11 papers
Large Language Continuous Diffusion Models
Zhihan Yang, Wei Guo, Jean-Marie Lemercier +14
Despite the success of discrete diffusion language models (dLMs) for fast parallel decoding, their non-smooth, high-dimensional space hinders trajectory steering for reasoning and…
Scaling Reinforcement Learning for Diffusion Models via Velocity Matching
Jaemoo Choi, Wei Guo, Yuchen Zhu +4
Reward-based fine-tuning of diffusion models has largely inherited likelihood-based policy optimization developed for autoregressive large language models (LLMs). Diffusion models,…
Parallel Decoding Distillation for Fast Image and Video Generation
Neta Shaul, Chao Liu, Arash Vahdat +1
Generation in video diffusion or flow models is computationally expensive due to the slow and iterative sampling process. Current state-of-the-art (SOTA) acceleration methods heavi…
Tensor Train Diffusion: Leveraging Low-Rank Structures for High-Dimensional Score-Based Sampling
Robert Gruhlke, Julius Berner, David Sommer +1
Diffusion models offer a powerful framework for sampling from complex probability densities by learning to reverse a noising process. A common approach involves solving for the tim…
Flex-Forcing: Towards a Unified Autoregressive and Bidirectional Video Diffusion Model
Xinyin Ma, Julius Berner, Chao Liu +3
Recent progress in large-scale generative models has substantially advanced video generation, yet existing methods remain constrained by a rigid inference paradigm. Bidirectional d…
Variational Flow Maps: Make Some Noise for One-Step Conditional Generation
Abbas Mammadov, So Takao, Bohan Chen +4
Flow maps enable high-quality image generation in a single forward pass. However, unlike iterative diffusion models, their lack of an explicit sampling trajectory impedes incorpora…
Mode Seeking meets Mean Seeking for Fast Long Video Generation
Shengqu Cai, Weili Nie, Chao Liu +8
Scaling video generation from seconds to minutes faces a critical bottleneck: while short-video data is abundant and high-fidelity, coherent long-form data is scarce and limited to…
Transition Matching Distillation for Fast Video Generation
Weili Nie, Julius Berner, Nanye Ma +3
Large video diffusion and flow models have achieved remarkable success in high-quality video generation, but their use in real-time interactive applications remains limited due to…
Trust Region Constrained Measure Transport in Path Space for Stochastic Optimal Control and Inference
Denis Blessing, Julius Berner, Lorenz Richter +4
Solving stochastic optimal control problems with quadratic control costs can be viewed as approximating a target path space measure, e.g. via gradient-based optimization. In practi…
Underdamped Diffusion Bridges with Applications to Sampling
Denis Blessing, Julius Berner, Lorenz Richter +1
We provide a general framework for learning diffusion bridges that transport prior to target distributions. It includes existing diffusion models for generative modeling, but also…
From discrete-time policies to continuous-time diffusion samplers: Asymptotic equivalences and faster training
Julius Berner, Lorenz Richter, Marcin Sendera +2
We study the problem of training neural stochastic differential equations, or diffusion models, to sample from a Boltzmann distribution without access to target samples. Existing m…