Discrete diffusion or flow models could enable faster and more controllable sequence
generation than autoregressive models. We show that na\" ive linear flow matching on the …

Protein design often begins with the knowledge of a desired function from a motif which motif-
scaffolding aims to construct a functional protein around. Recently, generative models have …

We introduce MusicFlow, a cascaded text-to-music generation model based on flow
matching. Based on self-supervised representations to bridge between text descriptions and …

Numerous biological and physical processes can be modeled as systems of interacting
entities evolving continuously over time, eg the dynamics of communicating cells or physical …

This paper introduces Bespoke Non-Stationary (BNS) Solvers, a solver distillation approach
to improve sample efficiency of Diffusion and Flow models. BNS solvers are based on a …

The task of conditional generation is one of the most important applications of generative
models, and numerous methods have been developed to date based on the celebrated flow …

Traditional methods for synthesizing 6-DoF grasp poses from 3D observations often rely on
geometric heuristics, resulting in poor generalizability, limited grasp options, and higher …

Recently, the application of diffusion models has facilitated the significant development of
speech and audio generation. Nevertheless, the quality of samples generated by diffusion …

We introduce Diffusion World Model (DWM), a conditional diffusion model capable of
predicting multistep future states and rewards concurrently. As opposed to traditional one …

Scaling text-to-speech (TTS) with autoregressive language model (LM) to large-scale
datasets by quantizing waveform into discrete speech tokens is making great progress to …