Log inSign up
user avatar
Arash Vahdat
@ArashVahdat
Research Director, leading fundamental generative AI research (GenAIR) @nvidia research, volunteer at California Search & Rescue, views are my own.
San Francisco Bay Area
research.nvidia.com/labs/genair
Joined January 2010
910
Following
11.2K
Followers
  • Pinned
    user avatar
    Arash Vahdat
    @ArashVahdat
    Mar 18
    🚨 We’re Hiring in Generative AI for Biomolecular Design! 🧬🤖 We’re looking for Research Scientists working on biomolecular design, including small molecules, proteins, RNA, and molecular dynamics. Join us to help shape the next generation of AI-driven discovery, expanding our
    00:00
    52K
  • user avatar
    Arash Vahdat
    @ArashVahdat
    Feb 3, 2021
    I can't believe after this many years of programming with NumPy/PyTorch/TensorFlow, I didn't know about 𝚎𝚒𝚗𝚜𝚞𝚖. You can get rid of so many lines of reshape, transpose, sum, product & expand_dim with a single einsum which is even easier to understand: stackoverflow.com/questions/2608…
  • user avatar
    Arash Vahdat
    @ArashVahdat
    Jul 9, 2020
    📢📢📢 Introducing NVAE 📢📢📢 We show that deep hierarchical VAEs w/ carefully designed network architecture, generate high-quality images & achieve SOTA likelihood, even when trained w/ original VAE loss. paper: arxiv.org/abs/2007.03898 with @jankautz at @NVIDIAAI (1/n)
  • user avatar
    Arash Vahdat
    @ArashVahdat
    Oct 10, 2023
    Our #CVPR2023 tutorial on diffusion models is now available publicly (with much better audio quality 🤣) Website: …3-tutorial-diffusion-models.github.io With: @chenlin_meng and @baaadas @CVPR
    Denoising Diffusion-based Generative Modeling: Foundations and Applications
    From cvpr2023-tutorial-diffusion-models.github.io
    63K
  • user avatar
    Arash Vahdat
    @ArashVahdat
    Oct 6, 2020
    It breaks my 💚 when researchers tell me that VAEs don't work. My first typical question is "did you try hierarchial VAE or vanilla VAE?", the answer is usually vanilla VAE. VAEs work much better with hierarchical structures. NVAEs and this work take this to the extreme!
    user avatar
    hardmaru
    @hardmaru
    Oct 6, 2020
    Very Deep VAEs Generalize Autoregressive Models and Can Outperform Them on Images “Very Deep VAEs” achieve higher likelihoods, use fewer parameters, generate samples 1000x faster, and are more easily applied to hi-res images, compared to PixelCNN. openreview.net/forum?id=RLRXC…
  • user avatar
    Arash Vahdat
    @ArashVahdat
    Jan 19, 2024
    📢🔥 My team at NVIDIA Research is looking for full-time research scientists & summer interns. Topics of interest are: 1⃣Gen AI for science (climate, biology, chemistry) 2⃣Image/Video/3D (generate, edit, manipulate) 3⃣Fundamental generative learning Apply via links below
    85K
  • user avatar
    Arash Vahdat
    @ArashVahdat
    Jul 27, 2022
    📢📢 The recording of our tutorial on denoising diffusion models is now available on YouTube: youtube.com/watch?v=cS6JQp… Slides and additional info: …2-tutorial-diffusion-models.github.io This tutorial was originally presented by @RuiqiGao, @karsten_kreis, and myself at #CVPR2022.
  • user avatar
    Arash Vahdat
    @ArashVahdat
    Feb 16, 2022
    🎉 Our tutorial proposal on 𝗗𝗲𝗻𝗼𝗶𝘀𝗶𝗻𝗴 𝗗𝗶𝗳𝗳𝘂𝘀𝗶𝗼𝗻-𝗯𝗮𝘀𝗲𝗱 𝗚𝗲𝗻𝗲𝗿𝗮𝘁𝗶𝘃𝗲 𝗠𝗼𝗱𝗲𝗹𝗶𝗻𝗴 has been accepted to #CVPR2022. Stay tuned for some cool lectures from @karsten_kreis, @RuiqiGao and me at @CVPR 2022.
  • user avatar
    Arash Vahdat
    @ArashVahdat
    Dec 4, 2018
    This is me while explaining relaxed Boltzmann machines and not knowing that the pioneer who introduced them to the field is just behind me :( #NeurIPS2018
    user avatar
    William Falcon ⚡️
    @williamfalcon
    Dec 4, 2018
    When you explain your poster and don’t notice Geoffrey Hinton standing behind you #NeurIPS2018
  • user avatar
    Arash Vahdat
    @ArashVahdat
    Oct 30, 2023
    📢 Would you like to build latent diffusion models for new problem domains? Wondering about theoretical and practical considerations! @RuiqiGao, @karsten_kreis and I will present the #NeurIPS2023 tutorial on "Latent Diffusion Models" on Monday, Dec 11. neurips2023-ldm-tutorial.github.io
    36K
  • user avatar
    Arash Vahdat
    @ArashVahdat
    Oct 12, 2023
    📢🔥 My team at NVIDIA research is looking for candidates with a fundamental generative learning background (ideally) in one of these domains: - Gen AI for science (climate, chemistry, biology) - Gen AI for 3D data Apply via: bit.ly/3P9yxMC bit.ly/43ZgpZW
    83K
  • user avatar
    Arash Vahdat
    @ArashVahdat
    Nov 29, 2023
    📢🔥My team at NVIDIA Research is looking for Summer 2024 interns. Topics of interest are: 1⃣ Fundamental generative learning (diffusion, etc) 2⃣Gen AI for science (climate, biology, chemistry) 3⃣Image/Video/3D (generate, edit, manipulate) Apply via nvidia.wd5.myworkdayjobs.com/en-US/NVIDIAEx…
    64K
  • user avatar
    Arash Vahdat
    @ArashVahdat
    Sep 3, 2020
    📢 NVAE source code is released! NVAE is deep hierarchical VAE w/ specially designed network architecture that can generate high-quality images & achieve SOTA log-likelihood. Happy coding! paper: arxiv.org/abs/2007.03898 code: github.com/NVlabs/NVAE w/ @jankautz at @NVIDIAAI
  • user avatar
    Arash Vahdat
    @ArashVahdat
    Jul 17, 2023
    📢 I am looking for Fall interns to join the fundamental gen AI research team at NVResearch. Topics of interest are: -Fundamental Gen AI research -3D generation -Text-based manipulation Remote/in-person, full/part-time options are available. Apply at bit.ly/3DijaKw
    70K