[1/7] Video diffusion has come a long way, generating more & more realistic videos. Can we revisit sparse-view novel view synthesis through these video priors? Meet FrameCrafter: a permutation-invariant multi-view model built on video diffusion 🧵 🌐 frame-crafter.github.io

Since Skill from Video (2018) and Videomimic (2025) the unspoken challenge has been finding the right videos to teach robots at scale. Zihan's work changes that with v2v, turning a few good demos into many counterfactual videos. Another step towards scalable real2sim2real!

Concept bottleneck models promise interpretable vision: predict named attributes first, classify from them. Where do the attributes come from? Usually an LLM prompted with the class name. No image is ever consulted. That turns out to be the weak link 🧵

🎉 "Ask Twice, Look Twice" was a Spotlight Oral at the eXCV Workshop, #ECCV2026! #eXCV The question before the image should help: it steers where the model looks, and we show it does. Yet it answers worse. Our fix: echo the question. 📄 arxiv.org/abs/2607.15565

World-action models typically imagine the future in RGB – but are pixels really the right representation for robotics? Our bet is no: RGB spends capacity on fine-grained details and variation that are often irrelevant for robot policies. DINO features, point tracks, and depth capture more useful features like semantics, motion, and geometry. But no single modality captures everything — how can we effectively combine them? We introduce ✨ModAR✨, which predicts the future one modality at a time, with each prediction informing the next. We train from scratch and find that this formulation performs best. Our 30.1M scratch-trained model even outperforms a 6B video-model-initialized model finetuned on the same data! 🧵 [1/8]

[1/N] Introducing Point4D: dense 4D reconstruction across hundreds of frames from a monocular video. Unlike existing feed-forward 4D methods that operate over short windows, Point4D keeps tracking in 3D, even across occlusions and out-of-frame motion.

The @CVPR 2027 Call for Papers is live! Key deadlines (2026, AoE): - Paper registration: Nov 10 - Paper submission: Nov 16 We look forward to seeing your best work! cvpr.thecvf.com/Conferences/… As agentic AI for research advances, we're working with OpenReview and others to develop guidance for thoughtful use of LLMs/AI to support authors and improve peer review. We'll share detailed policies on permitted uses and responsibilities as they are finalized. Stay tuned!

I very was happy to contribute to this white paper on Visual General Intelligence, which has interesting and different perspectives on learning, representation, and the hard challenges in computer vision over the coming years.

[1/6] Can one model fix rendering artifacts from any 3D representation? And what does it even mean to "fix" a rendering? At #ECCV2026, we present FixAnything (fix-anything.github.io): a single generalist video model that refines 3DGS/mesh/sparse point-cloud renderings into photorealistic, 3D-consistent videos.

Before AI can generate professional videos, it needs to see like a professional. We spent a year with 100+ content creators teaching AI to describe video like a filmmaker would. Introducing CHAI: Critique-based Human-AI Oversight for Building a Precise Video Language [CVPR'26 Highlight, Top 3%]. Try prompting a video generator for a dolly zoom, dutch angle, point of view, or camera roll. Most fall back to the same bland defaults: a push-in, a level shot, a third-person view. Why? These techniques require a language of cinema that current models rarely speak. We built that language: 1️⃣ Precise specification: 5-aspect structured captions co-designed with professional cinematographers covering subject, scene, motion, spatial, and camera dynamics 2️⃣ Scalable oversight: LLMs draft captions, humans critique what's wrong and how to fix it 3️⃣ Post-training recipes: Qwen3-VL-8B surpasses Gemini-3.1 and GPT-5 4️⃣ Video generation: fine-tuned Wan follows 400-word cinematic prompts with precise control Here's how each works 🧵 Work led by CMU and Harvard with @chancharikm, @du_yilun, and @RamananDeva. 📄 Paper: huggingface.co/papers/2604.2… 🌐 Site: linzhiqiu.github.io/papers/c…

Dexterous physical work in unpredictable environments is resistant to AI automation but time-intensive to teach. This team is building an AI system that acts as a virtual craft master, generating customized instructional content and providing real-time guidance through complex physical tasks on demand. ARISTOS: Reskilling for a Physical Workforce @CarnegieMellon @RamananDeva @ChangliuL Raj Reddy Katia Sycara @junyanz89 laude.org/moonshots/one/aris…

Pretrained ViTs like DINOv2 or CLIP are great, but they produce fixed, generic representations that encode the most salient visual concepts (e.g., "cat"). In human vision, prior priming with language changes how people parse an image. We believe visual encoders should do the same 🚨 Introducing Steerable Visual Representations, a new family of visual features you can steer with text towards specific visual concepts.

CRISP is accepted at ICLR 2026!!! @iclr_conf Excited to see more impact of building simulation-ready assets from monocular video on animation / robotics code is ready (github.com/Z1hanW/CRISP-Real…) with the cleaned-up videos, including several parkour videos clipped from YouTube.

MapAnything V1.1 Release is live! 🚨 ✅ Improved Checkpoints ✅ Model factory to test & train many models ✅ Profiling ✅ New COLMAP demos & voxelization tooling ✅ WAI format Benchmarking Data Time to update the CVPR subs 😉 Comparisons to DA3 (1.1), Pi3X & more info in 🧵👇

#ICCV2025 best paper award & best paper honorable mention! RI researchers collaborated with @CSDatCMU and @CMU_ECE to bring some incredible work to the conference this year👏🧠🔥 Check out the SCS news post on BrickGPT, which brought home best paper! bit.ly/4hqz7lc

🎉Despite massive pretraining, VLAs need to adapt to specific physical contexts. We introduce Robotic Steering, a novel finetuning method using mechanistic interpretability to surpass standard FT: 🎁 22× fewer parameters 🎁 +53% on unseen tasks 🎁 Interpretable Thread below👇

Introducing Any4D, a unified transformer for fully feed-forward, dense, metric-scale 4D reconstruction from flexible inputs! Any4D regresses per-pixel motion + geometry across frames in one pass — 15× faster, 2–3× more accurate reconstructions ⚡📈 Details + code below 👇 Exciting collab with @Nik__V__ @YuchenZhan54250 Tanisha Gupta @akashshrm02 @smash0190 @RamananDeva

Introduce CRISP, a real-to-sim pipeline that recovers human motion and simulatable scene geometry from monocular video! CRISP builds contact-faithful 3D scene for simulation - 8× fewer sim failures, +43% faster sim, and improves human motion! Interactive demos👉: crisp-real2sim.github.io/CRI… Exciting collaboration w/ @JiashunWang @jefftan969 @_Tsukasane @ Jessica Hodgins @shubhtuls @RamananDeva

If you miss the talk or want to dive deeper, please also check out our poster and our interview! Poster Session Details: - Location: Exhibit Hall I #306 - Time: Wed 22 Oct 2:45 p.m. HST — 4:45 p.m Read the interview in ICCV Daily: rsipvision.com/ICCV2025-Wedn…

🏆 Excited to share that BrickGPT (avalovelace1.github.io/Brick…) received the ICCV Best Paper Award! Our first author, @AvaLovelace0, will present it from 1:30 to 1:45 p.m. today in Exhibit Hall III. Huge thanks to all the co-authors @RuixuanLiu_ @RamananDeva @ChangliuL @junyanz89