paper-with-me

Papers

Probability Distributions Computed by Autoregressive Transformers

2025-10-31 · Andy Yang, Anej Svete, Jiaoda Li, Anthony Widjaja Lin, Jonathan Rawski, Ryan Cotterell, David Chiang arxiv

Most expressivity results for transformers treat them as language recognizers -- devices that accept or reject strings -- rather than as they are used in practice: as language models that generate strings autoregressively and probabilistically. We characterize the probability distributions that transformer language models can express. We show that making transformer language recognizers autoregressive can sometimes increase their expressivity, and that making them probabilistic can break equivalences that hold in the non-probabilistic case. Our overall contribution is to tease apart what functions transformers are capable of expressing in their most common use case as language models.

📄 PDF Abstract BibTeX arXiv:2510.27118

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Autoregressive Score Matching

2020-10-24 · NeurIPS 2020 12 · Chenlin Meng, Lantao Yu, Yang song, Jiaming Song 외

Autoregressive models use chain rule to define a joint probability distribution as a product of conditionals. These conditionals need to be normalized, imposing constraints on the functional families that can be used. To…

DenoisingDensity EstimationImage DenoisingImage Generation

Axial Attention in Multidimensional Transformers

2019-12-20 · Jonathan Ho, Nal Kalchbrenner, Dirk Weissenborn, Tim Salimans

We propose Axial Transformers, a self-attention-based autoregressive model for images and other data organized as high dimensional tensors. Existing autoregressive models either suffer from excessively large computationa…

Image Generation

Diverse Image Inpainting with Bidirectional and Autoregressive Transformers

2021-04-26 · Yingchen Yu, Fangneng Zhan, Rongliang Wu, Jianxiong Pan 외

Image inpainting is an underdetermined inverse problem, which naturally allows diverse contents to fill up the missing or corrupted regions realistically. Prevalent approaches using convolutional neural networks (CNNs) c…

DiversityImage InpaintingLanguage ModelingLanguage Modelling

TCR-GPT: Integrating Autoregressive Model and Reinforcement Learning for T-Cell Receptor Repertoires Generation

2024-08-02 · Yicheng Lin, Dandan Zhang, Yun Liu

T-cell receptors (TCRs) play a crucial role in the immune system by recognizing and binding to specific antigens presented by infected or cancerous cells. Understanding the sequence patterns of TCRs is essential for deve…

DecoderReinforcement Learning (RL)

Neural Autoregressive Flows

2018-04-03 · ICML 2018 7 · Chin-wei Huang, David Krueger, Alexandre Lacoste, Aaron Courville

Normalizing flows and autoregressive models have been successfully combined to produce state-of-the-art results in density estimation, via Masked Autoregressive Flows (MAF), and to accelerate state-of-the-art WaveNet-bas…

Density EstimationSpeech Synthesis