Related papers: SnapFlow: One-Step Action Generation for Flow-Matc…
Recent Vision-Language-Action (VLA) models have shown impressive flexibility and generalization, yet their deployment in robotic manipulation remains limited by heavy computational overhead and inference latency. In this work, we present…
In voice conversion (VC) applications, diffusion and flow-matching models have exhibited exceptional speech quality and speaker similarity performances. However, they are limited by slow conversion owing to their iterative inference.…
Normalizing Flows (NFs) learn invertible mappings between the data and a Gaussian distribution. Prior works usually suffer from two limitations. First, they add random noise to training samples or VAE latents as data augmentation,…
Denoising-based models, such as diffusion and flow matching, have been a critical component of robotic manipulation for their strong distribution-fitting and scaling capacity. Concurrently, several works have demonstrated that simple…
We propose Flow-GRPO, the first method to integrate online policy gradient reinforcement learning (RL) into flow matching models. Our approach uses two key strategies: (1) an ODE-to-SDE conversion that transforms a deterministic Ordinary…
Rectified flow models have become a de facto standard in image generation due to their stable sampling trajectories and high-fidelity outputs. Despite their strong generative capabilities, they face critical limitations in image editing…
Diffusion Models (DMs) have achieved great success in image generation and other fields. By fine sampling through the trajectory defined by the SDE/ODE solver based on a well-trained score model, DMs can generate remarkable high-quality…
A key challenge in synthesizing audios from silent videos is the inherent trade-off between synthesis quality and inference efficiency in existing methods. For instance, flow matching based models rely on modeling instantaneous velocity,…
Diffusion models have achieved significant progress in both image and video generation while still suffering from huge computation costs. As an effective solution, flow matching aims to reflow the diffusion process of diffusion models into…
Language models based on discrete diffusion have attracted widespread interest for their potential to provide faster generation than autoregressive models. Despite their promise, these models typically produce samples whose quality sharply…
The growing demand for real-time robotic deployment necessitates fast and on-device inference for vision-language-action (VLA) models. Within the VLA literature, efficiency has been extensively studied at the token level, such as visual…
Diffusion models have significantly advanced the state of the art in image, audio, and video generation tasks. However, their applications in practical scenarios are hindered by slow inference speed. Drawing inspiration from the…
Vision-language-action (VLA) models have recently emerged as a powerful paradigm for building generalist robots. However, traditional VLA models that generate actions through flow matching (FM) typically rely on rigid and uniform time…
Flow matching has emerged as a competitive framework for learning high-quality generative policies in robotics; however, we find that generalisation arises and saturates early along the flow trajectory, in accordance with recent findings in…
Multistep inference is a bottleneck for real-time generative speech enhancement because flow- and diffusion-based systems learn an instantaneous velocity field and therefore rely on iterative ordinary differential equation (ODE) solvers. We…
Vision-language-action (VLA) models aim to understand natural language instructions and visual observations and to execute corresponding actions as an embodied agent. Recent work integrates future images into the understanding-acting loop,…
We present NextFlow, a unified decoder-only autoregressive transformer trained on 6 trillion interleaved text-image discrete tokens. By leveraging a unified vision representation within a unified autoregressive architecture, NextFlow…
In recent years, Vision-Language-Action (VLA) models have become a vital research direction in robotics due to their impressive multimodal understanding and generalization capabilities. Despite the progress, their practical deployment is…
Recent hybrid video generation models combine autoregressive temporal dynamics with diffusion-based spatial denoising, but their sequential, iterative nature leads to error accumulation and long inference times. In this work, we propose a…
Flow-based vision-language-action (VLA) models excel in embodied control but suffer from intractable likelihoods during multi-step sampling, hindering online reinforcement learning. We propose \textbf{\textit{$\boldsymbol{\pi}$-StepNFT}}…