🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

Excited to introduce SketchAgent!👩‍🎨 We leverage the prior of pretrained multimodal LLMs for language-driven, sequential sketch generation and human-agent collaborative sketching! ✨ Try our fun interface here: github.com/yael-vinker/Sk…

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/ Gaoyue Zhou, Danny Tran, trevordarrell and Yann LeCun.

Come by our poster #1302 Thursday morning at #NeurIPS2024 to chat!

i'm in vancouver for #NeurIPS2024 presenting our 3D shape inference benchmark tomorrow! stop by poster #1210 at 4:30 on friday if you're interested and if you'd like to talk about neuro-ai, human cognition, or suggest nearby hikes, feel free to reach out!

I'll be presenting "Images that Sound" today at #NeurIPS2024! East Exhibit Hall A-C #2710. Come say hi to me and Andrew Owens :) (Ziyang Chen sadly could not make it, but will be there in spirit :') )

Mitigating racial bias from LLMs is a lot easier than removing it from humans! Can’t believe this happened at the best AI conference NeurIPS Conference We have ethical reviews for authors, but missed it for invited speakers? 😡

unfortunately kansas has snapped out of its identity crisis as a subtropical region and has stopped selling pomegranates en masse this year. RIP to my post-NeurIPS pomegranate binges (2020-2023) gone but not forgotten

Personal vision tasks–like detecting *your mug*-are hard; they’re data scarce and fine-grained. In our new paper, we show you can adapt general-purpose vision models to these tasks from just three photos! 📝: arxiv.org/abs/2412.16156 💻: github.com/ssundaram21/pe… (1/n)

Very excited to share ASAL! Artificial Life aims to recreate natural evolution, but is severely bottlenecked by hand-designed simulations. We propose using CLIP to automatically discover the interesting ALife simulations!

if you could press a button that cures your child’s brain tumor in exchange for ending your life immediately, every parent would hesitate for zero seconds before fighting to be the first to press it the cruelest thing is that no such button exists. but there is always a move 👇

Do LLMs understand probability distributions? Can they serve as effective simulators of probability? No! However, in our latest paper that via in-context learning, LLMs update their broken priors in a manner akin to Bayseian updating. 📝 arxiv.org/abs/2503.04722

🚨Large video-language models LLaVA-Video can do single-video tasks. But can they compare videos? Imagine you’re learning a sports skill like kicking: can an AI tell how your kick differs from an expert video? 🚀 Introducing "Video Action Differencing" (VidDiff), ICLR 2025 🧵

Next-gen vision pre-trained models shouldn’t be short-sighted. Humans can easily perceive 10K x 10K resolution. But today’s top vision models—like SigLIP and DINOv2—are still pre-trained at merely hundreds by hundreds of pixels, bottlenecking their real-world usage. Today, we

Thrilled to share the first-ever search leaderboard with lmarena.ai! It's so fun to see how models behave differently — OpenAI loves news (but not YT), Perplexity favors YouTube, and Gemini (Google DeepMind) leans on blogs/forums. More insights: blog.lmarena.ai/blog/2025/sear…

Ever wondered if the way we feed image patches to vision models is the best way? The standard row-by-row scan isn't always optimal! Modern long-sequence transformers can be surprisingly sensitive to patch order. We developed REOrder to find better, task-specific patch sequences.

🚀 Call for Papers! 🚀 Excited to help organize the 4th Workshop on What is Next in Multimodal Foundation Models? at ICCV in Honolulu, Hawai'i 🌺 Submit work on vision, language, audio & more! 🗓️ Deadline: July 1, 2025 🔗 sites.google.com/view/mmfm4thwo… #MMFM4 #ICCV2025 #AI #multimodal

Artifacts in your attention maps? Forgot to train with registers? Use 𝙩𝙚𝙨𝙩-𝙩𝙞𝙢𝙚 𝙧𝙚𝙜𝙞𝙨𝙩𝙚𝙧𝙨! We find a sparse set of activations set artifact positions. We can shift them anywhere ("Shifted") — even outside the image into an untrained token. Clean maps, no retrain.

What would a World Model look like if we start from a real embodied agent acting in the real world? It has to have: 1) A real, physically grounded and complex action space—not just abstract control signals. 2) Diverse, real-life scenarios and activities. Or in short: It has to

Some problems can’t be rushed—they can only be done step by step, no matter how many people or processors you throw at them. We’ve scaled AI by making everything bigger and more parallel: Our models are parallel. Our scaling is parallel. Our GPUs are parallel. But what if the