Maolin Gao

🚀 #CVPR2026 paper alert: 🦏 RINO: Rotation-Invariant Non-Rigid Correspondences Our network learns robust SO(3)-invariant features directly from raw 3D geometry. End-to-end, no pre-alignment or handcrafted descriptors! Joint work @tumcvg & @Stanford.

Excited to announce a new track of accelerating Generative AI: pi-Flow: Policy-Based Few-Step Generation via Imitation Distillation github.com/Lakonik/piFlow Distill 20B flow models now using just an L2 loss via imitation learning for SOTA diversity and teacher-aligned quality.

@tumcvg goes #ICCV2025 in Hawaii! 🛫🌋 We are very proud of our students who will present five papers (+ 1 workshop) during the conference! In particular, check out Back-on-track, which is an award candidate. (Congrats @wrchen530!)

🦖 We present “Feed-Forward SceneDINO for Unsupervised Semantic Scene Completion”. #ICCV2025 🌍: visinf.github.io/scenedino/ 📃: arxiv.org/abs/2507.06230 💻: github.com/tum-vision/sce… 🤗: huggingface.co/spaces/jev-ale… w/ A. Jevtić @felixwimbauer @olvr_hhn C. Rupprecht @stefanroth D. Cremers

🤖 What if a humanoid robot could make a hamburger from raw ingredients—all the way to your plate? 🔥 Excited to announce ViTacFormer: our new pipeline for next-level dexterous manipulation with active vision + high-resolution touch. 🎯 For the first time ever, we demonstrate ~2.5 minutes of continuous, autonomous control—combining active vision, high-res touch, and high-DoF robot hands SharpaWave — to complete complex, real-world tasks. Code is fully released; check out our: Homepage: roboverseorg.github.io/ViTacFormerPag… Paper link: arxiv.org/abs/2506.15953 Github: github.com/RoboVerseOrg/V…

Two more days until #ICCV2025 paper decisions are out🤞If you are working on 3D scene understanding with foundation models and want to present to a thriving community, consider submitting your work to the OpenSUN3D workshop @ICCVConference in Hawaii🌊🏄 ➡️openreview.net/group?id=thecv…

The recordings from our workshop on Open-World 3D Scene Understanding @CVPR are now available! See you @ICCVConference in Honolulu🏄‍♂️ for the next edition! ➡️ youtube.com/playlist?list=… 🌍 opensun3d.github.io

✨We introduce SuperDec, a new method which allows to create compact 3D scene representations via decomposition into superquadric primitives! Webpage: super-dec.github.io ArXiv: arxiv.org/abs/2504.00992 @BoyangSun @FrancisEngelman @mapo1 @cvg_ethz @ETH_AI_Center

@richard_yunqigu Congrats Richard! Very innovative work!

Which multimodal LLM should you be using to edit graphics in Blender? Today, we’re releasing our #CVPR2025 Highlight🌟 work, #BlenderGym 🏋️‍♀️, the first agentic 3D graphics editing benchmark that will tell you exactly how multimodal LLMs compare in their Blender-editing skills. What'd we find? 🧵👇

Excited to share our #CVPR2025 Highlight work, BlenderGym🏋️‍♂️, on benchmarking multimodal LLMs on graphics editing! Curious how inference compute allocation impacts performance, or how your favorite MLLM stacks up? Check out our paper and benchmark!👇

Excited to share our work: Gaussian Mixture Flow Matching Models (GMFlow) github.com/lakonik/gmflow GMFlow generalizes diffusion models by predicting Gaussian mixture denoising distributions, enabling precise few-step sampling and high-quality generation.

🏡Building realistic 3D scenes just got smarter! Introducing our #CVPR2025 work, 🔥FirePlace, a framework that enables Multimodal LLMs to automatically generate realistic and geometrically valid placements for objects into complex 3D scenes. How does it work?🧵👇

👉 We just added code for quickly visualizing interactions and functionality annotations in 3D scenes. Find it here: github.com/SceneFun3D/sce… Check out the full #SceneFun3D dataset here: scenefun3d.github.io Will also host a @CVPR challenge on this, stay tuned! 🚀

Applications due in less than a week!

Really excited to put together this @CVPR workshop on "4D Vision: Modeling the Dynamic World" -- one of the most fascinating areas in computer vision today! We've invited incredible researchers who are leading fantastic work at various related fields. 4dvisionworkshop.github.io

Thrilled to see our work accepted to @iclr_conf !! If you're curious about incorporating deformation priors into dynamic reconstruction models, be sure to check out our paper: research.nvidia.com/labs/toronto-a… A fantastic paper for @sara_oblak to kick off her academic publishing journey!

🚀 Excited to announce that our work on enhancing the 3D awareness of Vision Transformers (ViT) is accepted to #ICLR2025! We evaluate ViT models' 3D equivariance and introduce a simple finetuning strategy using 3D correspondences, achieving remarkable improvements in pose estimation, tracking, and semantic transfer even with minimal finetuning. 🔗 Arxiv paper: arxiv.org/abs/2411.19458 💻 Code is now available on github.com/qq456cvb/3DCor…, check it out! 🤗 Try out the demo on Hugging Face: huggingface.co/spaces/qq456cv… 🙏 Grateful to my amazing co-authors Yixin Li, Congyue Deng (@CongyueD), Yue Wang (@yuewang314), Leonidas Guibas for the contributions! #ICLR2025 #3Dvision

Get ready for the next @CVPR workshop on OpenWorld 3D Scene Understanding ➡️ opensun3d.github.io We will be hosting: - prized challenge 🏆 (see scenefun3d.github.io) - paper track 🗞️ - exciting keynote speakers  👩‍🏫 #CVPR2025

NeurIPS acknowledges that the cultural generalization made by the keynote speaker today reinforces implicit biases by making generalisations about Chinese scholars. This is not what NeurIPS stands for. NeurIPS is dedicated to being a safe space for all of us. We want to address the comment made during the invited talk this afternoon, as it is something that NeurIPS does not condone and it doesn't align with our code of conduct. We are addressing this issue with the speaker directly. NeurIPS is dedicated to being a diverse and inclusive place where everyone is treated equally.

Mitigating racial bias from LLMs is a lot easier than removing it from humans! Can’t believe this happened at the best AI conference @NeurIPSConf We have ethical reviews for authors, but missed it for invited speakers? 😡