Bag of Design Choices for Inference of High-Resolution Masked Generative Transformer

• URL: http://arxiv.org/abs/2411.10781v1
• Date: Sat, 16 Nov 2024 11:51:33 GMT
• Title: Bag of Design Choices for Inference of High-Resolution Masked Generative Transformer
• Abstract summary: Masked generative Transformer (MGT) serves as a promising intermediary between DM and autoregressive models (ARMs) We modify and re-design a set of DM-based inference techniques for MGT and further elucidate their performance on MGT. We achieve winning rates of approximately 70% compared to vanilla sampling on HPS v2 with the recent SOTA MGT Meissonic.
• Score: 20.145862858765245
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Text-to-image diffusion models (DMs) develop at an unprecedented pace, supported by thorough theoretical exploration and empirical analysis. Unfortunately, the discrepancy between DMs and autoregressive models (ARMs) complicates the path toward achieving the goal of unified vision and language generation. Recently, the masked generative Transformer (MGT) serves as a promising intermediary between DM and ARM by predicting randomly masked image tokens (i.e., masked image modeling), combining the efficiency of DM with the discrete token nature of ARM. However, we find that the comprehensive analyses regarding the inference for MGT are virtually non-existent, and thus we aim to present positive design choices to fill this gap. We modify and re-design a set of DM-based inference techniques for MGT and further elucidate their performance on MGT. We also discuss the approach to correcting token's distribution to enhance inference. Extensive experiments and empirical analyses lead to concrete and effective design choices, and these design choices can be merged to achieve further performance gains. For instance, in terms of enhanced inference, we achieve winning rates of approximately 70% compared to vanilla sampling on HPS v2 with the recent SOTA MGT Meissonic. Our contributions have the potential to further enhance the capabilities and future development of MGTs.

Related papers

• AffectAgent: Collaborative Multi-Agent Reasoning for Retrieval-Augmented Multimodal Emotion Recognition [62.16431420189863]
  LLM-based multimodal emotion recognition relies on static parametric memory and often hallucinates when interpreting nuanced affective states.<n>We introduce AffectAgent, an affect-oriented multi-agent retrieval-augmented generation framework.<n>AffectAgent comprises three jointly optimized agents, namely a query planner, an evidence filter, and an emotion generator.
  arXiv  Detail & Related papers  (2026-04-14T13:49:19Z)
• CREM: Compression-Driven Representation Enhancement for Multimodal Retrieval and Comprehension [49.6969505536365]
  We propose CREM, with a unified framework that enhances multimodal representations for retrieval while preserving generative ability.<n>CREM achieves state-of-the-art retrieval performance on MMEB while maintaining strong generative performance on multiple comprehension benchmarks.
  arXiv  Detail & Related papers  (2026-02-22T08:09:51Z)
• Co-GRPO: Co-Optimized Group Relative Policy Optimization for Masked Diffusion Model [74.99242687133408]
  Masked Diffusion Models (MDMs) have shown promising potential across vision, language, and cross-modal generation.<n>We introduce Co-GRPO, which reformulates MDM generation as a unified Markov Decision Process (MDP) that jointly incorporates both the model and the inference schedule.
  arXiv  Detail & Related papers  (2025-12-25T12:06:04Z)
• Demystifying MaskGIT Sampler and Beyond: Adaptive Order Selection in Masked Diffusion [41.409281069230325]
  Masked diffusion models have shown promising performance in generating high-quality samples in a wide range of domains.<n>This paper theoretically analyzes the MaskGIT sampler for image modeling, revealing its implicit temperature sampling mechanism.<n>We introduce the "moment sampler," which employs a "choose-then-sample" approach by selecting unmasking positions before sampling tokens.
  arXiv  Detail & Related papers  (2025-10-06T06:30:22Z)
• Reinforcing Multimodal Understanding and Generation with Dual Self-rewards [56.08202047680044]
  Large language models (LLMs) unify cross-model understanding and generation into a single framework.<n>Current solutions require external supervision (e.g., human feedback or reward models) and only address unidirectional tasks.<n>We introduce a self-supervised dual reward mechanism to reinforce the understanding and generation capabilities of LMMs.
