🔥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

What it would take to train a VLM to perform in-context learning (ICL) over egocentric videos? At #EMNLP2024 get the details on EILEV by Michigan SLED Lab's Peter Yu Peter Yu, Brian Zheyuan Zhang, @Hu_FY_, Shane Storks, PhD, Joyce Chai. 📰 arxiv.org/abs/2311.17041

How well can VLMs detect and explain humans' procedural mistakes, like in cooking or assembly? 🧑‍🍳🧑‍🔧 My new pre-print with Itamar Bar-Yossef, Yayuan Li, Brian Zheyuan Zhang, Jason Corso, and Joyce Chai (Michigan SLED Lab MichiganAI Computer Science and Engineering at Michigan) dives into this! arxiv.org/pdf/2412.11927

I've decided to take a final screenshot of this empty project page. This is the most exciting and ambitious project of my career, and it's been in the works for two years. You can probably guess what this tweet signifies! Building a 3D world simulator is central to my deep

Everything you love about generative models — now powered by real physics! Announcing the Genesis project — after a 24-month large-scale research collaboration involving over 20 research labs — a generative physics engine able to generate 4D dynamical worlds powered by a physics

Introducing ASAL: Automating the Search for Artificial Life with Foundation Models sakana.ai/asal/ Artificial Life (ALife) research holds key insights that can transform and accelerate progress in AI. By speeding up ALife discovery with AI, we accelerate our

The last paper of my PhD is finally out ! Introducing "Intuitive physics understanding emerges from self-supervised pretraining on natural videos" We show that without any prior, V-JEPA --a self-supervised video model-- develops an understanding of intuitive physics !

"What we want is a machine that can learn from experience." ---Alan Turing, 1947

Andrew G. Barto and Richard S. Sutton have been awarded the prestigious 2024 ACM A.M. #TuringAward for developing a branch of artificial intelligence known as reinforcement learning. University of Alberta Manning College of Information & Computer Sciences #ManningCICS #ArtificialIntelligence #UMass bit.ly/3F6Poww

New Anthropic research: Tracing the thoughts of a large language model. We built a "microscope" to inspect what happens inside AI models and use it to understand Claude’s (often complex and surprising) internal mechanisms.

Rich's slogans for AI research (revised 2006): 1. Approximate the solution, not the problem (no special cases) 2. Drive from the problem 3. Take the agent’s point of view 4. Don’t ask the agent to achieve what it can’t measure 5. Don't ask the agent to know what it can't verify

The real world is an embodied multi-agent system with natural language communication. What if we had a benchmark and platform to study those challenges? ⛏️Introducing MINDcraft and MineCollab, the 1st platform and benchmark for studying embodied multi-agent LLM collaboration!

Virtual Community An Open World for Humans, Robots, and Society

Can we scale 4D pretraining to learn general space-time representations that reconstruct an object from a few views at any time to any view at any other time? Introducing 4D-LRM: a Large Space-Time Reconstruction Model that ... 🔹 Predicts 4D Gaussian primitives directly from

📣 Excited to announce SpaVLE: #NeurIPS2025 Workshop on Space in Vision, Language, and Embodied AI! 👉 …vision-language-embodied-ai.github.io 🦾Co-organized with an incredible team → Freda Shi · Jiayuan Mao · Jiafei Duan · Manling Li · David Hsu · Parisa Kordjamshidi 🌌 Why Space & SpaVLE? We

You can install anycoder as a Progressive Web App on your device. Visit huggingface.co/spaces/akhaliq… and in the footer click settings then follow instructions and click the install button in the URL address bar of your browser

Thanks AK for sharing our work! MindJourney enables: 🧠 Flexible perspective taking, powered by a controllable world model 📐 Robust spatial reasoning via test-time scaling 🔌 Plug & play performance boost — no fine-tuning needed!

Test-time scaling nailed code & math—next stop: the real 3D world. 🌍 MindJourney pairs any VLM with a video-diffusion World Model, letting it explore an imagined scene before answering. One frame becomes a tour—and the tour leads to new SOTA in spatial reasoning. 🚀 🧵1/