Related papers: Trajectory-Consistent Flow Matching for Robust Vis…
We present a framework for assistive robot manipulation, which focuses on two fundamental challenges: first, efficiently adapting large-scale models to downstream scene affordance understanding tasks, especially in daily living scenarios…
Generative manipulation policies can fail catastrophically under deployment-time distribution shift, yet many failures are near-misses: the robot reaches almost-correct poses and would succeed with a small corrective motion. We propose…
Reinforcement Fine-Tuning (RFT) on flow-based models is crucial for preference alignment. However, they often introduce visual hallucinations like over-optimized details and semantic misalignment. This work preliminarily explores why visual…
Learning-based optical flow estimation has been dominated with the pipeline of cost volume with convolutions for flow regression, which is inherently limited to local correlations and thus is hard to address the long-standing challenge of…
Safety validation for Level 4 autonomous vehicles (AVs) is currently bottlenecked by the inability to scale the detection of rare, high-risk long-tail scenarios using traditional rule-based heuristics. We present Deep-Flow, an unsupervised…
We introduce Riemannian Flow Matching Policies (RFMP), a novel model for learning and synthesizing robot visuomotor policies. RFMP leverages the efficient training and inference capabilities of flow matching methods. By design, RFMP…
Generating high-quality time-series data is challenging because real-world signals often exhibit multimodal patterns and multiscale dynamics, including oscillations and high-frequency variations. Flow Matching (FM) offers an efficient…
Over the several recent years, there has been a boom in development of Flow Matching (FM) methods for generative modeling. One intriguing property pursued by the community is the ability to learn flows with straight trajectories which…
Few-shot imitation learning relies on only a small amount of task-specific demonstrations to efficiently adapt a policy for a given downstream tasks. Retrieval-based methods come with a promise of retrieving relevant past experiences to…
Most end-to-end Multi-Object Tracking (MOT) methods face the problems of low accuracy and poor generalization ability. Although traditional filter-based methods can achieve better results, they are difficult to be endowed with optimal…
Flow matching has recently emerged as a promising alternative to diffusion-based generative models, offering faster sampling and simpler training by learning continuous flows governed by ordinary differential equations. Despite growing…
Scene flow estimation is a crucial component in the development of autonomous driving and 3D robotics, providing valuable information for environment perception and navigation. Despite the advantages of learning-based scene flow estimation…
We propose ReinFlow, a simple yet effective online reinforcement learning (RL) framework that fine-tunes a family of flow matching policies for continuous robotic control. Derived from rigorous RL theory, ReinFlow injects learnable noise…
Training data is a critical requirement for machine learning tasks, and labeled training data can be expensive to acquire, often requiring manual or semi-automated data collection pipelines. For tracking applications, the data collection…
Robotic manipulation requires policies that are smooth and responsive to evolving observations. However, synchronous inference in the raw action space introduces several challenges, including intra-chunk jitter, inter-chunk discontinuities,…
Unconditional flow-matching trains diffusion models to transport samples from a source distribution to a target distribution by enforcing that the flows between sample pairs are unique. However, in conditional settings (e.g.,…
The use of guidance to steer sampling toward desired outcomes has been widely explored within diffusion models, especially in applications such as image and trajectory generation. However, incorporating guidance during training remains…
Traditional discriminative computer vision relies predominantly on static projections, mapping input features to outputs in a single computational step. Although efficient, this paradigm lacks the iterative refinement and robustness…
Imposing consistency through proxy tasks has been shown to enhance data-driven learning and enable self-supervision in various tasks. This paper introduces novel and effective consistency strategies for optical flow estimation, a problem…
Flow matching generates data by integrating a learned velocity field, where the number of integration steps (NFE) directly determines inference cost. We analyze which properties of the velocity field govern integration error by decomposing…