  arXiv  Detail & Related papers  (2025-06-09T17:38:45Z)
• Error Analyses of Auto-Regressive Video Diffusion Models: A Unified Framework [127.61297651993561]
  A variety of Auto-Regressive Video Diffusion Models (ARVDM) have achieved remarkable successes in generating realistic long-form videos. We develop theoretical underpinnings for these models and use our insights to improve the performance of existing models.
  arXiv  Detail & Related papers  (2025-03-12T15:32:44Z)
• Progressive Multimodal Reasoning via Active Retrieval [64.74746997923967]
  Multi-step multimodal reasoning tasks pose significant challenges for large language models (MLLMs) We propose AR-MCTS, a universal framework designed to progressively improve the reasoning capabilities of MLLMs. We show that AR-MCTS can optimize sampling diversity and accuracy, yielding reliable multimodal reasoning.
  arXiv  Detail & Related papers  (2024-12-19T13:25:39Z)
• Efficient Generative Modeling with Residual Vector Quantization-Based Tokens [5.949779668853557]
  ResGen is an efficient Residual Vector Quantization-based generative model for high-fidelity generation with fast sampling.<n>We validate the efficacy and generalizability of the proposed method on two challenging tasks: conditional image generation on ImageNet 256x256 and zero-shot text-to-speech synthesis.<n>As we scale the depth of RVQ, our generative models exhibit enhanced generation fidelity or faster sampling speeds compared to similarly sized baseline models.
  arXiv  Detail & Related papers  (2024-12-13T15:31:17Z)
• 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)
• Masked Diffusion Models are Secretly Time-Agnostic Masked Models and Exploit Inaccurate Categorical Sampling [47.82616476928464]
  Masked diffusion models (MDMs) have emerged as a popular research topic for generative modeling of discrete data. We show that both training and sampling of MDMs are theoretically free from the time variable. We identify, for the first time, an underlying numerical issue, even with the commonly used 32-bit floating-point precision.
  arXiv  Detail & Related papers  (2024-09-04T17:48:19Z)
• Zero-Shot Embeddings Inform Learning and Forgetting with Vision-Language Encoders [6.7181844004432385]
  The Inter-Intra Modal Measure (IIMM) functions as a strong predictor of performance changes with fine-tuning. Fine-tuning on tasks with higher IIMM scores produces greater in-domain performance gains but also induces more severe out-of-domain performance degradation. With only a single forward pass of the target data, practitioners can leverage this key insight to evaluate the degree to which a model can be expected to improve following fine-tuning.
  arXiv  Detail & Related papers  (2024-07-22T15:35:09Z)
• Chain-of-Thought Prompting for Demographic Inference with Large Multimodal Models [58.58594658683919]
  Large multimodal models (LMMs) have shown transformative potential across various research tasks. Our findings indicate LMMs possess advantages in zero-shot learning, interpretability, and handling uncurated 'in-the-wild' inputs. We propose a Chain-of-Thought augmented prompting approach, which effectively mitigates the off-target prediction issue.
  arXiv  Detail & Related papers  (2024-05-24T16:26:56Z)
• DEEM: Diffusion Models Serve as the Eyes of Large Language Models for Image Perception [66.88792390480343]
  We propose DEEM, a simple but effective approach that utilizes the generative feedback of diffusion models to align the semantic distributions of the image encoder. DEEM exhibits enhanced robustness and a superior capacity to alleviate model hallucinations while utilizing fewer trainable parameters, less pre-training data, and a smaller base model size.
  arXiv  Detail & Related papers  (2024-05-24T05:46:04Z)
• Unchosen Experts Can Contribute Too: Unleashing MoE Models' Power by Self-Contrast [58.98411447739218]
  Mixture-of-Experts (MoE) has emerged as a prominent architecture for scaling model size while maintaining computational efficiency. We propose Self-Contrast Mixture-of-Experts (SCMoE), a training-free strategy that utilizes unchosen experts in a self-contrast manner during inference. Our method is conceptually simple and computationally lightweight, as it incurs minimal latency compared to greedy decoding.
