1/ 🎉 How can we develop methods to generate synthetic, photorealistic data for training #AI models in robotics? We present SplatSim, a step in this direction. SplatSim is a scalable framework that generates photorealistic data for manipulation tasks using existing simulators as

🍌We present DenseMatcher！ 🤖️DenseMatcher enables robots to acquire generalizable skills across diverse object categories by only seeing one demo, by finding correspondences between 3D objects even with different types, shapes, and appearances.

#NeurIPS2024 Spotlight: Fri 11am - 2pm , West Ballro.m #6307 We present DiffTORI, which utilizes Differentiable Trajectory Optimization as policy representation for deep Reinforcement and Imitation learning, with superior performances on existing RL and IL benchmarks. 🧵 1/

#NeurIPS2024 🤔 How can 2D images unlock the potential of Open-Vocabulary 3D Object Detection? 🚀 Introducing ImOV3D: A groundbreaking framework that leverages Only 2D data to tackle the challenge of 3D data scarcity in OV3Det.

Welcome to the world of Genesis!

Introducing ArticuBot🤖at #RSS2025, in which we learn a single policy for manipulating diverse articulated objects across 3 robot embodiments in different labs, kitchens & lounges, achieved via large-scale simulation and hierarchical imitation learning. articubot.github.io 🧵

Thrilled to share our new paper SAFE🤖! A robust failure detector for Vision-Language-Action models! This was my first time working on real-world robot experiments, and many moments over the past few months have made me excited for my robotics journey😻😻

🔍 How can we build AI agents that reason about the physical world the way humans do (or better) ? Excited to share Causal-PIK: Causality-based Physical Reasoning with a Physics-Informed Kernel, which will be presented next Thursday July 17th at ICML in Vancouver! 👇(1/6)

Check out Kallol Saha's very cool work on learning and planning for long-horizon tasks!

How do we discover a robot's failure modes before deploying it in the real world? Standard benchmarks often don't capture the full picture, leaving policies vulnerable to plausible variations in object shape. Thrilled that our work, "Geometric Red-Teaming for Robotic

Introducing FMVP: a method that adapts to natural arm motions during robot-assisted dressing. Pre-trained on vision in sim, fine-tuned with limited real-world vision+force data, and tested in a 12-user, 264-trial study, FMVP is robust across garments and motions. #CoRL2025