Constrained Sampling

Follow this topic Ask about this topic

Latest papers

29 papers6 papers in the last four weeks, up 50% on the four weeks before. 0.0% of all new papers.

CS-Pi: Constraint-Satisfying Flow Policy Sampling
Nov 5, 2026Soumojit Bhattacharya, Oliver Kroemer, Shubham TulsianiConstrained Sampling Robot Policy Learning
Robotics Institute, Carnegie Mellon University
Numerical Integration on Bounded Domains via Learned Reflected Diffusions
Oct 29, 2026Kirill Korolev, Artur Goldman, Timofei Gritsaev +2Numerical Integration Importance Sampling
HSE University · ETH Zürich, ETH AI Center · Constructor University
First hardware demonstration of a continuous-state probabilistic computer with programmable energy-defined sampling
Oct 22, 2026Chao Fang, Hsuan Yao Tu, Yihan He +3Energy-Based Models Constrained Sampling
Department of Electrical and Computer Engineering, National University of Singapore, 117583 Singapore · Department of Electronics and Electrical Engineering and Institute of Electrical and Computer Engineering, National Yang Ming Chiao Tung University, Hsinchu, Taiwan · Industry Academia Innovation School, National Yang-Ming Chiao Tung University, Hsinchu, Taiwan
ConicFlow: constrained Inference-time optimal control for flow matching models
Oct 9, 2026Shervin Khalafi, Kasra Fallah, Sung Cho +3Constrained Generative Modeling Constrained Sampling
University of Pennsylvania · Columbia University · University of Tennessee, Knoxville
Primal-Dual Flow Matching for Sample-Wise Constrained Generation
Oct 8, 2026Zhengyan Huan, Peter Y. Lu, Shuchin AeronConstrained Generative Modeling Constrained Sampling
Department of Electrical and Computer Engineering, Tufts University · NSF AI Institute for Artificial Intelligence and Fundamental Interactions
Accelerating Non-Smooth and Heavy-Tailed Sampling
Oct 8, 2026Pervez Ali, Xiaoyu Wang, Yingli Wang +1Constrained Sampling Langevin Dynamics
Department of Mathematics, Florida State University, Tallahassee, Florida, United States of America · Fintech Thrust, Hong Kong University of Science and Technology (Guangzhou), Guangzhou, Guangdong Province, People’s Republic of China · School of Mathematical Sciences, Fudan University, Shanghai, People’s Republic of China
Reflected Anchored Langevin Algorithms
Oct 7, 2026Changwei Tu, Xiaoyu Wang, Yingli Wang +2Constrained Sampling Langevin Dynamics
Hong Kong University of Science and Technology (Guangzhou), Guangzhou, Guangdong Province, People’s Republic of China · School of Mathematical Sciences, Fudan University, Shanghai, People’s Republic of China · School of Mathematics and Statistics, Beijing Institute of Technology, Beijing 100081, People’s Republic of China +1
MintFlow: Minimal Trajectory Intervention for Constrained Flow Matching
Sep 30, 2026Yesom Park, Kelvin Kan, Qifan Chen +3Constrained Generative Modeling Constrained Sampling
Department of Mathematics, University of California, Los Angeles · Brookhaven National Laboratory
Making Grid Beam Search Less Greedy
Sep 30, 2026Sean Papay, Roman KlingerConstrained Decoding Constrained Sampling
Fundamentals of Natural Language Processing University of Bamberg Germany
Penalized Nonreversible Langevin for Constrained Sampling
Sep 21, 2026Pervez Ali, Weihao Dong, Xiaoyu WangMarkov Chain Monte Carlo Stochastic Gradient Langevin Dynamics
Department of Mathematics, Florida State University, Tallahassee, Florida, United States of America · Hong Kong University of Science and Technology (Guangzhou), Guangzhou, Guangdong, People’s Republic of China · FinTech Thrust, Hong Kong University of Science and Technology (Guangzhou), Guangzhou, Guangdong, People’s Republic of China
Quenched Ensemble Sampling
Sep 14, 2026David YallupBayesian Inference Posterior Sampling
Kavli Institute for Cosmology Cambridge Institute of Astronomy, University of Cambridge, Madingley Road, Cambridge, CB3 0HA, UK
The Cost of Conservation: Coordination-Memory Laws for Exact-Support Generation
Aug 17, 2026Zhen Zhang, Amr AlanwarConstrained Sampling
School of Computation, Information and Technology Technical University of Munich, Germany
Integration Matters: Rollout-Based Training for Constrained Diffusion Models
Jul 15, 2026Xiaoxuan Liang, Saeid Naderiparizi, Berend Zwartsenberg +1Constrained Generative Modeling Diffusion Sampling
University of British Columbia · Inverted AI · Alberta Machine Intelligence Institute
SNAP-FM: Sparse Nonlinear Accelerated Projection for Physics-Constrained Generative Modeling
