相关论文: Guided Streaming Stochastic Interpolant Policy

We consider the problem of estimating a linear time-invariant (LTI) dynamical system from a single trajectory via streaming algorithms, which is encountered in several applications including reinforcement learning (RL) and time-series…

Offline reinforcement learning methods typically enforce strict constraints to ensure safety; yet this rigidity often prevents the discovery of optimal behaviors outside the immediate support of the behavior policy. To address this, we…

Stochastic gradient descent (SGD) is a powerful optimization technique that is particularly useful in online learning scenarios. Its convergence analysis is relatively well understood under the assumption that the data samples are…

Instructional video generation is an emerging task that aims to synthesize coherent demonstrations of procedural activities from textual descriptions. Such capability has broad implications for content creation, education, and human-AI…

This paper addresses stochastic optimization in a streaming setting with time-dependent and biased gradient estimates. We analyze several first-order methods, including Stochastic Gradient Descent (SGD), mini-batch SGD, and time-varying…

Diffusion- and flow-based policies deliver state-of-the-art performance on long-horizon robotic manipulation and imitation learning tasks. However, these controllers employ a fixed inference budget at every control step, regardless of task…

Robot motion distributions often exhibit multi-modality and require flexible generative models for accurate representation. Streaming Flow Policies (SFPs) have recently emerged as a powerful paradigm for generating robot trajectories by…

A class of generative models that unifies flow-based and diffusion-based methods is introduced. These models extend the framework proposed in Albergo and Vanden-Eijnden (2023), enabling the use of a broad class of continuous-time stochastic…

We introduce a streaming framework for analyzing stochastic approximation/optimization problems. This streaming framework is analogous to solving optimization problems using time-varying mini-batches that arrive sequentially. We provide…

Generative robot policies such as Flow Matching offer flexible, multi-modal policy learning but are sample-inefficient. Although object-centric policies improve sample efficiency, it does not resolve this limitation. In this work, we…

We propose a conditional stochastic interpolation (CSI) method for learning conditional distributions. CSI is based on estimating probability flow equations or stochastic differential equations that transport a reference distribution to the…

Many deployed learning systems must update models on streaming data under memory constraints. The default strategy, sequential fine-tuning on each new phase, is architecture-agnostic but often suffers catastrophic forgetting when later…

Real-time Video Frame Interpolation (VFI) has long been dominated by flow-based methods like RIFE, which offer high throughput but often fail in complicated scenarios involving large motion and occlusion. Conversely, recent diffusion-based…

Temporal point processes have been widely applied to model event sequence data generated by online users. In this paper, we consider the problem of how to design the optimal control policy for point processes, such that the stochastic…

Projection-based model reduction enables efficient simulation of complex dynamical systems by constructing low-dimensional surrogate models from high-dimensional data. The Operator Inference (OpInf) approach learns such reduced surrogate…

A streaming algorithm to compute the spectral proper orthogonal decomposition (SPOD) of stationary random processes is presented. As new data becomes available, an incremental update of the truncated eigenbasis of the estimated…

We introduce Guided Harmonic Path-Integral Diffusion (GH-PID), a linearly-solvable framework for guided Stochastic Optimal Transport (SOT) with a hard terminal distribution and soft, application-driven path costs. A low-dimensional guidance…

Transport-based methods have emerged as a leading paradigm for building generative models from large, clean datasets. However, in many scientific and engineering domains, clean data are often unavailable: instead, we only observe…

Over the last few years, sampling-based stochastic optimal control (SOC) frameworks have shown impressive performances in reinforcement learning (RL) with applications in robotics. However, such approaches require a large amount of samples…

This paper considers optimal control of dynamical systems which are represented by nonlinear stochastic differential equations. It is well-known that the optimal control policy for this problem can be obtained as a function of a value…