paper-with-me

홈 › Papers

Quantization-Free Autoregressive Action Transformer

2025-03-18 · Ziyad Sheebaelhamd, Michael Tschannen, Michael Muehlebach, Claire Vernade

Current transformer-based imitation learning approaches introduce discrete action representations and train an autoregressive transformer decoder on the resulting latent code. However, the initial quantization breaks the continuous structure of the action space thereby limiting the capabilities of the generative model. We propose a quantization-free method instead that leverages Generative Infinite-Vocabulary Transformers (GIVT) as a direct, continuous policy parametrization for autoregressive transformers. This simplifies the imitation learning pipeline while achieving state-of-the-art performance on a variety of popular simulated robotics tasks. We enhance our policy roll-outs by carefully studying sampling algorithms, further improving the results.

📄 PDF Abstract BibTeX arXiv:2503.14259

Code (1)

ziyadsheeba/qfat 공식 구현

Tasks

Imitation LearningQuantizationSequential Decision Making

Similar Papers 제목 키워드 기반

Understanding Behavior Cloning with Action Quantization

2026-03-20 · Haoqun Cao, Tengyang Xie arxiv

Behavior cloning is a fundamental paradigm in machine learning, enabling policy learning from expert demonstrations across robotics, autonomous driving, and generative models. Autoregressive models like transformer have …

Continuous ControlAutonomous Driving

HiFlow: Tokenization-Free Scale-Wise Autoregressive Policy Learning via Flow Matching

2026-03-28 · Daichi Yashima, Koki Seno, Shuhei Kurita, Yusuke Oda 외 arxiv

Coarse-to-fine autoregressive modeling has recently shown strong promise for visuomotor policy learning, combining the inference efficiency of autoregressive methods with the global trajectory coherence of diffusion-base…

Image Generation

Towards Accurate Image Coding: Improved Autoregressive Image Generation with Dynamic Vector Quantization

2023-05-19 · CVPR 2023 1 · Mengqi Huang, Zhendong Mao, Zhuowei Chen, Yongdong Zhang

Existing vector quantization (VQ) based autoregressive models follow a two-stage generation paradigm that first learns a codebook to encode images as discrete codes, and then completes generation based on the learned cod…

Image GenerationPositionQuantization

Autoregressive Image Generation using Residual Quantization

2022-03-03 · CVPR 2022 1 · Doyup Lee, Chiheon Kim, Saehoon Kim, Minsu Cho 외

For autoregressive (AR) modeling of high-resolution images, vector quantization (VQ) represents an image as a sequence of discrete codes. A short sequence length is important for an AR model to reduce its computational c…

Conditional Image GenerationImage GenerationImage ReconstructionQuantization+1

Closing the Dequantization Gap: PixelCNN as a Single-Layer Flow

2020-02-06 · NeurIPS 2020 12 · Didrik Nielsen, Ole Winther

Flow models have recently made great progress at modeling ordinal discrete data such as images and audio. Due to the continuous nature of flow models, dequantization is typically applied when using them for such discrete…