Jun 30, 2026Alaina Kolli, Theodoros Xenakis, Utkarsh Utkarsh +4Constrained Generative Modeling Physics-Informed Generative Modeling
Massachusetts Institute of Technology, Cambridge, MA, USA · Norwegian University of Science and Technology, Trondheim, Norway
BayesFP: Posterior Estimation for Flow-Based Policies via Feynman-Kac Sampling
Jun 19, 2026Sreevardhan Sirigiri, Weiming Zhi, Fabio RamosDiffusion Policy Trajectory Generation
School of Computer Science, The University of Sydney, Australia · Australian Centre For Robotics, The University of Sydney, Australia · College of Connected Computing, Vanderbilt University, TN, USA. +1
Constrained Diffusion Models with Primal-Dual Inference
Jun 15, 2026Samar Hadou, Yigit Berkay Uslu, Alejandro RibeiroPrimal-Dual Optimization Constrained Generative Modeling
Department of Electrical and Systems Engineering, University of Pennsylvania
The Right Measure for Physics-Constrained Generation: A Co-Area Correction for Posterior-Consistent PDE Inverse Problems
Jun 3, 2026Jian Xu, Yanning Wu, Delu Zeng +2Constrained Generative Modeling Physics-Informed Generative Modeling
1RIKEN iTHEMS · 2RIKEN AIP · 3South China University of Technology +1
Mitigating Bias in Locally Constrained Decoding via Tractable Proposals
Jun 1, 2026Meihua Dang, Linxin Song, Honghua Zhang +3Constrained Generative Modeling Constrained Decoding
Department of Computer Science, Stanford University · Department of Computer Science, University of Southern California · Department of Computer Science, University of California, Los Angeles
Constraint-Aware Flow Matching: Decision Aligned End-to-End Training for Constrained Sampling
May 12, 2026Jacob K. Christopher, James E. Warner, Ferdinando FiorettoConstrained Generative Modeling Flow Matching
University of Virginia · NASA Langley Research Center
Manifold Sampling via Entropy Maximization
May 12, 2026Cornelius V. Braun, Tilman Burghoff, Marc ToussaintMarkov Chain Monte Carlo Constrained Sampling
Technische Universität Berlin · Robotics Institute Germany
Enforcing Constraints in Generative Sampling via Adaptive Correction Scheduling
May 11, 2026Noah Trupin, Yexiang XueConstrained Generative Modeling Diffusion Sampling
Department of Computer Science, Purdue University
Primal-Dual Guided Decoding for Constrained Discrete Diffusion
May 10, 2026Federico Tomasi, Dmitrii Moor, Alice Wang +1Primal-Dual Optimization Constrained Generative Modeling
Spotify
Decentralized Proximal Stochastic Gradient Langevin Dynamics
May 1, 2026Mohammad Rafiqul Islam, Lingjiong ZhuMarkov Chain Monte Carlo Stochastic Gradient Langevin Dynamics
Department of Mathematics, Florida State University, Tallahassee, Florida, United States of America
Efficient Diffusion Models under Nonconvex Equality and Inequality constraints via Landing
Apr 20, 2026Kijung Jeon, Michael Muehlebach, Molei TaoConstrained Generative Modeling Langevin Dynamics
Georgia Institute of Technology · Max Planck Institute for Int. Sys.
Improved Constrained Generation by Bridging Pretrained Generative Models
Mar 6, 2026Xiaoxuan Liang, Saeid Naderiparizi, Yunpeng Liu +2Constrained Generative Modeling Generative Modeling
University of British Columbia · Inverted AI
Provably Safe Generative Sampling with Constricting Barrier Functions
Feb 24, 2026Darshan Gadginmath, Ahmed Allibhoy, Fabio PasqualettiConstrained Sampling Constrained Generative Modeling
Mitsubishi Electric Research Laboratories Cambridge, Massachusetts · Electrical Engineering and Computer Science University of California, Irvine
Constrained and Composite Sampling via Proximal Sampler
Feb 16, 2026Thanh Dang, Jiaming LiangProximal Sampling Constrained Sampling
Department of Computer Science, University of Rochester, Rochester, NY 14620. · Goergen Institute for Data Science and Artificial Intelligence (GIDS-AI) and Department of Computer Science, University of Rochester, Rochester, NY 14620
Manifold-Aware Perturbations for Constrained Generative Modeling
Jan 30, 2026Katherine Keegan, Lars RuthottoConstrained Generative Modeling Generative Modeling
Department of Mathematics, Emory University, Atlanta, Georgia, USA.
Sampling Method for Generalized Graph Signals With Pre-Selected Vertices via DC Optimization
Sep 18, 2025Keitaro Yamashita, Kazuki Naganuma, Shunsuke OnoGraph Signal Processing Constrained Sampling
Institute of Science Tokyo, Tokyo, Japan · Tokyo University of Agriculture and Technology, Tokyo, Japan

