English
Related papers

Related papers: Transformer-like Inference from Optimal Control

200 papers

Transformers can generate predictions in two approaches: 1. auto-regressively by conditioning each sequence element on the previous ones, or 2. directly produce an output sequences in parallel. While research has mostly explored upon this…

Computer Vision and Pattern Recognition · Computer Science 2021-08-18 Andrea Alfieri , Yancong Lin , Jan C. van Gemert

Transformers have exhibited exceptional capabilities in sequence modeling tasks, leveraging self-attention and in-context learning. Critical to this success are induction heads, attention circuits that enable copying tokens based on their…

Machine Learning · Computer Science 2025-09-11 Francesco D'Angelo , Francesco Croce , Nicolas Flammarion

Attention-based transformers have been remarkably successful at modeling generative processes across various domains and modalities. In this paper, we study the behavior of transformers on data drawn from \kth Markov processes, where the…

Machine Learning · Computer Science 2024-07-26 Nived Rajaraman , Marco Bondaschi , Kannan Ramchandran , Michael Gastpar , Ashok Vardhan Makkuva

In this technical note, we study the problem of inverse permutation learning in decoder-only transformers. Given a permutation and a string to which that permutation has been applied, the model is tasked with producing the original…

Machine Learning · Computer Science 2025-12-11 Rohan Alur , Chris Hays , Manish Raghavan , Devavrat Shah

Transformers have demonstrated remarkable success across various applications. However, the success of transformers have not been understood in theory. In this work, we give a case study of how transformers can be trained to learn a classic…

Machine Learning · Statistics 2025-04-14 Chenyang Zhang , Xuran Meng , Yuan Cao

The recent promises of Model Predictive Control in robotics have motivated the development of tailored second-order methods to solve optimal control problems efficiently. While those methods benefit from strong convergence properties,…

Robotics · Computer Science 2024-09-30 Jianghan Zhang , Armand Jordana , Ludovic Righetti

Transformers evaluated in a single, fixed-depth pass are provably limited in expressive power to the constant-depth circuit class TC0. Running a Transformer autoregressively removes that ceiling -- first in next-token prediction and, more…

Machine Learning · Computer Science 2025-07-21 Mrinal Mathur , Mike Doan , Barak Pearlmutter , Sergey Plis

What computational structures emerge in transformers trained on next-token prediction? In this work, we provide evidence that transformers implement constrained Bayesian belief updating -- a parallelized version of partial Bayesian…

Machine Learning · Computer Science 2025-10-16 Mateusz Piotrowski , Paul M. Riechers , Daniel Filan , Adam S. Shai

Modern large language models (LLMs) excel at tasks that require storing and retrieving knowledge, such as factual recall and question answering. Transformers are central to this capability because they can encode information during training…

Machine Learning · Statistics 2026-03-18 Nuri Mert Vural , Alberto Bietti , Mahdi Soltanolkotabi , Denny Wu

One critical component in lossy deep image compression is the entropy model, which predicts the probability distribution of the quantized latent representation in the encoding and decoding modules. Previous works build entropy models upon…

Image and Video Processing · Electrical Eng. & Systems 2023-03-16 Yichen Qian , Ming Lin , Xiuyu Sun , Zhiyu Tan , Rong Jin

This paper proposes Progressive Inference - a framework to compute input attributions to explain the predictions of decoder-only sequence classification models. Our work is based on the insight that the classification head of a decoder-only…

Machine Learning · Computer Science 2024-06-06 Sanjay Kariyappa , Freddy Lécué , Saumitra Mishra , Christopher Pond , Daniele Magazzeni , Manuela Veloso

Transformer-based diffusion models have demonstrated remarkable performance at generating high-quality samples. However, our theoretical understanding of the reasons for this success remains limited. For instance, existing models are…

Machine Learning · Computer Science 2026-04-14 Hongkang Li , Hancheng Min , Rene Vidal

A two-layer control architecture is proposed, which promotes scalable implementations for model predictive controllers. The top layer acts as both a reference governor for the bottom layer and as a feedback controller for the regulated…

Systems and Control · Electrical Eng. & Systems 2026-04-13 Andrei Sperilă , Alessio Iovine , Sorin Olaru , Patrick Panciatici

Transformers pretrained via next token prediction learn to factor their world into parts, representing these factors in orthogonal subspaces of the residual stream. We formalize two representational hypotheses: (1) a representation in the…

The large attention-based encoder-decoder network (Transformer) has become prevailing recently due to its effectiveness. But the high computation complexity of its decoder raises the inefficiency issue. By examining the mathematic…

Computation and Language · Computer Science 2023-05-12 Yanyang Li , Ye Lin , Tong Xiao , Jingbo Zhu

What computational structure are we building into large language models when we train them on next-token prediction? Here, we present evidence that this structure is given by the meta-dynamics of belief updating over hidden states of the…

Machine Learning · Computer Science 2025-02-05 Adam S. Shai , Sarah E. Marzen , Lucas Teixeira , Alexander Gietelink Oldenziel , Paul M. Riechers

We propose a new model for multi-token prediction in transformers, aiming to enhance sampling efficiency without compromising accuracy. Motivated by recent work that predicts the probabilities of subsequent tokens using multiple heads, we…

Machine Learning · Computer Science 2025-02-11 Artem Basharin , Andrei Chertkov , Ivan Oseledets

Recent advances in machine learning, specifically transformer architecture, have led to significant advancements in commercial domains. These powerful models have demonstrated superior capability to learn complex relationships and often…

Machine Learning · Computer Science 2024-05-29 Matthew L. Olson , Shusen Liu , Jayaraman J. Thiagarajan , Bogdan Kustowski , Weng-Keen Wong , Rushil Anirudh

Transformer-based encoder-decoder models produce a fused token-wise representation after every encoder layer. We investigate the effects of allowing the encoder to preserve and explore alternative hypotheses, combined at the end of the…

Computation and Language · Computer Science 2021-07-23 Mikhail Burtsev , Anna Rumshisky

Most neural networks utilize the same amount of compute for every example independent of the inherent complexity of the input. Further, methods that adapt the amount of computation to the example focus on finding a fixed inference-time…

Machine Learning · Computer Science 2020-04-17 Ankur Bapna , Naveen Arivazhagan , Orhan Firat