🔥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

Introducing AdaCache, a training-free inference accleration method for video DiTs. It allocates compute tailored to each video generation, maximizing quality-latency trade-off. project-page: adacache-dit.github.io code: github.com/AdaCache-DiT/A… arxiv: arxiv.org/pdf/2411.02397

Our team has arrived in Munich and we're thrilled to present this work at the LangRob Workshop @ #CoRL2024 as a spotlight presentation on Nov. 9 morning. Stay tuned!

I am extremely pleased to announce that CoRL 2025 will be in Seoul, Korea! The organizing team includes myself and Abhinav Gupta as general chairs, and Joseph Lim, @songshuran, and Hae-Won Park (KAIST) as program chairs.

Introducing Theia, a vision foundation model for robotics developed by our team at the Institute. By using off-the-shelf vision foundation models as a basis, Theia generates rich visual representations for robot policy learning at a lower computation cost. theaiinstitute.com/news/theia

🚨 I’ll be at #NeurIPS2024! 🚨On the industry job market this year and eager to connect in person! 🔍 My research explores multimodal learning, with a focus on object-level understanding and video understanding. 📜 3 papers at NeurIPS 2024: Workshop on Video-Language Models 📅

This is a matter of great concern and I'm glad to see that most people in the community know what needs to be done. Looking forward to further updates.

Congrats again to everyone!

Can visual SSL match CLIP on VQA? Yes! We show with controlled experiments that visual SSL can be competitive even on OCR/Chart VQA, as demonstrated by our new Web-SSL model family (1B-7B params) which is trained purely on web images – without any language supervision.

Hi everyone! I hope you had a great time in Singapore🇸🇬. Though I could not be there in person, I'm excited to share our poster schedule at #ICLR2025. Feel free to stop by, check out our work, and bring any questions you have to Kanchana Ranasinghe.

Introducing ✨Posed DROID✨, results of our efforts at automatic post-hoc calibration of a large-scale robotics manipulation dataset. We provide: 🤖 ~36k calibrated episodes with good quality extrinsic calibration 🦾 ~24k calibrated multi-view episodes with good-quality

Our MVU poster is all set up at Hall 3 poster 102 ICLR 2026 ! See you soon github.com/kahnchana/mvu

Our first author Xiang Li joining us virtually!

Thank you so much, Kanchana, for setting this up. Looking forward to great discussions!

Introducing LangToMo, learning to use pixel motion forecasting as (universal) intermediate representations for robot control: kahnchana.github.io/LangToMo