Nov 5, 2026J/K move · Enter open · S save

CS-Pi: Constraint-Satisfying Flow Policy Sampling

Soumojit Bhattacharya, Oliver Kroemer, Shubham Tulsiani

Robotics Institute, Carnegie Mellon University

Constrained Sampling Robot Policy Learning Flow Matching for Action Generation Flow-Based Policy Learning

Open paper AskPDF arXiv

A flow-matching policy deployed in the field must often satisfy a constraint that was absent from its demonstrations, such as avoiding an obstacle it has never seen. Retraining for every new constraint is impractical, so the constraint must be enforced at inference time. Enforcing it must not discard what the policy learned: an action the policy would rarely sample may avoid the obstacle yet fail the task. We therefore want actions that are both safe, satisfying the constraint, and plausible, remaining likely under the policy. Gradient guidance, the most common approach, steers noisy states, so it must evaluate its cost on the policy's running estimate of the clean action; when the policy is uncertain between passing left or right of an obstacle, this estimate is their average and can pass straight through it. We instead build on rejection and projection. Rejection redraws actions until one is safe: every output is plausible, but the wait is intractable when safe actions are rare. Projection moves an action to the nearest safe one: it is efficient, but the result need not be plausible. Our key insight is that flow-matching sampling lets us combine the two, keeping projection's efficiency and rejection's plausibility. CS-Pi, our draw-project-renoise sampler, projects each draw to the nearest safe action, adds noise back scaled to how far the projection moved it, and re-runs the unmodified policy until a draw is safe. Replacing only the projection step extends CS-Pi to continuous costs. Across a 2D diagnostic, a 7-DoF shelf pick-and-place, an orientation preference, and a zero-shot Franka deployment, CS-Pi reaches 81% safe success on the shelf and 55% on hardware, against 55% and 40% for projection, while staying plausible.