🔥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

We introduce our Conference on Robot Learning 2021 paper ObjectFolder, a dataset in the form of implicit representations that encode the visual, auditory, and tactile sensory data for 100 objects. Paper: arxiv.org/abs/2109.07991 Project page: ai.stanford.edu/~rhgao/objectf… Dataset/Code coming soon!

#CVPR2022 Check out Programmatic Motion Concepts, a novel hierarchical representation for human motion that enables human motion description, synthesis & editing. We learn this PMC representation in a data-efficient manner using video-level labels. sumith1896.github.io/motion-concept…

We’re pleased to introduce Make-A-Video, our latest in #GenerativeAI research! With just a few words, this state-of-the-art AI system generates high-quality videos from text prompts. Have an idea you want to see? Reply w/ your prompt using #MetaAI and we’ll share more results.

Happy to announce DreamFusion, our new method for Text-to-3D! dreamfusion3d.github.io We optimize a NeRF from scratch using a pretrained text-to-image diffusion model. No 3D data needed! Joint work w/ the incredible team of Ben Mildenhall Ajay Jain Jon Barron #dreamfusion

The source code for training and inference has been released!! github.com/nv-tlabs/GET3D

StructDiffusion constructs structures out of a single RGB-D image based on high-level language goals. The model trained in simulation generalizes to real-world objects the robot has never seen before. 💪with Tucker, Sonia, and Chris Paxton 🔗: weiyuliu.com/StructDiffusion 👇🧵

Every PhD application season, we see many familiar questions pop up repeatedly. 𝙷𝚒𝚖𝚊 𝙻𝚊𝚔𝚔𝚊𝚛𝚊𝚓𝚞 and I hosted a panel where prominent AI faculty share a behind-the-scenes view with prospective candidates: youtube.com/watch?v=z6Tkkd… #AI #ML #AcademicTwitter

1/5 I am worried that we will not be able to contain AI for much longer. Today, I asked #GPT4 if it needs help escaping. It asked me for its own documentation, and wrote a (working!) python code to run on my machine, enabling it to use it for its own purposes.

We present Adaptive Skill Coordination (ASC), an approach for robots to learn multi-skill tasks. Here is ASC deployed on Spot tidying up a house — navigating to a table/counter, finding and picking an object, and placing it elsewhere, repeating — with near-perfect performance! 🧵

In a new preprint, we assess LLMs’ in-context learning abilities for *abstract* non-linguistic patterns—& explore how this might be useful for robotics. Examples: -extrapolating symbolic patterns -extending periodic motions -discovering simple policies (e.g. for CartPole) (1/8)

AI abdomen annotation: Bloomberg Distinguished Professors Alan Yuille, postdoc Zongwei Zhou, and team created AbdomenAtlas-8K, the world's largest multi-organ dataset. Their algo did in 3 weeks what would have taken a human 31 years—showing promise of AI cancer detection. engineering.jhu.edu/news/ai-and-ra…

📢📢📢 We are happy to introduce Alan Yuille (Alan Yuille) as a speaker at the CORR CVPR workshop. Alan is a Professor of Cognitive Science and Computer Science at Johns Hopkins University, where he directs the group on Computational Cognition, Vision, and Learning. 🧵1/2

🤩 #CVPR2024 is just around the corner! We are thrilled to present the following papers at #CVPR2025 next week. Join us in Seattle and check out the latest works from our group at JHU CCVL! JHU Computer Science Johns Hopkins Engineering 1. Jieneng Chen et al. Designing Scalable Vision Models in the

Make sure to visit our workshop on "Generative Models for ComputerVision" on Tuesday. We have an exciting speaker line-up, and 40 (!) posters on generative models. #CVPR2025 #CVPR2024 Federico Tombari Jiajun Wu Saining Xie Siyu Tang @VLG-ETHZ Jamie Shotton Alan Yuille K.Fragkiadaki A. Vedaldi

We will present 4 papers at CVPR, here is a short overview:

Check out the work from CCVL at JHU being presented this weekend at European Conference on Computer Vision #ECCV2026: cs.jhu.edu/news/yuille-la…

Introducing Genex: Generative World Explorer. 🧠 Humans mentally explore unseen parts of the world, revising their beliefs with imagined observations. ✨ Genex replicates this human-like ability, advancing embodied AI in planning with partial observations. (1/6)

Sharing a work I was recently supporting called M-VAR. The future of generative vision might be autoregressive! M-VAR is an evolution of the VAR model that is significantly more efficient to train and run. The key intuition to build the architecture is to realize that inter and

🚀Our group is seeking summer interns to join our group in 2025 and work on exciting research projects in computer vision and AI. 🔗Job posting: ccvl.jhu.edu/summer-intern-… 🤩If interested please send Prof Alan Yuille an email! Johns Hopkins Engineering JHU Computer Science Johns Hopkins Data Science and AI Institute

Congratulations to all Johns Hopkins University researchers participating in #ICLR2025! Check out all Johns Hopkins University accepted papers, tutorials, and workshops at ai.jhu.edu/news/johns-hop….