Sparse Polynomial Optimization with Unbounded Sets just accepted to SIAM Journal on Optimization! Congrats to Shucheng Kang! A lot to expect from sparse moment-sos relaxations!

Going to miss #NeurIPS2024 but please check out Aneesh's "Fast TRAC: A Parameter-Free Optimizer for Lifelong Reinforcement Learning"!

Just landed and here are at #NeurIPS2024!! Would love to chat with anyone on: lifelong RL (FastTRAC), generative world models, vision-language-action models, ARC-AGI, AI scientists, and more.

How is Rosalind going to face the hundreds of talented, hardworking, and genuine Chinese students at Massachusetts Institute of Technology (MIT) when she got back? They (and many of us) went through so much trouble to get to the US due to the pure drive to do good science, and yet you put this in your slide. This is

Congrats to our wonderful Rhodes Scholar Aneesh! Made us proud!

How robust can model predictive control be if we can solve each trajectory optimization to global optimality? On the contact-rich push-T problem, we show that model-based global optimization is so robust that it never fails, even if the model is not even correct! We achieve

Diffusion has shown great promise for generating robot **actions**, can it act as a **world model** to generate the future conditioned on actions? In our work led by han qi Haocheng Yin and in collaboration with Yilun Du, we show a **controllable** action-conditioned video

Here is the paper containing technical details of “Global Contact-Rich Planning with Sparsity-Rich Semidefinite Relaxations” arxiv.org/pdf/2502.02829 Stay tuned for SPOT (Sparse Polynomial Optimization Toolbox)!

Building Rome with Convex Optimization Haoyuhan, Heng Yang tl;dr: 2D keypoints+pretrained depth->scaled BA->QCQP->empirically tight convex SDR->Burer-Monteiro factorization+CUDA-based trust-region Riemannian optimizer arxiv.org/abs/2502.04640

In Contact-Rich motion planning, the so-called "Contact-Implicit" formulation stands out as it embeds discrete and combinatorial contact sequencing using implicit "complementarity constraints" in a continuous optimization problem. The contact-implicit formulation looks

Had fun presenting Shucheng Kang's recent work, “Local Linear Convergence of ADMM for Solving SDPs under Strict Complementarity,” at the Numerical Analysis Seminar hosted by the Department of Mathematics at the University of Maryland. In this work, we uncover and prove an

Going to #ICLR2025? Check out our Spotlight paper "Control-oriented Clustering of Visual Latent Representation" presented by Han Qi. TL;DR: We investigated the geometric structure of the visual latent space in a vision-based control pipeline trained via behavior cloning, and

Here is the recording of the Robotics Worldwide Workshop, held at MIT on April 4, 2025: youtube.com/watch?v=0OdOvk… -includes "All Robotics in 90 minutes" lightning talks and a panel discussion on the future of robotics. not for the faint of heart. #mitSparkLab MIT LIDS MIT Schwarzman College of Computing

"Building Rome with Convex Optimization" has been accepted to #RSS2025! Try XM, our new structure from motion pipeline powered by GPU-accelerated convex semidefinite optimization: github.com/ComputationalR… XM solves large-scale (nonconvex) global bundle adjustment problem via

Wow "Building Rome with Convex Optimization" is a #RSS2025 Outstanding Systems Paper Award Finalist — congratulations to Haoyuhan! Also excited to see XM tackled a massive bundle adjustment problem involving 20,000 images, shared by a GitHub issue — an SDP of size 60,000 ×

Excited about this work that leverages simulation for more efficient real-world validation.

Check out Kevin’s work on Adapting Conformal Prediction to Distribution Shifts without Labels at UAI!