Suchergebnisse - Simchowitz, Max

Smoothed Online Learning for Prediction in Piecewise Affine Systems von Block, Adam, Simchowitz, Max, Tedrake, Russ

Volltext

Oracle-Efficient Smoothed Online Learning for Piecewise Continuous Decision Making von Block, Adam, Rakhlin, Alexander, Simchowitz, Max

Volltext

The Pitfalls of Imitation Learning when Actions are Continuous von Simchowitz, Max, Pfrommer, Daniel, Jadbabaie, Ali

Volltext

A Test-Function Approach to Incremental Stability von Pfrommer, Daniel, Simchowitz, Max, Jadbabaie, Ali

Volltext

Constrained Bimanual Planning with Analytic Inverse Kinematics von Cohn, Thomas, Shaw, Seiji, Simchowitz, Max, Tedrake, Russ

Volltext

On the Stability of Nonlinear Receding Horizon Control: A Geometric Perspective von Westenbroek, Tyler, Simchowitz, Max, Jordan, Michael I., Sastry, S. Shankar

Volltext

Robot Fleet Learning via Policy Merging von Wang, Lirui, Zhang, Kaiqing, Zhou, Allan, Simchowitz, Max, Tedrake, Russ

Volltext

Action Chunking and Exploratory Data Collection Yield Exponential Improvements in Behavior Cloning for Continuous Control von Zhang, Thomas T., Pfrommer, Daniel, Pan, Chaoyi, Matni, Nikolai, Simchowitz, Max

Volltext

Is Your Conditional Diffusion Model Actually Denoising? von Pfrommer, Daniel, Dou, Zehao, Scarvelis, Christopher, Simchowitz, Max, Jadbabaie, Ali

Volltext

History-Guided Video Diffusion von Song, Kiwhan, Chen, Boyuan, Simchowitz, Max, Du, Yilun, Tedrake, Russ, Sitzmann, Vincent

Volltext

Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion von Chen, Boyuan, Monso, Diego Marti, Du, Yilun, Simchowitz, Max, Tedrake, Russ, Sitzmann, Vincent

Volltext

Faster Algorithms for Growing Collision-Free Convex Polytopes in Robot Configuration Space von Werner, Peter, Cohn, Thomas, Jiang, Rebecca H., Seyde, Tim, Simchowitz, Max, Tedrake, Russ, Rus, Daniela

Volltext

Turning Video Models into Generalist Robot Policies von Li, Sizhe Lester, Kim, Evan, Bai, Xingjian, Zhao, Tong, Pang, Tao, Simchowitz, Max, Sitzmann, Vincent

Volltext

Joint Distillation for Fast Likelihood Evaluation and Sampling in Flow-based Models von Ai, Xinyue, He, Yutong, Gu, Albert, Salakhutdinov, Ruslan, Kolter, J Zico, Boffi, Nicholas Matthew, Simchowitz, Max

Volltext

Self-Improvement in Language Models: The Sharpening Mechanism von Huang, Audrey, Block, Adam, Foster, Dylan J., Rohatgi, Dhruv, Zhang, Cyril, Simchowitz, Max, Ash, Jordan T., Krishnamurthy, Akshay

Volltext

Nano World Models: A Minimalist Implementation of Future Video Prediction von Huang, Siqiao, Kaushik, Partha, Chen, Michael, Pan, Hengkai, Geng, Kaiwen, Chehab, Omar, Moreno-Pino, Fernando, Simchowitz, Max

Volltext

Is Linear Feedback on Smoothed Dynamics Sufficient for Stabilizing Contact-Rich Plans? von Shirai, Yuki, Zhao, Tong, Suh, H. J. Terry, Zhu, Huaijiang, Ni, Xinpei, Wang, Jiuguang, Simchowitz, Max, Pang, Tao

Volltext

e3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMs von Setlur, Amrith, Yang, Matthew Y. R., Snell, Charlie, Greer, Jeremy, Wu, Ian, Smith, Virginia, Simchowitz, Max, Kumar, Aviral

Volltext

Diffusion Policy Policy Optimization von Ren, Allen Z., Lidard, Justin, Ankile, Lars L., Simeonov, Anthony, Agrawal, Pulkit, Majumdar, Anirudha, Burchfiel, Benjamin, Dai, Hongkai, Simchowitz, Max

Volltext

Diamond Maps: Efficient Reward Alignment via Stochastic Flow Maps von Holderrieth, Peter, Chen, Douglas, Eyring, Luca, Shah, Ishin, Anantharaman, Giri, He, Yutong, Akata, Zeynep, Jaakkola, Tommi, Boffi, Nicholas Matthew, Simchowitz, Max

Volltext