Related papers: FlowRetrieval: Flow-Guided Data Retrieval for Few-…

The wide application of flow-matching methods has greatly promoted the development of robot imitation learning. However, these methods all face the problem of high inference time. To address this issue, researchers have proposed…

Visual imitation learning provides a framework for learning complex manipulation behaviors by leveraging human demonstrations. However, current interfaces for imitation such as kinesthetic teaching or teleoperation prohibitively restrict…

High-frequency trading (HFT) is an investing strategy that continuously monitors market states and places bid and ask orders at millisecond speeds. Traditional HFT approaches fit models with historical data and assume that future market…

Post-training of flow matching models-aligning the output distribution with a high-quality target-is mathematically equivalent to imitation learning. While Supervised Fine-Tuning mimics expert demonstrations effectively, it cannot correct…

Point clouds are a widely available and canonical data modality which convey the 3D geometry of a scene. Despite significant progress in classification and segmentation from point clouds, policy learning from such a modality remains…

We present FlowLM, a flow matching language model transformed from pre-trained diffusion language models via efficient fine-tuning. By re-aligning the curved sampling trajectories of diffusion models into straight-line flows, FlowLM enables…

Feature matching across video streams remains a cornerstone challenge in computer vision. Increasingly, robust multimodal matching has garnered interest in robotics, surveillance, remote sensing, and medical imaging. While traditional rely…

While generative modeling has achieved remarkable success on tasks like natural language-conditioned image generation, enabling model adaptation from example data points remains a relatively underexplored and challenging problem. To this…

Building on the success of diffusion models in visual generation, flow-based models reemerge as another prominent family of generative models that have achieved competitive or better performance in terms of both visual quality and inference…

In reinforcement learning and imitation learning, an object of central importance is the state distribution induced by the policy. It plays a crucial role in the policy gradient theorem, and references to it--along with the related…

Learning a generalizable bimanual manipulation policy is extremely challenging for embodied agents due to the large action space and the need for coordinated arm movements. Existing approaches rely on Vision-Language-Action (VLA) models to…

With the success of flow matching in visual generation, sampling efficiency remains a critical bottleneck for its practical application. Among flow models' accelerating methods, ReFlow has been somehow overlooked although it has theoretical…

Despite tremendous recent progress, Flow Matching methods still suffer from exposure bias due to discrepancies in training and inference. This paper investigates the root causes of exposure bias in Flow Matching, including: (1) the model…

Image retrieval is the task of finding images in a database that are most similar to a given query image. The performance of an image retrieval pipeline depends on many training-time factors, including the embedding model architecture, loss…

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…

Few-shot Learning aims to learn and distinguish new categories with a very limited number of available images, presenting a significant challenge in the realm of deep learning. Recent researchers have sought to leverage the additional…

Diffusion-based unsupervised image registration has been explored for cardiac cine MR, but expensive multi-step inference limits practical use. We propose FlowReg, a flow-matching framework in displacement field space that achieves strong…

Few-step diffusion or flow-based generative models typically distill a velocity-predicting teacher into a student that predicts a shortcut towards denoised data. This format mismatch has led to complex distillation procedures that often…

Offline reinforcement learning often relies on behavior regularization that enforces policies to remain close to the dataset distribution. However, such approaches fail to distinguish between high-value and low-value actions in their…

The focus of recent meta-learning research has been on the development of learning algorithms that can quickly adapt to test time tasks with limited data and low computational cost. Few-shot learning is widely used as one of the standard…