Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion

• URL: http://arxiv.org/abs/2407.01392v3
• Date: Thu, 4 Jul 2024 04:51:10 GMT
• Title: Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion
• Authors: Boyuan Chen, Diego Marti Monso, Yilun Du, Max Simchowitz, Russ Tedrake, Vincent Sitzmann,
• Abstract summary: Diffusion Forcing is a new training paradigm where a diffusion model is trained to denoise a set of tokens with independent per-token noise levels. We apply Diffusion Forcing to sequence generative modeling by training a causal next-token prediction model to generate one or several future tokens.
• Score: 61.03681839276652
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: This paper presents Diffusion Forcing, a new training paradigm where a diffusion model is trained to denoise a set of tokens with independent per-token noise levels. We apply Diffusion Forcing to sequence generative modeling by training a causal next-token prediction model to generate one or several future tokens without fully diffusing past ones. Our approach is shown to combine the strengths of next-token prediction models, such as variable-length generation, with the strengths of full-sequence diffusion models, such as the ability to guide sampling to desirable trajectories. Our method offers a range of additional capabilities, such as (1) rolling-out sequences of continuous tokens, such as video, with lengths past the training horizon, where baselines diverge and (2) new sampling and guiding schemes that uniquely profit from Diffusion Forcing's variable-horizon and causal architecture, and which lead to marked performance gains in decision-making and planning tasks. In addition to its empirical success, our method is proven to optimize a variational lower bound on the likelihoods of all subsequences of tokens drawn from the true joint distribution. Project website: https://boyuan.space/diffusion-forcing

Related papers

• Faster Language Models with Better Multi-Token Prediction Using Tensor Decomposition [5.575078692353885]
  We propose a new model for multi-token prediction in transformers, aiming to enhance sampling efficiency without compromising accuracy. By generalizing it to a rank-$r$ canonical probability decomposition, we develop an improved model that predicts multiple tokens simultaneously.
  arXiv  Detail & Related papers  (2024-10-23T11:06:36Z)
• Constrained Diffusion Models via Dual Training [80.03953599062365]
  Diffusion processes are prone to generating samples that reflect biases in a training dataset. We develop constrained diffusion models by imposing diffusion constraints based on desired distributions. We show that our constrained diffusion models generate new data from a mixture data distribution that achieves the optimal trade-off among objective and constraints.
  arXiv  Detail & Related papers  (2024-08-27T14:25:42Z)
• Non-autoregressive Sequence-to-Sequence Vision-Language Models [63.77614880533488]
  We propose a parallel decoding sequence-to-sequence vision-language model that marginalizes over multiple inference paths in the decoder. The model achieves performance on-par with its state-of-the-art autoregressive counterpart, but is faster at inference time.
  arXiv  Detail & Related papers  (2024-03-04T17:34:59Z)
• Guided Diffusion from Self-Supervised Diffusion Features [49.78673164423208]
  Guidance serves as a key concept in diffusion models, yet its effectiveness is often limited by the need for extra data annotation or pretraining. We propose a framework to extract guidance from, and specifically for, diffusion models.
  arXiv  Detail & Related papers  (2023-12-14T11:19:11Z)
• Bayesian Flow Networks [4.585102332532472]
  This paper introduces Bayesian Flow Networks (BFNs), a new class of generative model in which the parameters of a set of independent distributions are modified with Bayesian inference. Starting from a simple prior and iteratively updating the two distributions yields a generative procedure similar to the reverse process of diffusion models. BFNs achieve competitive log-likelihoods for image modelling on dynamically binarized MNIST and CIFAR-10, and outperform all known discrete diffusion models on the text8 character-level language modelling task.
  arXiv  Detail & Related papers  (2023-08-14T09:56:35Z)
• Latent Autoregressive Source Separation [5.871054749661012]
  This paper introduces vector-quantized Latent Autoregressive Source Separation (i.e., de-mixing an input signal into its constituent sources) without requiring additional gradient-based optimization or modifications of existing models. Our separation method relies on the Bayesian formulation in which the autoregressive models are the priors, and a discrete (non-parametric) likelihood function is constructed by performing frequency counts over latent sums of addend tokens.
  arXiv  Detail & Related papers  (2023-01-09T17:32:00Z)
• Truncated Diffusion Probabilistic Models and Diffusion-based Adversarial Auto-Encoders [137.1060633388405]
  Diffusion-based generative models learn how to generate the data by inferring a reverse diffusion chain. We propose a faster and cheaper approach that adds noise not until the data become pure random noise. We show that the proposed model can be cast as an adversarial auto-encoder empowered by both the diffusion process and a learnable implicit prior.
  arXiv  Detail & Related papers  (2022-02-19T20:18:49Z)
• Parameter Decoupling Strategy for Semi-supervised 3D Left Atrium Segmentation [0.0]
  We present a novel semi-supervised segmentation model based on parameter decoupling strategy to encourage consistent predictions from diverse views. Our method has achieved a competitive result over the state-of-the-art semisupervised methods on the Atrial Challenge dataset.
  arXiv  Detail & Related papers  (2021-09-20T14:51:42Z)
• Symbolic Music Generation with Diffusion Models [4.817429789586127]
  We present a technique for training diffusion models on sequential data by parameterizing the discrete domain in the continuous latent space of a pre-trained variational autoencoder. We show strong unconditional generation and post-hoc conditional infilling results compared to autoregressive language models operating over the same continuous embeddings.
  arXiv  Detail & Related papers  (2021-03-30T05:48:05Z)
• Haar Wavelet based Block Autoregressive Flows for Trajectories [129.37479472754083]
  Prediction of trajectories such as that of pedestrians is crucial to the performance of autonomous agents. We introduce a novel Haar wavelet based block autoregressive model leveraging split couplings. We illustrate the advantages of our approach for generating diverse and accurate trajectories on two real-world datasets.
  arXiv  Detail & Related papers  (2020-09-21T13:57:10Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.