Tejaswi Kasarla

Want to improve content safety and NSFW detection in CLIP? Hyperbolic geometry can make this possible. Check out our #CVPR2025 paper, Hyperbolic Safety-Aware Vision-Language Models. With: @TobiaP93332, @PascalMettes, @lorenzo_baraldi, @ricucch #ELLISforEurope #Ellis_Amsterdam

Excited to share that we're looking for a new colleague at @AMLab_UvA : Assistant Professor in AI for Science 🔬🤖 AMLab is a world-class ML research group embedded in Amsterdam's thriving AI ecosystem: leading research groups, an ELLIS unit, startups, and big tech — all within reach. And Dutch academic labor conditions are genuinely among the best in Europe ❤️ Deadline: May 30 👉 werkenbij.uva.nl/en/vacancies/a…

🌎 World understanding needs vision, language and reasoning. My keynote on “Seeing, Speaking, and Reasoning in a Visual World” at last month’s VISAPP and GRIVAPP Conferences is now available. 🤩 vimeo.com/1176655583

New survey in IJCV: "Looking Beyond the Obvious: A Survey on Abstract Concept Recognition for Video Understanding." Machines recognize objects, actions, and scenes well. But concepts like justice, intent, or togetherness remain an open challenge. doi.org/10.1007/s11263…

I am very happy to share the result of my internship at FAIR (Meta): V-JEPA 2.1: Unlocking Dense Features in Video Self-Supervised Learning with @ylecun @AdrienBardes Our approach learns dense, spatially coherent features from video while preserving strong global understanding

If you, as a CS Prof, are wondering whether you need PhD students at all now that you have wangled a subscription to Claude Code, your lab probably had a pretty depressing vibe to begin with--and 'em students are likely better off with you hanging out with Claude.. #AIAphorisms

I am happy to share that I have joined forces with @ylecun and fellow founders as Co-Founder and Chief Research & Innovation Officer at AMI - Advanced Machine Intelligence. I will lead research initiatives that push AI to be genuinely human-centered - AI that perceives, learns, reasons and acts like we do and in our best interest. I am thankful for the trust placed in us and deeply aware of the responsibility we share to making the world a better place through our work everyday. Join us!

How can agents learn in long, open-ended tasks where success is rare and rewards are sparse? 👀 🚨 Enter ∆Belief-RL: we show how to use agent’s own belief updates as a dense reward for turn-level credit assignment. the result? Surprisingly strong generalization. (1/8) 🧵⬇️

It's great to see the excitement these days about world models and their applications in robotics. World models predate deep learning, and if you're curious, here's my history talk starting from Craik (1943) & Kalman (1960) youtube.com/watch?v=9B4kka…

Attending Mila World Modeling Workshop (world-model-mila.github.io) to present 3 papers from our team: VL-JEPA, VLWM, and Action100M.

We release Action100M, the hero behind VL-JEPA. It is a large dataset with O(100 million) dense action annotations on HowTo100M procedural videos. We hope it serves as a robust data foundation to advance physical world modeling research.

My first PhD paper is out! 🎓 "What Drives Success in Physical Planning with Joint-Embedding Predictive World Models?" tl:dr: JEPA-WMs for robotics: learn dynamics on top of visual encoders, optimize actions towards goal 👇 w/ @JimmyTYYang1, Jean Ponce, @AdrienBardes, @ylecun

1/4 For the last several years I worked part-time at the FAIR lab at Meta, in addition to being a professor at UC Berkeley. That phase is now over, and starting Jan. 5, I will be leading a robotics research effort at Amazon FAR in San Francisco, while continuing at Berkeley.

VL-JEPA is out! A non-generative vision-language model, based on JEPA. Different from typical data-space autoregressive VLMs, VL-JEPA is trained to predict continuous embeddings in the latent space. (1/N)

Introducing VL-JEPA: Vision-Language Joint Embedding Predictive Architecture for streaming, live action recognition, retrieval, VQA, and classification tasks with better performance and higher efficiency than large VLMs. • VL-JEPA is the first non-generative model that can perform general-domain vision-language tasks in real-time, built on a joint embedding predictive architecture. • We demonstrate in controlled experiments that VL-JEPA, trained with latent space embedding prediction, outperforms VLMs that rely on data space token prediction. • We show that VL-JEPA delivers significant efficiency gains over VLMs for online video streaming applications, thanks to its non-autoregressive design and native support for selective decoding. • We highlight that our VL-JEPA model, with an unified model architecture, can effectively handle a wide range of classification, retrieval, and VQA tasks at the same time. by @Delong0_0 @MustafaShukor1 @TheoMoutakanni @willyhcchung Jade Lei Yu Tejaswi Kasarla @AllenBolourchi @ylecun @pascalefung arxiv.org/abs/2512.10942

I have funding for 2 new PhD students on hyperbolic deep learning. Interested in joining this exciting research direction? Check out the vacancy and consider applying! Link: werkenbij.uva.nl/en/vacancies/t…

I am very happy to share that I received the NWO VIDI grant for my research on hyperbolic computer vision. Many more hyperbolic papers on the horizon the next few years! ivi.uva.nl/content/news/2…

We trained the whole stack. 𝗣𝗿𝗲𝘁𝗿𝗮𝗶𝗻. 𝗦𝗙𝗧. 𝗥𝗟. 𝗢𝗽𝗲𝗻 𝘄𝗲𝗶𝗴𝗵𝘁𝘀. 𝗢𝗽𝗲𝗻 𝗺𝗲𝘁𝗵𝗼𝗱𝘀. 𝗢𝗽𝗲𝗻 𝘀𝗰𝗶𝗲𝗻𝗰𝗲. From tokens to traces. From guesses to grounded. 𝗖𝗼𝗱𝗲 𝗪𝗼𝗿𝗹𝗱 𝗠𝗼𝗱𝗲𝗹 is here 50+ pages Report. Ckpts. Code. ai.meta.com/research/publi…

Say hello to DINOv3 🦖🦖🦖 A major release that raises the bar of self-supervised vision foundation models. With stunning high-resolution dense features, it’s a game-changer for vision tasks! We scaled model size and training data, but here's what makes it special 👇

Audio General Intelligence (AGI) is no longer a dream — it’s arriving. Today, we’re releasing Audio Flamingo 3 — fully open source. A model that listens, understands, and reasons across sound and language like never before. Gradio demo: huggingface.co/spaces/nvidia/… #NVIDIAAI #Audio

Super happy to share that I have joined @AIatMeta as a Research Scientist Intern! I’m working with @pascalefung in FAIR Paris on training and evaluating multimodal world models. Already enjoying the collaborative atmosphere and the energy of Paris, excited for what’s to come!