MS
Max Simchowitz
cs.LGstat.MLmath.OCcs.ROcs.AIcs.DScs.SYeess.SYmath.STstat.TH
On Valency
published · living versionsW_xeqskrbu·v1 · currentpublished
Compression Forcing: Hierarchical History Tokenization Enables Flexible World Models
with Siqiao Huang, Partha Kaushik, Michael Chen, Hengkai Pan +3
1 version
Preprints & journals
76 papers in the corpus · 2015–2026Conditional Flow Models Convert Epistemic Uncertainty into Apparent Aleatoric Variance2610.29172v1 · Navodita Sharma, Abhishek Shetty, Max Simchowitz et al.2026 · 0 citationsarXivon Valency
VaDar: Implicit Goal Conditioning via Value Disaggregation2610.26629v1 · Shashwat Saxena, Mehul Goel, Sreyas Venkataraman et al.2026 · 0 citationsarXivon Valency
Memory Without Curation: Learning Multi-Stream Latent Memory for Robot Policies2610.14406v1 · Yilin Wu, Rutav Shah, Shuaiyi Huang et al.2026 · 0 citationsarXiv
Workspace Models: Lightweight Robotic Memory via Saliency-Driven Supervision2609.20820v3 · Nitish Dashora, Douglas Chen, Idan Shenfeld et al.2026 · 0 citationsarXiv
What Does It Take For A Generalist Robot Policy To Adapt Using Minimal Data?2608.11363v3 · Shreyas Kowshik, Sreyas Venkataraman, Leo Wang et al.2026 · 0 citationsarXiv
FADA: Few-Shot Domain Adaptation via Dynamics Alignment for Humanoid Control2606.28476v2 · Angchen Xie, Nikhil Sobanbabu, Ishayu Shikhare et al.2026 · 0 citationsarXiv
Double Preconditioning (DoPr): Optimization for Test-Time Performance, not Validation Loss2606.06418v1 · Thomas T. Zhang, Alok Shah, Yifei Zhang et al.2026 · 0 citationsarXiv
Turning Video Models into Generalist Robot Policies2605.27817v1 · Sizhe Lester Li, Evan Kim, Xingjian Bai et al.2026 · 0 citationsarXiv
Nano World Models: A Minimalist Implementation of Future Video Prediction2605.23993v2 · Siqiao Huang, Partha Kaushik, Michael Chen et al.2026 · 0 citationsarXiv
MLS-Bench: A Holistic and Rigorous Assessment of AI Systems on Building Better AI2605.08678v3 · Bohan Lyu, Yucheng Yang, Siqiao Huang et al.2026 · 0 citationsarXiv
OGPO: Sample Efficient Full-Finetuning of Generative Control Policies2605.03065v4 · Sarvesh Patil, Mitsuhiko Nakamoto, Manan Agarwal et al.2026 · 0 citationsarXiv
Diamond Maps: Efficient Reward Alignment via Stochastic Flow Maps2602.05993v3 · Peter Holderrieth, Douglas Chen, Luca Eyring et al.2026 · 1 citationarXiv
Is Your Conditional Diffusion Model Actually Denoising?2512.18736v1 · Daniel Pfrommer, Zehao Dou, Christopher Scarvelis et al.2025 · 0 citationsarXiv
Joint Distillation for Fast Likelihood Evaluation and Sampling in Flow-based Models2512.02636v3 · Xinyue Ai, Yutong He, Albert Gu et al.2025 · 0 citationsarXiv
Much Ado About Noising: Dispelling the Myths of Generative Robotic Control2512.01809v3 · Chaoyi Pan, Giri Anantharaman, Nai-Chieh Huang et al.2025 · 0 citationsarXiv
Action Chunking and Exploratory Data Collection Yield Exponential Improvements in Behavior Cloning for Continuous Control2507.09061v5 · Thomas T. Zhang, Daniel Pfrommer, Chaoyi Pan et al.2025 · 0 citationsarXiv
A Test-Function Approach to Incremental Stability2507.00695v2 · Daniel Pfrommer, Max Simchowitz, Ali Jadbabaie2025 · 0 citationsarXiv
e3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMs2506.09026v2 · Amrith Setlur, Matthew Y. R. Yang, Charlie Snell et al.2025 · 0 citationsarXiv
The Pitfalls of Imitation Learning when Actions are Continuous2503.09722v4 · Max Simchowitz, Daniel Pfrommer, Ali Jadbabaie2025 · 0 citationsarXiv
History-Guided Video Diffusion2502.06764v2 · Kiwhan Song, Boyuan Chen, Max Simchowitz et al.2025 · 0 citationsarXiv
Self-Improvement in Language Models: The Sharpening Mechanism2412.01951v2 · Audrey Huang, Adam Block, Dylan J. Foster et al.2024 · 2 citationsarXiv
Is Linear Feedback on Smoothed Dynamics Sufficient for Stabilizing Contact-Rich Plans?2411.06542v4 · Yuki Shirai, Tong Zhao, H.J. Terry Suh et al.2024 · 4 citationsarXiv
Faster Algorithms for Growing Collision-Free Convex Polytopes in Robot Configuration Space2410.12649v2 · Peter Werner, Thomas Cohn, Rebecca H. Jiang et al.2024 · 2 citationsarXiv
Diffusion Policy Policy Optimization2409.00588v3 · Allen Z. Ren, Justin Lidard, Lars L. Ankile et al.2024 · 2 citationsarXiv
Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion2407.01392v4 · Boyuan Chen, Diego Marti Monso, Yilun Du et al.2024 · 59 citationsarXiv
Butterfly Effects of SGD Noise: Error Amplification in Behavior Cloning and Autoregression2310.11428v1 · Adam Block, Dylan J. Foster, Akshay Krishnamurthy et al.2023 · 0 citationsarXiv
Robot Fleet Learning via Policy Merging2310.01362v3 · Lirui Wang, Kaiqing Zhang, Allan Zhou et al.2023 · 0 citationsarXiv
Constrained Bimanual Planning with Analytic Inverse Kinematics2309.08770v2 · Thomas Cohn, Seiji Shaw, Max Simchowitz et al.2023 · 11 citationsarXiv
RePo: Resilient Model-Based Reinforcement Learning by Regularizing Posterior Predictability2309.00082v2 · Chuning Zhu, Max Simchowitz, Siri Gadipudi et al.2023 · 2 citationsarXiv
Provable Guarantees for Generative Behavior Cloning: Bridging Low-Level Stability and High-Level Behavior2307.14619v5 · Adam Block, Ali Jadbabaie, Daniel Pfrommer et al.2023 · 4 citationsarXiv
Tackling Combinatorial Distribution Shift: A Matrix Completion Perspective2307.06457v3 · Max Simchowitz, Abhishek Gupta, Kaiqing Zhang2023 · 1 citationarXiv
The Power of Learned Locally Linear Models for Nonlinear Policy Optimization2305.09619v1 · Daniel Pfrommer, Max Simchowitz, Tyler Westenbroek et al.2023 · 1 citationarXiv
Non-Euclidean Motion Planning with Graphs of Geodesically-Convex Sets2305.06341v2 · Thomas Cohn, Mark Petersen, Max Simchowitz et al.2023 · 17 citationsarXiv
Learning to Extrapolate: A Transductive Approach2304.14329v1 · Aviv Netanyahu, Abhishek Gupta, Max Simchowitz et al.2023 · 2 citationsarXiv
Statistical Learning under Heterogeneous Distribution Shift2302.13934v4 · Max Simchowitz, Anurag Ajay, Pulkit Agrawal et al.2023 · 1 citationarXiv
Oracle-Efficient Smoothed Online Learning for Piecewise Continuous Decision Making2302.05430v2 · Adam Block, Alexander Rakhlin, Max Simchowitz2023 · 0 citationsarXiv
Smoothed Online Learning for Prediction in Piecewise Affine Systems2301.11187v2 · Adam Block, Max Simchowitz, Russ Tedrake2023 · 0 citationsarXiv
Efficient and Near-Optimal Smoothed Online Learning for Generalized Linear Functions2205.13056v1 · Adam Block, Max Simchowitz2022 · 0 citationsarXiv
Globally Convergent Policy Search over Dynamic Filters for Output Estimation2202.11659v2 · Jack Umenberger, Max Simchowitz, Juan C. Perdomo et al.2022 · 6 citationsarXiv
Online Control of Unknown Time-Varying Dynamical Systems2202.07890v1 · Edgar Minasyan, Paula Gradu, Max Simchowitz et al.2022 · 6 citationsarXiv
Do Differentiable Simulators Give Better Policy Gradients?2202.00817v2 · H.J. Terry Suh, Max Simchowitz, Kaiqing Zhang et al.2022 · 17 citationsICML 2022
Reward-Free RL is No Harder Than Reward-Aware RL in Linear Markov Decision Processes2201.11206v2 · Andrew Wagenmaker, Yifang Chen, Max Simchowitz et al.2022 · 8 citationsarXiv
First-Order Regret in Reinforcement Learning with Linear Function Approximation: A Robust Estimation Approach2112.03432v4 · Andrew Wagenmaker, Yifang Chen, Max Simchowitz et al.2021 · 3 citationsarXiv
Stabilizing Dynamical Systems via Policy Gradient Methods2110.06418v1 · Juan C. Perdomo, Jack Umenberger, Max Simchowitz2021 · 19 citationsarXiv
Beyond No Regret: Instance-Dependent PAC Reinforcement Learning2108.02717v2 · Andrew Wagenmaker, Max Simchowitz, Kevin Jamieson2021 · 4 citationsarXiv
Bayesian decision-making under misspecified priors with applications to meta-learning2107.01509v1 · Max Simchowitz, Christopher Tosh, Akshay Krishnamurthy et al.2021 · 9 citationsarXiv
On the Stability of Nonlinear Receding Horizon Control: A Geometric Perspective2103.15010v3 · Tyler Westenbroek, Max Simchowitz, Michael I. Jordan et al.2021 · 4 citationsarXiv
Towards a Dimension-Free Understanding of Adaptive Linear Control2103.10620v2 · Juan C. Perdomo, Max Simchowitz, Alekh Agarwal et al.2021 · 2 citationsarXiv
Exploration and Incentives in Reinforcement Learning2103.00360v5 · Max Simchowitz, Aleksandrs Slivkins2021 · 18 citationsarXiv
Task-Optimal Exploration in Linear Dynamical Systems2102.05214v2 · Andrew Wagenmaker, Max Simchowitz, Kevin Jamieson2021 · 7 citationsarXiv
Career total: 87 works. 76 are in this corpus.Showing the 50 most recent.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.