Log inSign up
Songyou Peng
476 posts
Image
user avatar
Songyou Peng
@songyoupeng
Teaching multimodality to Gemini, Nano Banana, and more @GoogleDeepMind. PhD from @ETH and @MPI_IS.
San Francisco
pengsongyou.github.io
Joined January 2019
797
Following
8,655
Followers
  • Pinned
    user avatar
    Songyou Peng
    @songyoupeng
    Apr 23
    Yay, finally! Introducing Vision Banana🍌 from @GoogleDeepMind, our unified model that outperforms SoTA specialist models on various vision tasks! By treating 2D/3D vision tasks as image generation, we unlock a new foundation for CV. Project page: vision-banana.github.io (1/5)
    Image
    00:00
    284K
  • user avatar
    Songyou Peng
    @songyoupeng
    May 24, 2024
    Career Update: I’m happy to share that I’m starting a new position as Research Scientist at @GoogleDeepMind in San Francisco, USA! 🌉🥳🚀 I'm super excited to embark on this new adventure and eager to connect with people in the Bay Area! Reach out if you wanna have a chat :)
    Image
    38K
  • user avatar
    Songyou Peng
    @songyoupeng
    Nov 4, 2025
    Our bigger group at Google DeepMind is hiring interns for next summer! If you are interested in working with us, apply through the link below and also email us. step 1: google.com/about/careers/… (US-based) step 2: send an email to [email protected]
    user avatar
    Jon Barron
    @jon_barron
    Nov 4, 2025
    Our intern applications are open, instructions are below.
    Image
    google.com
    Student Researcher, PhD, Winter/Summer 2026
    The Student Researcher Program fosters academic collaborations by hiring students onto research projects aligned to company priorities in scientific advancement. The program offers placements on...
    92K
  • user avatar
    Songyou Peng
    @songyoupeng
    Jun 16, 2023
    📢Can we leverage LLM for a wide range of novel 3D scene understanding tasks without labeled 3D data? Yup, check our OpenScene at #CVPR2023!🚀 pengsongyou.github.io/openscene Internship work at Google Research @GoogleAI w/ Kyle Genova @maxjiang93 @taiyasaki @mapo1 & Tom Funkhouser 1/8
    Image
    00:00
    60K
  • user avatar
    Songyou Peng
    @songyoupeng
    Apr 21, 2022
    🚨 Are neural implicit representations applicable for larger-scale SLAM? Check out our NICE-SLAM👍! #CVPR2022 NICE website: pengsongyou.github.io/nice-slam NICE code: github.com/cvg/nice-slam NICE collaborations w/ Zihan Zhu (undergrad) @visionviktor @Martin_R_Oswald @mapo1 et al. 1/6
    Image
    00:00
  • user avatar
    Songyou Peng
    @songyoupeng
    Dec 2, 2021
    🚨 Check out our @NeurIPSConf Oral paper: Shape As Points (SAP)! We represent watertight meshes of any topology as a lightweight point cloud at speed. The key idea is to bridge them with a super simple, fast, versatile, and differentiable Poisson solver. pengsongyou.github.io/sap
    Image
    00:00
  • user avatar
    Songyou Peng
    @songyoupeng
    May 6, 2025
    Gemini 2.5 Pro has changed my day-to-day life at work for the past months, including helping me together improve the next generation of Gemini.
    user avatar
    Google DeepMind
    @GoogleDeepMind
    Mar 25, 2025
    Think you know Gemini? 🤔 Think again. Meet Gemini 2.5: our most intelligent model 💡 The first release is Pro Experimental, which is state-of-the-art across many benchmarks - meaning it can handle complex problems and give more accurate responses. Try it now →
    Image
    00:00
    17K
  • user avatar
    Songyou Peng
    @songyoupeng
    Oct 1, 2024
    Honored to receive the ECVA PhD Award at #ECCV24! This incredible PhD journey wouldn't have been possible without the tremendous support of two of my wonderful supervisors @mapo1 and @AutoVisionGroup! My deepest gratitude to you both❤️
    user avatar
    European Conference on Computer Vision #ECCV2026
    @eccvconf
    Oct 1, 2024
    Replying to @eccvconf
    Image
    Image
    Image
    Image
    27K
  • user avatar
    Songyou Peng
    @songyoupeng
    Nov 23, 2023
    🎓 This journey has been incredible! HUGE THANK YOU to my supervisors @mapo1 & @AutoVisionGroup, and all friends, colleagues, and mentors who've been part of this adventure ❤️ Special thanks also go to my committees @vincesitzmann and Leo Guibas!
    This Post is from an account that no longer exists. Learn more
    20K
  • user avatar
    Songyou Peng
    @songyoupeng
    Oct 8, 2025
    📣 Announcing MUSI: 1st Multimodal Spatial Intelligence Workshop @ICCVConference! 🎙️All-star keynotes: @sainingxie, @ManlingLi_, @RanjayKrishna, @yuewang314, and @QianqianWang5 - plus a panel on the future of the field! 🗓 Oct 20, 1pm-5:30pm HST 🔗 musi-workshop.github.io
    Image
    67K
  • user avatar
    Songyou Peng
    @songyoupeng
    Mar 20, 2024
    🥳🥳Congrats to all the co-authors @visionviktor @Martin_R_Oswald @ZhaopengCui @AutoVisionGroup @mapo1 ! HUGE kudos to Zihan, who started working on this project during his bachelor's degree, and did such a wonderful job!
    user avatar
    International Conference on 3D Vision (3DV)
    @3DVconf
    Mar 19, 2024
    Replying to @3DVconf
    Image
    12K
  • user avatar
    Songyou Peng
    @songyoupeng
    Jun 21, 2024
    "The straight line belongs to men, the curved one to God." — Antoni Gaudí We will present 3D Edge Reconstruction from UDF at #CVPR2024 today at 10:30, Poster 162! Amazing works done by Lei Li (great master thesis!), Zehao, @B1ueber2y, Remi & @mapo1! neural-edge-map.github.io
    Image
    00:00
    11K
  • user avatar
    Songyou Peng
    @songyoupeng
    Nov 26, 2024
    Our bigger group at Google DeepMind is hiring interns for next summer. If you are interested in working with us, apply through the link below and also email us. google.com/about/careers/… (US-based) email: [email protected]
    user avatar
    Jon Barron
    @jon_barron
    Nov 25, 2024
    Our group at Google DeepMind is now accepting intern applications for summer 2025. Attached is the official "call for interns" email; the links and email aliases that got lost in the screenshot are below.
    Image
    23K
  • user avatar
    Songyou Peng
    @songyoupeng
    Aug 17, 2020
    📢 New paper: "Convolutional Occupancy Networks" with @Mi_Niemeyer @LMescheder @mapo1 and A. Geiger, #ECCV2020 spotlight 😄 Project page: pengsongyou.github.io/conv_onet Paper: arxiv.org/abs/2003.04618 A flexible neural implicit representation for large-scale 3D reconstruction. 👇👇
    Image
    00:00

New to X?

Sign up now to get your own personalized timeline!

Create account

By signing up, you agree to the Terms of Service and Privacy Policy, including Cookie Use.

Terms·Privacy·Cookies·Accessibility·Ads Info·© 2026 X Corp.
Don't miss what's happening
People on X are the first to know.
Log inSign up
Advertisement
Advertisement