Bowen Li

"Generalization means being able to solve problems that the system hasn't been prepared for." Our latest work in #RSS2025 can automatically invent neural networks as state abstractions, which help robots generalize. Check it out here: jaraxxus-me.github.io/IVNTR/

How to generate billion-scale manipulation demonstrations easily? Let us leverage generative models! 🤖✨ We introduce Dex1B, a framework that generates 1 BILLION diverse dexterous hand demonstrations for both grasping 🖐️and articulation 💻 tasks using a simple C-VAE model.

🚀 Excited to share that the Workshop on Mathematical Reasoning and AI (MATH‑AI) will be at NeurIPS 2025! 📅 Dec 6 or 7 (TBD), 2025 🌴 San Diego, California

Officially validated IMO gold medal, purely via search in token space, achieved in 4.5 hrs (unclear at what compute cost). The solutions read nicely as well deepmind.google/discover/blog/…

Is "scaling is all you need" the right path for robotics? Announcing our @corl_conf workshop on "Resource-Rational Robot Learning", where we will explore how to build efficient intelligent systems that learn & thrive under real-world constraints. Submission deadline: Aug 8 🧵

Large robot datasets are crucial for training 🤖foundation models. Yet, we lack systematic understanding of what data matters. Introducing MimicLabs ✅System to generate large synthetic robot 🦾 datasets ✅Data-composition study 🗄️ on how to collect and use large datasets 🧵1/

Model and training code for LaCT on language model, AR video gen and novel view synthesis are released, also have a TTT layer implementation with sequence parallel supported. Both object-centric and scene-level view synthesis checkpoints are released 🤓— come play!

Today we’re releasing our first public preview of ARC-AGI-3: the first three games. Version 3 is a big upgrade over v1 and v2 which are designed to challenge pure deep learning and static reasoning. In contrast, v3 challenges interactive reasoning (eg. agents). The full version…

Sharing a project that’s kept me excited for months: Five years ago, I tried projecting a 10000×10000 symmetric matrix onto the positive semidefinite cone using MATLAB’s eig on my MacBook—gave up out of sheer impatience. Today, we released a CUDA-based factorization-free method…

Hello world! This is @nishanthkumar23 and I'll be taking over @MIT_CSAIL 's X/Twitter & Instagram for 24 hours! I'm a 4th year PhD @MITEECS working on AI/ML for Robotics and Computer Agents. Drop any and all questions about research, AI, MIT, or dogs (esp. robot dogs!) below 👇

We're excited to announce the third workshop on LEAP: Learning Effective Abstractions for Planning, to be held at #CoRL2025 @corl_conf! Early submission deadline: Aug 12 Late submission deadline: Sep 5 Website link below 👇

Introducing SOAR 🚀, a self-improving framework for prog synth that alternates between search and learning (accepted to #ICML!) It brings LLMs from just a few percent on ARC-AGI-1 up to 52% We’re releasing the finetuned LLMs, a dataset of 5M generated programs and the code. 🧵

Thrilled to join @virginia_tech as an assistant professor in @VirginiaTech_ME this fall! At the TEA lab (tealab.ai), we’ll explore hybrid AI systems for efficient and adaptive agents and robots 🤖 Thank you to everyone who has supported me along the way!

Perhaps the most unintuitive thing about AI today is that AI can simultaneously score 50%+ on Humanity's Last Exam (relatively hard for humans) while only scoring 16% on ARC-AGI-2 (relatively easy for humans). Example v2 task below.

I'm teaching a new course this fall called "Robot Planning Meets Machine Learning." Half lectures, half seminar. Paper recommendations for the seminar part are welcome. I'm looking for any creative combinations of robot planning and ML.

TRI's latest Large Behavior Model (LBM) paper landed on arxiv last night! Check out our project website: toyotaresearchinstitute.github.io/lbm1/ One of our main goals for this paper was to put out a very careful and thorough study on the topic to help people understand the state of the…

Recording of my talk "From Sim2Real 1.0 to 4.0 for Humanoid Whole-Body Control and Loco-Manipulation" (at ICRA&CVPR workshops and Caltech): youtu.be/AGNcw4qnimk?si… Slides: drive.google.com/file/d/1h5MxNH…

I'm attending @RoboticsSciSys for the first time #RSS2025 in LA Excited to be giving two invited talks, at the Continual Learning and EgoAct workshops on Sat, June 21 I'll share the latest on 2D/3D motion prediction from human videos for manipulation! Do drop by and say hi :)

🚀 VR-Robo: A Real-to-Sim-to-Real pipeline for RGB vision-based navigation & control in legged robots. 💡 Reconstruct realistic indoor scenes using RGB 🧠 Train RL policies with photorealistic simulation 🤖 Deploy directly on real visual robots! 🔗 vr-robo.github.io

Most assistive robots live in labs. We want to change that. FEAST enables care recipients to personalize mealtime assistance in-the-wild, with minimal researcher intervention across diverse in-home scenarios. 🏆 Outstanding Paper & Systems Paper Finalist @RoboticsSciSys 🧵1/8

🚀 Introducing UniRelight, a general-purpose relighting framework powered by video diffusion models. 🌟UniRelight jointly models the distribution of scene intrinsics and illumination, enabling high-quality relighting and intrinsic decomposition from a single image or video.