Log inSign up
Amir Bar
AMI Labs
728 posts
user avatar
Amir Bar
AMI Labs
@_amirbar
Assistant Professor @imperialcollege MTS @amilabs
London
amirbar.net
Joined March 2016
1,428
Following
3,985
Followers
  • user avatar
    Amir Bar
    AMI Labs
    @_amirbar
    Jun 11, 2019
    (1/2) New CVPR paper on speech-to-gesture prediction! Human speech is often accompanied by hand and arm gestures. Given audio speech input, we generate plausible gestures to go along with the sound and synthesize a corresponding video of the speaker.
    Image
    00:00
  • user avatar
    Amir Bar
    AMI Labs
    @_amirbar
    Sep 2, 2022
    📢 New paper alert! How does one adapt a pre-trained visual model to novel downstream tasks without task-specific finetuning or any model modification? Inspired by #prompting in NLP, our new paper investigates Visual Prompting. (1/5)
    Image
  • user avatar
    Amir Bar
    AMI Labs
    @_amirbar
    Oct 23, 2024
    model = torch.compile(model) is magic. With only one line of code, I get ~40% speed up per training iteration.
    88K
  • user avatar
    Amir Bar
    AMI Labs
    @_amirbar
    Apr 29, 2024
    Animals are intelligent agents that plan and act to accomplish complex goals. Can we try learning from them? We present EgoPet, a new ego centric video dataset of animals scraped from YouTube and TikTok.
    Image
    00:00
    182K
  • user avatar
    Amir Bar
    AMI Labs
    @_amirbar
    Apr 2, 2025
    CLIP is arguably the leading pretraining paradigm in computer vision. In a new preprint, we show that vision-only SSL models trained on web data can match CLIP on VQA tasks, despite not using language. Paper: arxiv.org/abs/2504.01017 Project Page: davidfan.io/webssl/
    Image
    19K
  • user avatar
    Amir Bar
    AMI Labs
    @_amirbar
    Jul 29, 2024
    Life update: Wrapping up my PhD and graduating in two weeks from @TelAvivUni and @berkeley_ai! Next up: moving to NYC to start a postdoc at @AIatMeta, where i will be working with @ylecun. 🚀 Also, looking to meet some new and old friends in NYC area, DM me :)
    37K
  • user avatar
    Amir Bar
    AMI Labs
    @_amirbar
    Jun 13, 2025
    Navigation World Models won the Best Paper Honorable Mention Award at #CVPR2025 ☺️ It is my first postdoc paper since joining Yann's lab at @AIatMeta, so I am very excited. It was also extremely fun working with @GaoyueZhou, @dans_t123, @trevordarrell (and @ylecun) Fun story:
    user avatar
    #CVPR2026
    @CVPR
    Jun 13, 2025
    Congratulations to the #CVPR2025 Honorable Mentions for Best Paper! @GoogleDeepMind, @UCBerkeley, @UMich, @AIatMeta, @nyuniversity, @berkeley_ai, #AllenInstituteforAI, @UW, #UniversityCollegeLondon, @UniversityLeeds, @ZJU_China, @NTUsg, @PKU1898, @Huawei Singapore Research Center
    Image
    Image
    75K
  • user avatar
    Amir Bar
    AMI Labs
    @_amirbar
    Dec 5, 2024
    Happy to share our new work on Navigation World Models! 🔥🔥 Navigation is a fundamental skill of agents with visual-motor capabilities. We train a single World Model across multiple environments and diverse agent data. w/ @GaoyueZhou, Danny Tran, @trevordarrell and @ylecun.
    Image
    00:00
    84K
  • user avatar
    Amir Bar
    AMI Labs
    @_amirbar
    Aug 9, 2025
    a recipe to reproduce #Genie3: 1️⃣ collect a large egocentric video dataset and apply VGGT to get camera poses. Add more data from 3D reconstructed scenes. 2️⃣ train a Navigation World Model with long context → amirbar.net/nwm 3️⃣ distill to an efficient model for RT.
    27K
  • user avatar
    Amir Bar
    AMI Labs
    @_amirbar
    Oct 25, 2025
    also- it is a distraction. long horizon planning in pixel space doesn’t make sense.
    user avatar
    C. Zhang
    @ChongZzZhang
    Oct 25, 2025
    On world model / egocentric visual dynamics model, also on building robotic simulation, also on building robotic genAI models: Being visually realistic doesn't mean being physically accurate and semantically correct.
    43K
  • user avatar
    Amir Bar
    AMI Labs
    @_amirbar
    Jul 20, 2024
    #ICML2024 Flying to Vienna to present our paper "Stochastic Positional Embeddings Improve Masked Image Modeling" in @icmlconf. Masked Image Modeling is a popular SSL objective but scaling MIM might suffer due to appearance and location uncertainties. (1/n)
    Image
    54K
  • user avatar
    Amir Bar
    AMI Labs
    @_amirbar
    Apr 2, 2025
    FAIR is probably the only lab outside of academia where research projects can start like this.
    user avatar
    David Fan
    AMI Labs
    @DavidJFan
    Apr 2, 2025
    Replying to @DavidJFan
    [7/8] This side project started in October when @TongPetersb, @_amirbar, and I were thinking about the rise of CLIP as a popular vision encoder for MLLMs. The community often assumes that language supervision is the primary reason for CLIP's strong performance. However, we
    16K
  • user avatar
    Amir Bar
    AMI Labs
    @_amirbar
    Apr 10, 2025
    Excited to share that our paper on Navigation World Models was selected for an Oral presentation at CVPR! Code & models: github.com/facebookresear… huggingface.co/facebook/nwm
    user avatar
    Amir Bar
    AMI Labs
    @_amirbar
    Dec 5, 2024
    Happy to share our new work on Navigation World Models! 🔥🔥 Navigation is a fundamental skill of agents with visual-motor capabilities. We train a single World Model across multiple environments and diverse agent data. w/ @GaoyueZhou, Danny Tran, @trevordarrell and @ylecun.
    Image
    00:00
    Image
    GitHub - facebookresearch/nwm: Official code for the CVPR 2025 paper "Navigation World Models".
    From github.com
    8.3K
  • user avatar
    Amir Bar
    AMI Labs
    @_amirbar
    Oct 19, 2025
    heading to #ICCV2025, anyone up for a ☕️? also, my team at FAIR has an internship opening on world modeling, planning, and their robotics applications. DM me if you’re interested.
    13K

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