[MASK] is All You Need

• URL: http://arxiv.org/abs/2412.06787v2
• Date: Tue, 10 Dec 2024 14:09:22 GMT
• Title: [MASK] is All You Need
• Authors: Vincent Tao Hu, Björn Ommer,
• Abstract summary: We propose using discrete-state models to connect Masked Generative and Non-autoregressive Diffusion models. By leveraging [MASK] in discrete-state models, we can bridge Masked Generative and Non-autoregressive Diffusion models.
• Score: 28.90875822599164
• License:
• Abstract: In generative models, two paradigms have gained attraction in various applications: next-set prediction-based Masked Generative Models and next-noise prediction-based Non-Autoregressive Models, e.g., Diffusion Models. In this work, we propose using discrete-state models to connect them and explore their scalability in the vision domain. First, we conduct a step-by-step analysis in a unified design space across two types of models including timestep-independence, noise schedule, temperature, guidance strength, etc in a scalable manner. Second, we re-cast typical discriminative tasks, e.g., image segmentation, as an unmasking process from [MASK] tokens on a discrete-state model. This enables us to perform various sampling processes, including flexible conditional sampling by only training once to model the joint distribution. All aforementioned explorations lead to our framework named Discrete Interpolants, which enables us to achieve state-of-the-art or competitive performance compared to previous discrete-state based methods in various benchmarks, like ImageNet256, MS COCO, and video dataset FaceForensics. In summary, by leveraging [MASK] in discrete-state models, we can bridge Masked Generative and Non-autoregressive Diffusion models, as well as generative and discriminative tasks.

Related papers

• Steering Masked Discrete Diffusion Models via Discrete Denoising Posterior Prediction [88.65168366064061]
  We introduce Discrete Denoising Posterior Prediction (DDPP), a novel framework that casts the task of steering pre-trained MDMs as a problem of probabilistic inference. Our framework leads to a family of three novel objectives that are all simulation-free, and thus scalable. We substantiate our designs via wet-lab validation, where we observe transient expression of reward-optimized protein sequences.
  arXiv  Detail & Related papers  (2024-10-10T17:18:30Z)
• EMR-Merging: Tuning-Free High-Performance Model Merging [55.03509900949149]
  We show that Elect, Mask & Rescale-Merging (EMR-Merging) shows outstanding performance compared to existing merging methods. EMR-Merging is tuning-free, thus requiring no data availability or any additional training while showing impressive performance.
  arXiv  Detail & Related papers  (2024-05-23T05:25:45Z)
• On the Efficient Marginalization of Probabilistic Sequence Models [3.5897534810405403]
  This dissertation focuses on using autoregressive models to answer complex probabilistic queries. We develop a class of novel and efficient approximation techniques for marginalization in sequential models that are model-agnostic.
  arXiv  Detail & Related papers  (2024-03-06T19:29:08Z)
• Synthetic location trajectory generation using categorical diffusion models [50.809683239937584]
  Diffusion models (DPMs) have rapidly evolved to be one of the predominant generative models for the simulation of synthetic data. We propose using DPMs for the generation of synthetic individual location trajectories (ILTs) which are sequences of variables representing physical locations visited by individuals.
  arXiv  Detail & Related papers  (2024-02-19T15:57:39Z)
• Predict, Refine, Synthesize: Self-Guiding Diffusion Models for Probabilistic Time Series Forecasting [10.491628898499684]
  We propose TSDiff, an unconditionally-trained diffusion model for time series. Our proposed self-guidance mechanism enables conditioning TSDiff for downstream tasks during inference, without requiring auxiliary networks or altering the training procedure. We demonstrate the effectiveness of our method on three different time series tasks: forecasting, refinement, and synthetic data generation.
  arXiv  Detail & Related papers  (2023-07-21T10:56:36Z)
• A Class of Two-Timescale Stochastic EM Algorithms for Nonconvex Latent Variable Models [21.13011760066456]
  The Expectation-Maximization (EM) algorithm is a popular choice for learning variable models. In this paper, we propose a general class of methods called Two-Time Methods.
  arXiv  Detail & Related papers  (2022-03-18T22:46:34Z)
• Oops I Took A Gradient: Scalable Sampling for Discrete Distributions [53.3142984019796]
  We show that this approach outperforms generic samplers in a number of difficult settings. We also demonstrate the use of our improved sampler for training deep energy-based models on high dimensional discrete data.
  arXiv  Detail & Related papers  (2021-02-08T20:08:50Z)
• Conditional Generative Models for Counterfactual Explanations [0.0]
  We propose a general framework to generate sparse, in-distribution counterfactual model explanations. The framework is flexible with respect to the type of generative model used as well as the task of the underlying predictive model.
  arXiv  Detail & Related papers  (2021-01-25T14:31:13Z)
• Improving the Reconstruction of Disentangled Representation Learners via Multi-Stage Modeling [54.94763543386523]
  Current autoencoder-based disentangled representation learning methods achieve disentanglement by penalizing the ( aggregate) posterior to encourage statistical independence of the latent factors. We present a novel multi-stage modeling approach where the disentangled factors are first learned using a penalty-based disentangled representation learning method. Then, the low-quality reconstruction is improved with another deep generative model that is trained to model the missing correlated latent variables.
  arXiv  Detail & Related papers  (2020-10-25T18:51:15Z)
• Deep Neural Dynamic Bayesian Networks applied to EEG sleep spindles modeling [0.0]
  We propose a generative model for single-channel EEG that incorporates the constraints experts actively enforce during visual scoring. We derive algorithms for exact, tractable inference as a special case of Generalized Expectation Maximization. We validate the model on three public datasets and provide support that more complex models are able to surpass state-of-the-art detectors.
  arXiv  Detail & Related papers  (2020-10-16T21:48:29Z)
• Robust Finite Mixture Regression for Heterogeneous Targets [70.19798470463378]
  We propose an FMR model that finds sample clusters and jointly models multiple incomplete mixed-type targets simultaneously. We provide non-asymptotic oracle performance bounds for our model under a high-dimensional learning framework. The results show that our model can achieve state-of-the-art performance.
  arXiv  Detail & Related papers  (2020-10-12T03:27:07Z)

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.