How can we get VLMs to move their eyes—and reason step-by-step in visually grounded ways? 👀 We introduce ViGoRL, a RL method that anchors reasoning to image regions. 🎯 It outperforms vanilla GRPO and SFT across grounding, spatial tasks, and visual search (86.4% on V*). 👇🧵

This was a really fun and exciting workshop #CVPR2025! Huge thanks to all the speakers, organizers and reviewers #CVPR2026! We hope to be able to release the video recordings soon!

1/6 Retrieval is supposed to improve generation in RAG systems. But in practice, adding more documents can hurt performance, even when relevant ones are retrieved. We introduce RAGGED, a framework to measure and diagnose when retrieval helps and when it hurts.

Excited to share recent work with Kaihua Chen and Deva Ramanan where we learn to do novel view synthesis for dynamic scenes in a self-supervised manner, only from 2D videos! webpage: cog-nvs.github.io arxiv: arxiv.org/abs/2507.12646 code (soon): github.com/Kaihua-Chen/co…

Meet MapAnything – a transformer that directly regresses factored metric 3D scene geometry (from images, calibration, poses, or depth) in an end-to-end way. No pipelines, no extra stages. Just 3D geometry & cameras, straight from any type of input, delivering new state-of-the-art