  arXiv  Detail & Related papers  (2024-05-23T12:45:29Z)
• MIMIC: Mask Image Pre-training with Mix Contrastive Fine-tuning for Facial Expression Recognition [11.820043444385432]
  We introduce a novel FER training paradigm named Mask Image pre-training with MIx Contrastive fine-tuning (MIMIC) In the initial phase, we pre-train the ViT via masked image reconstruction on general images. In the fine-tuning stage, we introduce a mix-supervised contrastive learning process, which enhances the model with a more extensive range of positive samples.
  arXiv  Detail & Related papers  (2024-01-14T10:30:32Z)
• On the Robustness of Large Multimodal Models Against Image Adversarial Attacks [81.2935966933355]
  We study the impact of visual adversarial attacks on Large Multimodal Models (LMMs) We find that in general LMMs are not robust to visual adversarial inputs. We propose a new approach to real-world image classification which we term query decomposition.
  arXiv  Detail & Related papers  (2023-12-06T04:59:56Z)
• Diversifying the Mixture-of-Experts Representation for Language Models with Orthogonal Optimizer [59.43462055143123]
  The Mixture of Experts (MoE) has emerged as a highly successful technique in deep learning. In this study, we shed light on the homogeneous representation problem, wherein experts in the MoE fail to specialize and lack diversity. We propose an alternating training strategy that encourages each expert to update in a direction to the subspace spanned by other experts.
  arXiv  Detail & Related papers  (2023-10-15T07:20:28Z)
• Sampling From Autoencoders' Latent Space via Quantization And Probability Mass Function Concepts [1.534667887016089]
  We introduce a novel post-training sampling algorithm rooted in the concept of probability mass functions, coupled with a quantization process. Our proposed algorithm establishes a vicinity around each latent vector from the input data and then proceeds to draw samples from these defined neighborhoods. This strategic approach ensures that the sampled latent vectors predominantly inhabit high-probability regions, which, in turn, can be effectively transformed into authentic real-world images.
  arXiv  Detail & Related papers  (2023-08-21T13:18:12Z)
• VERITE: A Robust Benchmark for Multimodal Misinformation Detection Accounting for Unimodal Bias [17.107961913114778]
  multimodal misinformation is a growing problem on social media platforms. In this study, we investigate and identify the presence of unimodal bias in widely-used MMD benchmarks. We introduce a new method -- termed Crossmodal HArd Synthetic MisAlignment (CHASMA) -- for generating realistic synthetic training data.
  arXiv  Detail & Related papers  (2023-04-27T12:28:29Z)
• IMKGA-SM: Interpretable Multimodal Knowledge Graph Answer Prediction via Sequence Modeling [3.867363075280544]
  Multimodal knowledge graph link prediction aims to improve the accuracy and efficiency of link prediction tasks for multimodal data. New model is developed, namely Interpretable Multimodal Knowledge Graph Answer Prediction via Sequence Modeling (IMKGA-SM) Model achieves much better performance than SOTA baselines on multimodal link prediction datasets of different sizes.
  arXiv  Detail & Related papers  (2023-01-06T10:08:11Z)
• On Reinforcement Learning and Distribution Matching for Fine-Tuning Language Models with no Catastrophic Forgetting [5.5302127686575435]
  Two main paradigms have emerged to tackle this challenge: Reward Maximization (RM) and, more recently, Distribution Matching (DM) We show that methods such as KL-control developed for RM can also be construed as belonging to DM. We leverage connections between the two paradigms to import the concept of baseline into DM methods.
  arXiv  Detail & Related papers  (2022-06-01T20:54:41Z)
• Distributional Robustness with IPMs and links to Regularization and GANs [10.863536797169148]
  We study robustness via divergence-based uncertainty sets in machine learning. We extend our results to shed light on adversarial generative modelling via $f$-GANs.
  arXiv  Detail & Related papers  (2020-06-08T04:41:29Z)

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.