paper-with-me

Papers

M2T: Masking Transformers Twice for Faster Decoding

2023-04-14 · ICCV 2023 1 · Fabian Mentzer, Eirikur Agustsson, Michael Tschannen

We show how bidirectional transformers trained for masked token prediction can be applied to neural image compression to achieve state-of-the-art results. Such models were previously used for image generation by progressivly sampling groups of masked tokens according to uncertainty-adaptive schedules. Unlike these works, we demonstrate that predefined, deterministic schedules perform as well or better for image compression. This insight allows us to use masked attention during training in addition to masked inputs, and activation caching during inference, to significantly speed up our models (~4 higher inference speed) at a small increase in bitrate.

📄 PDF Abstract BibTeX arXiv:2304.07313

Code (0)

등록된 구현이 없습니다.

Tasks

Image CompressionImage Generation

Methods 이 논문이 사용한 방법론

SPEED The monocular depth estimation (MDE) is the task of estimating depth from a single frame. This information is an essential knowledge in many computer vision tasks such as scene…

Similar Papers 제목 키워드 기반

UNCAGE: Contrastive Attention Guidance for Masked Generative Transformers in Text-to-Image Generation

2025-08-07 · Wonjun Kang, Byeongkeun Ahn, Minjae Lee, Kevin Galim 외 arxiv

Text-to-image (T2I) generation has been actively studied using Diffusion Models and Autoregressive Models. Recently, Masked Generative Transformers have gained attention as an alternative to Autoregressive Models to over…

Text-to-Image Generation

SMELT: Scaling Laws for Compute-Matched MoE Looped Transformers

2026-09-01 · Shaowen Wang, Ge Zhang, Kairong Luo, Yuhao Wu 외 hf

Looped Transformers increase effective depth by iterating a shared block of layers, but most evaluations compare at fixed model size, conflating architectural advantage with extra FLOPs. We study looping on Mixture-of-Ex…

Re-evaluating Confidence Remasking in Masked Diffusion Language Models

2026-06-10 · Stipe Frkovic, Metod Jazbec, Dan Zhang, Christian A. Naesseth 외 arxiv

Masked diffusion language models (dLLMs) have recently emerged as a competitive alternative to autoregressive language models, with the promise of faster inference via parallel token generation. A notable limitation of t…

Fast Inference from Transformers via Speculative Decoding

2022-11-30 · Yaniv Leviathan, Matan Kalman, Yossi Matias

Inference from large autoregressive models like Transformers is slow - decoding K tokens takes K serial runs of the model. In this work we introduce speculative decoding - an algorithm to sample from autoregressive model…

Language ModelingLanguage Modelling

Decoding billions of integers per second through vectorization

2012-09-10 · Daniel Lemire, Leonid Boytsov

In many important applications -- such as search engines and relational database systems -- data is stored in the form of arrays of integers. Encoding and, most importantly, decoding of these arrays consumes considerable…

CPU