Excited to share that our work “TIDE: Training Locally Interpretable Domain Generalization Models Enables Test-time Correction” has been accepted at #CVPR2025 🎉 Paper:

Discover how Adobe Researchers joined forces with the @AdobeExpress team to create On-brand Recolor—a new feature that uses AI and tailored algorithms to thoughtfully recolor graphics with your brand’s color palette in mind! https://t.co/8cl8S7qswH

Disappointed with your ICLR paper being rejected? Ten years ago today, Sergey and I finished training some of the first end-to-end neutral nets for robot control 🤖 We submitted the paper to RSS on January 23, 2015. It was rejected for being "incremental" and "unlikely to have

Today, I reached 100 citations on Google Scholar! It might seem a bit trivial to celebrate this, but looking at where I started just a couple years back, it really does feel like a meaningful milestone. https://t.co/LoWLpvvKSu

🚀 Just launched a new repo compiling key papers on Explainable CV! 🔍 I've added short summary for each paper, with a major focus on concept-based explanations—I'm expanding to include other directions too! Contributions are welcome! Check it out here:

Here's a link to a lecture on interpretability that I gave at @dawnsongtweets and @DanHendrycks UCB course last spring, which covers a some of the ways we're thinking about AI interpretability in our lab. https://t.co/nRoc0URzxg Thanks Dan and Dawn for the opportunity to talk!

Poster session from 6:15-8:15 pm tonight at the Exhibit Hall!

Unlock your new era of productivity 🔓 with the new AI Assistant (beta) in Adobe Acrobat. Now available on Acrobat desktop and web; coming soon to Reader. ✨ Learn more: https://t.co/L8Y09ynX52

To all the prospective PhDs in/from India, before you sign up for a PhD position in the US, please carefully consider if you would do better (PhDing) in India. I sketched my experience in this blog https://t.co/CmriQS2yGz. Feel free to send me your comments 😃

Introducing MATTE - a Multi-ATTributE Inversion algorithm to constrain image generation of pre-trained stable diffusion models on different attributes (e.g., color, style, layout, semantics) of user-provided reference images. arXiv: https://t.co/sQmdZCbXH8

Introducing EMILIE: Iterative Multi-granular Image Editing using Diffusion Models. paper Accepted at IEEE/CVF Winter Conference on Applications of Computer Vision (WACV). Work led by @josephkj_in @Prateksha_03 with @aisagarw @balajivasan #WACV2024 https://t.co/l3QhIevpQE

Discover @AdobeResearch’s new work in #ComputerVision at #ICCV2023 this week! In addition to technical papers, Adobe authors have also contributed to the conference in many other ways. Check out our contributions: https://t.co/QWBAoCAV0j

Excited to be at @ICCVConference to present two papers: 1) https://t.co/yVi4zFhao7 2) https://t.co/WQnJqOcD9n Also, we are looking for awesome Computer Vision interns to join us at #adoberesearch. Meet @KK_Ilkal, @aisagarw or myself for a chat. Merci!

Excited to share that I'll be attending #ICCV2023 in-person! See you at our poster on Wednesday (10:30 AM - 12:30 PM). Looking forward to meeting you all! @ICCVConference @AdobeResearch

Do check out the latest work on improved text-to-image diffusion model by @aisagarw and several other esteemed colleagues at @AdobeResearch India. #ICCV2023

Excited to share that our work “A-STAR: Test-time Attention Segregation and Retention for Text-to-image Synthesis” has been accepted at #ICCV2023 Paper: https://t.co/gPRv23RX9F

Happy to share that a part of my Dual Degree Project work “Semantics-Driven Generative Replay for Few-Shot Class Incremental Learning" (@BiplabB81293285 @fabio_cuzzolin) has been accepted @acmmm2022.

Feeling numb. Devastated. Yesterday was Saraswati Puja & today Ma took her blessed one with her. Somehow it feels that even the birds, trees & wind are silent today. Swar Kokila Bharat Ratna #LataMangeshkar ji your divine voice will echo till eternity. Rest in peace. Om Shanti.

[New paper 🚨] You’ve heard of catastrophic forgetting, but have you heard of *fortuitous* forgetting? In this paper, we show how forgetting can be a friend of learning in artificial neural nets. With @AnkitKVani, @hugo_larochelle, @AaronCourville (1/6) https://t.co/0bFsd3ndXU

Neural language models are really good at explaining held-out data. So when we sample from them, why do they yield dull and degenerate text? Our paper analyzes this behavior using information theory, and corrects for it with a new sampling principle: https://t.co/8DA6Q3DN8X