Jiaying Fang

Excited about our new release: π0.7. One result I’m especially excited about is cross-embodiment transfer. 🤖 We train on laundry folding data from lightweight, easy-to-teleoperate bimanual robots, yet the model transfers the skill to a bimanual UR5e — heavier, bulkier, and harder to control due to large joint inertia — with no task data on that robot. It matches the performance of our most experienced teleoperators attempting this task on UR5e for the first time. Early on, when we started exploring cross-embodiment transfer with @allenzren and @QuanVng, shirt folding on UR5e felt out of reach. Seeing the first signs that it might work was exciting — pushing it to this level was even more so. To me, this is both scientifically and practically exciting: robots are no longer isolated data sources. Experience from one platform can directly benefit another. Instead of fragmented, per-robot data collection, we move toward a shared learning process where every embodiment both contributes to and benefits from the whole. Proud of the team @physical_int ! 🎉🎉🎉

🤖 Can a single robot policy manipulate diverse tools without ever seeing them before? Introducing SimToolReal 🔨 : a generalist dexterous manipulation policy that transfers zero-shot sim→real to unseen tools + unseen tasks All videos are 1x speed (60 Hz control) 🧵👇

Physical caregiving is one of robotics' hardest frontiers: it is contact-rich, physically intensive, long-horizon, safety-critical, and full of deformable objects. Physical caregiving tasks such as bathing, dressing, transferring, toileting, and grooming require professional training and considerable practical experience. Yet, no existing dataset captures how expert caregivers perceive, interact, and adapt in real-time when performing these tasks, in a form that robots can learn from. ✨ We introduce OpenRoboCare at #IROS2025, the first expert-collected, multi-task, multimodal dataset for physical robot caregiving, featuring: 🩺 21 expert occupational therapists demonstrating caregiving procedures 🛠️ 15 caregiving tasks across 5 Activities of Daily Living (bathing, dressing, transferring, toileting, grooming) 🧍 2 hospital-grade manikins for safety and repeatability 🎥 5 synchronized sensing modalities: RGB-D, pose tracking, eye gaze, tactile sensing, and expert task & action annotations 📂 315 sessions · 19.8 hrs · 31,185 samples Beyond raw data, OpenRoboCare distills core physical caregiving insights: - 3 core principles followed by occupational therapists: pre-positioning, anticipation of body mechanics, and task efficiency. - 4 key physical techniques: the bridge strategy, segmental rolling, wheelchair recline, and stabilization of key control points. - Quantitative patterns in task duration, predictive gaze behavior that precedes physical contact, and the timing, magnitude, and spatial distribution of contact forces across body regions and task phases. The dataset will be made openly accessible through the AWS Open Data Sponsorship Program soon. 🌐 Check out our project website for more visuals and insights: emprise.cs.cornell.edu/robo-care/ This work is led by: @xiaoyul14, @RealZiangLiu, and Kelvin Lin. This is a collaboration with Harold Soh's group from NUS and @DimitropoulouDr from CUIMC. @EmpriseLab @Cornell_CS @IROS2025 @awscloud

Excited to share our work on multimodal perception for real robots, CLAMP, now accepted at #CoRL2025 ! Do come say hi at our poster session on Sep 30 if you're attending!

During a meal, food may cool down resulting in a change in its physical properties, even though visually it may look the same! How can robots reliably pick up food when it looks the same but feels different — such as steak 🥩getting firmer as it cools? 🍴 Check out @ZhanxinWu0725's work SAVOR: Skill Affordance Learning from Visuo-Haptic Perception for Robot-Assisted Bite Acquisition — an oral at #CoRL2025. SAVOR introduces a novel method to learn skill affordances, which capture how suitable a manipulation skill (e.g., skewering, scooping) is for a utensil–food interaction. Skill affordances arise from the combination of tool affordances (what a utensil can do) and food affordances (what the food allows). Using this method, SAVOR improves bite acquisition success by 13% over state-of-the-art methods. @EmpriseLab @Cornell_CS @corl_conf 🗣️ Oral presentation at #CoRL2025 — join us on Sep 28 (afternoon session) 🌐 Website: emprise.cs.cornell.edu/savor/ 📄 Paper: arxiv.org/pdf/2506.02353 Check this thread for more details (1/6) 🧵

Now with open-source code for both, Masquerade and its predecessor Phantom!

NERC 2025 is happening @Cornell this year. Here is the website with more details: nerc2025.cis.cornell.edu We have a fantastic set of keynote speakers from a variety of backgrounds @Majumdar_Ani from @Princeton, Victoria Webster-Wood from @CarnegieMellon, @wendyju from @cornell_tech, and @HerlantLaura from RAI With poster presentations of extended abstracts, Rising Star spotlight talks, and demos / booths and other support from our generous sponsors @FourierRobots @rai_inst @clearpathrobots @UnitreeRobotics @CornellCIS and @CornellCOE , this event is going to be exciting! Do register (Early Deadline: September 10th, Late Deadline: October 3rd) and come enjoy this event at the beautiful @Cornell Campus in Ithaca on October 11th 🎉🎉

Can’t wait to start my PhD with @TapoBhat at @EmpriseLab!

The internet is full of human videos, but how can we use them to teach robots? 🤖💡 Check out our new work, Masquerade 🎭 We "replace" human arms with robot arms!

@dimadamen @marionlepert @leto__jean Thank you! 🥳

When googling the authors to tag them I realized this is an all-female author list, which made me even more excited... Big shout out to female rising stars @marionlepert @jiaying_fang0 and of course their advisor @leto__jean

This is one of the coolest ideas using EPIC-KITCHENS in a long while... We've all been waiting to be replaced by robots! At least this is now done in the generative space... Great work by @marionlepert @jiaying_fang0 @leto__jean @StanfordIPRL .. congrats! arxiv.org/abs/2508.09976

Introducing Masquerade 🎭: We edit in-the-wild videos to look like robot demos, and find that co-training policies with this data achieves much stronger performance in new environments. ❗Note: No real robots in these videos❗It’s all 💪🏼 ➡️ 🦾 🧵1/6

Check out our Phantom👻, thrilled to be part of this!

Introducing Phantom 👻: a method to train robot policies without collecting any robot data — using only human video demonstrations. Phantom turns human videos into "robot" demonstrations, making it significantly easier to scale up and diversify robotics data. 🧵1/9