English
Related papers

Related papers: Future Lens: Anticipating Subsequent Tokens from a…

200 papers

Are generative pre-trained transformer (GPT) models, trained only to predict the next token, implicitly learning a world model from which sequences are generated one token at a time? We address this question by deriving a causal…

Artificial Intelligence · Computer Science 2025-07-08 Raanan Y. Rohekar , Yaniv Gurwicz , Sungduk Yu , Estelle Aflalo , Vasudev Lal

The transformer is a state-of-the-art neural translation model that uses attention to iteratively refine lexical representations with information drawn from the surrounding context. Lexical features are fed into the first layer and…

Computation and Language · Computer Science 2019-07-01 Denis Emelin , Ivan Titov , Rico Sennrich

The automated detection of hallucinations and training data contamination is pivotal to the safe deployment of Large Language Models (LLMs). These tasks are particularly challenging in settings where no access to model internals is…

Machine Learning · Computer Science 2025-10-01 Guy Bar-Shalom , Fabrizio Frasca , Derek Lim , Yoav Gelberg , Yftah Ziser , Ran El-Yaniv , Gal Chechik , Haggai Maron

Adaptive cognition requires structured internal models of objects and their relations. Predictive neural networks are often proposed to learn such world models, but how these are instantiated and how they support prediction remain unclear.…

Machine Learning · Computer Science 2026-05-11 Linda Ariel Ventura , Victoria Bosch , Tim C Kietzmann , Sushrut Thorat

Augmenting large language models (LLMs) with auxiliary tokens has emerged as a promising strategy for enhancing model performance. In this work, we introduce a lightweight method termed latent tokens; these are dummy tokens that may be…

Machine Learning · Computer Science 2025-05-20 Yuchang Sun , Yanxi Chen , Yaliang Li , Bolin Ding

In large language models (LLMs), each block operates on the residual stream to map input token sequences to output token distributions. However, most of the interpretability literature focuses on internal latent representations, leaving…

Machine Learning · Computer Science 2026-02-03 Riccardo Ali , Francesco Caso , Christopher Irwin , Pietro Liò

In this work, we propose a step towards a more accurate prediction of the environment light given a single picture of a known object. To achieve this, we developed a deep learning method that is able to encode the latent space of indoor…

Computer Vision and Pattern Recognition · Computer Science 2018-08-14 Henrique Weber , Donald Prévost , Jean-François Lalonde

Despite significant progress in transformer interpretability, an understanding of the computational mechanisms of large language models (LLMs) remains a fundamental challenge. Many approaches interpret a network's hidden representations but…

Machine Learning · Computer Science 2025-10-14 James R. Golden

We demonstrate that, hidden within one-layer randomly weighted neural networks, there exist subnetworks that can achieve impressive performance, without ever modifying the weight initializations, on machine translation tasks. To find…

Computation and Language · Computer Science 2021-09-10 Sheng Shen , Zhewei Yao , Douwe Kiela , Kurt Keutzer , Michael W. Mahoney

Language models have shown unprecedented capabilities, sparking debate over the source of their performance. Is it merely the outcome of learning syntactic patterns and surface level statistics, or do they extract semantics and a world…

Machine Learning · Computer Science 2024-07-16 Adam Karvonen

Not all entangled states can exhibit quantum steering, and determining whether a given entangled state is steerable is a crucial problem in quantum information theory. The main challenge lies in verifying the existence of a local…

Quantum Physics · Physics 2025-12-29 Yanning Jia , Fenzhuo Guo , Mengyan Li , Haifeng Dong , Fei Gao

In this paper we propose augmenting Vision Transformer models with learnable memory tokens. Our approach allows the model to adapt to new tasks, using few parameters, while optionally preserving its capabilities on previously learned tasks.…

Computer Vision and Pattern Recognition · Computer Science 2022-03-31 Mark Sandler , Andrey Zhmoginov , Max Vladymyrov , Andrew Jackson

Recurrent Neural Networks are an effective and prevalent tool used to model sequential data such as natural language text. However, their deep nature and massive number of parameters pose a challenge for those intending to study precisely…

Computation and Language · Computer Science 2020-08-18 Lindsey Sawatzky , Steven Bergner , Fred Popowich

The text produced by language models (LMs) can exhibit specific `behaviors,' such as a failure to follow alignment training, that we hope to detect and react to during deployment. Identifying these behaviors can often only be done post…

Computation and Language · Computer Science 2025-09-24 Dhananjay Ashok , Jonathan May

Large language models (LLMs) have achieved notable progress. Despite their success, next-token prediction (NTP), the dominant method for LLM training and inference, is constrained in both contextual coverage and inference efficiency due to…

Computation and Language · Computer Science 2025-09-23 Xiaohao Liu , Xiaobo Xia , Weixiang Zhao , Manyi Zhang , Xianzhi Yu , Xiu Su , Shuo Yang , See-Kiong Ng , Tat-Seng Chua

Modern language models scale depth by stacking layers, each holding its own state - a per-layer KV cache in transformers, a per-layer matrix in Mamba, Gated DeltaNet (GDN), RWKV, and xLSTM. Biological systems lean heavily on recurrence…

Computation and Language · Computer Science 2026-05-12 Zanmin Wang

Transformers are state-of-the-art deep learning models that are composed of stacked attention and point-wise, fully connected layers designed for handling sequential data. Transformers are not only ubiquitous throughout Natural Language…

Computer Vision and Pattern Recognition · Computer Science 2021-12-01 Onur Kara , Arijit Sehanobish , Hector H Corzo

Detectors in the laboratory are often unlike their ideal theoretical cousins. They have non-ideal efficiencies, which may then lead to non-trivial implications. We show how it is possible to predict correct answers about whether a shared…

Quantum Physics · Physics 2021-06-09 Kornikar Sen , Sreetama Das , Ujjwal Sen

Neutrino telescopes detect rare interactions of particles produced in some of the most extreme environments in the Universe. This is accomplished by instrumenting a cubic-kilometer scale volume of naturally occurring transparent medium with…

Data Analysis, Statistics and Probability · Physics 2025-11-26 Felix J. Yu , Nicholas Kamp , Carlos A. Argüelles

We present novel methods for analyzing the activation patterns of RNNs from a linguistic point of view and explore the types of linguistic structure they learn. As a case study, we use a multi-task gated recurrent network architecture…

Computation and Language · Computer Science 2016-06-09 Ákos Kádár , Grzegorz Chrupała , Afra Alishahi