets, evaluate model performance, visualize embeddings, catch annotation errors, and eliminate duplicate images—all in one place. “pip install fiftyone” is all it takes to get started - hubs.ly/Q04nvvSZ0 #computervision #ai #artificialintelligence #machinevision #machinelearning #datascience #physicalai #mcp #agents

- Proceedings Deadline: July 7th, 2026 (23:59 CEST) - Non-Proceedings (Nectar) Deadline: Rolling Submission! Submit by July 10th to get notified by July 15th. Accepted papers at recent conferences (CVPR, ECCV, ICCV, NeurIPS, ICLR, ICML, etc.) can be submitted as is.

. @Tesla_AI is at CVPR this week. We have a few presentations at the workshops sharing our recent progress. We also have a booth in the exhibition hall where you can meet the Optimus robot, try our world model simulator, and sign up for FSD demo rides. We’re also hiring across FSD, Optimus, and Digital Optimus (computer use). Come meet the team, learn more about the roles, and explore what we’re building.