🔥Telegram İfşa

Can robots choose actions (position objects by pushing) and precisely execute them (decide the push trajectories) to fulfill abstract goals? We use a relational model that considers actions and the resulting dynamics between objects and environments. Check out Yixuan's 🧵!

ICRA workshop dates are out. The first workshop on Vision-Language Models for Navigation and Manipulation will be held on 17th May in Yokohama, Japan. We are currently accepting submissions on OpenReview. openreview.net/group?id=IEEE.…

Can we use wearable devices to collect robot data without actual robots? Yes! With a pair of gloves🧤! Introducing DexCap, a portable hand motion capture system that collects 3D data (point cloud + finger motion) for training robots with dexterous hands Everything open-sourced

A T-RO paper by researchers University of Utah Robotics Center, NVIDIA, HRL Laboratories and Georgia Tech describes a #robot that can rearrange novel objects in diverse environments with logical goals by flexibly combining primitive actions including pick, place and push. ieeexplore.ieee.org/document/10418…

Does your sim2real robot falter at critical moments 🤯? Want to help but unsure how, all you can do is reward tuning in sim 😮‍💨? Introduce 𝐓𝐑𝐀𝐍𝐒𝐈𝐂 for manipulation sim2real. Robots learned in sim can accomplish complex tasks in real, such as furniture assembly. 🤿🧵

What structural task representation enables multi-stage, in-the-wild, bimanual, reactive manipulation? Introducing ReKep: LVM to label keypoints & VLM to write keypoint-based constraints, solve w/ optimization for diverse tasks, w/o task-specific training or env models. 🧵👇

Learned visuomotor robot policies are sensitive to observation viewpoint shifts, which happen all the time. Can visual priors from large-scale data help? Introducing VISTA: using zero-shot novel view synthesis models for view-robust policy learning! #CoRL2024 🧵👇

Why hand-engineer digital twins when digital cousins are free? Check out ACDC: Automated Creation of Digital Cousins 👭 for Robust Policy Learning, accepted at @corl2024! 🎉 📸 Single image -> 🏡 Interactive scene ⏩ Fully automatic (no annotations needed!) 🦾 Robot policies

Accurate and controllable scene generation has been difficult with natural language alone. You instead need a language for scenes. Introducing the Scene Language — a visual representation for high-quality 3D/4D generation by integrating programs, words, and embeddings — 🧵(1/6)

What can we learn from demonstrations of long-horizon tasks? I am presenting our #CoRL2024 paper "Learning Compositional Behaviors from Demonstration and Language" today, showing we can learn a library of behaviors that can be composed to solve new tasks. blade-bot.github.io

To build complex 3D structures with many parts, like IKEA furniture, we usually follow instructions and how-to videos. We introduce a new dataset with dense annotations on internet videos to study the grounding of video instructions in 3D. Check out the thread for details!

1/ [NeurIPS D&B] Introducing HourVideo: A benchmark for hour-long video-language understanding!🚀 500 egocentric videos, 18 total tasks & ~13k questions! Performance: GPT-4➡️25.7% Gemini 1.5 Pro➡️37.3% Humans➡️85.0% We highlight a significant gap in multimodal capabilities🧵👇

🤖 Ever wondered what robots need to truly help humans around the house? 🏡 Introducing 𝗕𝗘𝗛𝗔𝗩𝗜𝗢𝗥 𝗥𝗼𝗯𝗼𝘁 𝗦𝘂𝗶𝘁𝗲 (𝗕𝗥𝗦)—a comprehensive framework for mastering mobile whole-body manipulation across diverse household tasks! 🧹🫧 From taking out the trash to

How to extract spatial knowledge from VLMs to generate 3D layouts? We combine spatial relations, visual markers, and code into a unified representation that is both interpretable by VLMs and flexible for generating diverse scenes. Check out the detailed post by Fan-Yun Sun!

Today is the day! Welcome to join #CVPR2025 workshop on Foundation Models meet Embodied Agents! 🗓️Jun 11 📍Room 214 🌐…models-meet-embodied-agents.github.io/cvpr2025/ Looking forward to learning insights from wonderful speakers Jitendra MALIK Ranjay Krishna Katerina Fragkiadaki Shuang Li Yilun Du

Thank you for sharing our work Y Combinator! Please checkout vernerobotics.com to schedule a free pilot to see how our robots can transform your business! - Thank you to (co-founder) Aditya, my research advisors, colleagues, friends and family for your support!

Congratulations to Neil Nie and the team on the launch! Neil has worked with us at Stanford over the past two years on learning generalizable long-horizon manipulation from as few as five demonstrations. I’m excited to see where his next adventure takes him and how our

I’m at #CoRL2025 in Seoul this week! I’m looking for students to join my lab next year, and also for folks excited to build robotic foundation models at a startup. If you’re into generalization, planning and reasoning, or robots that use language, let's chat!

To complete a wide range of household tasks, such as cleaning after a meal, robots must actively look 👀 at task-relevant objects that change across stages, manipulate 🙌 with two arms for both coordinated and independent actions, and move 👣 intelligently to facilitate