English
Related papers

Related papers: You Do Not Fully Utilize Transformer's Representat…

200 papers

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

Transformers are widely used across data modalities, and yet the principles distilled from text models often transfer imperfectly to models trained to other modalities. In this paper, we analyze Transformers through the lens of rank…

Large Language Models are prone to biased predictions and hallucinations, underlining the paramount importance of understanding their model-internal reasoning process. However, achieving faithful attributions for the entirety of a black-box…

Due to its perceptual limitations, an agent may have too little information about the state of the environment to act optimally. In such cases, it is important to keep track of the observation history to uncover hidden state. Recent deep…

Machine Learning · Computer Science 2021-02-18 Miguel Suau , Jinke He , Elena Congeduti , Rolf A. N. Starre , Aleksander Czechowski , Frans A. Oliehoek

Despite the advantageous subquadratic complexity of modern recurrent deep learning models -- such as state-space models (SSMs) -- recent studies have highlighted their potential shortcomings compared to transformers on reasoning and…

Machine Learning · Computer Science 2025-10-13 Destiny Okpekpe , Antonio Orvieto

Recent studies have demonstrated that the performance of transformers on the task of language modeling obeys a power-law relationship with model size over six orders of magnitude. While transformers exhibit impressive scaling, their…

Machine Learning · Computer Science 2021-10-07 Narsimha Chilkuri , Eric Hunsberger , Aaron Voelker , Gurshaant Malik , Chris Eliasmith

Transformers have shown a remarkable ability for in-context learning (ICL), making predictions based on contextual examples. However, while theoretical analyses have explored this prediction capability, the nature of the inferred context…

Machine Learning · Computer Science 2025-05-20 Fei Lu , Yue Yu

The embedding layers transforming input words into real vectors are the key components of deep neural networks used in natural language processing. However, when the vocabulary is large, the corresponding weight matrices can be enormous,…

Computation and Language · Computer Science 2020-02-20 Oleksii Hrinchuk , Valentin Khrulkov , Leyla Mirvakhabova , Elena Orlova , Ivan Oseledets

Theoretical efforts to prove advantages of Transformers in comparison with classical architectures such as feedforward and recurrent neural networks have mostly focused on representational power. In this work, we take an alternative…

Machine Learning · Statistics 2025-03-17 Alireza Mousavi-Hosseini , Clayton Sanford , Denny Wu , Murat A. Erdogdu

Sequence modeling requires both compositional reasoning and local static knowledge retrieval, yet standard Transformers handle both through dense computation. Engram partially decouples retrieval from the backbone, but its token-based keys…

Computation and Language · Computer Science 2026-05-26 Yunao Zheng , Guoyang Xia , Xiaojie Wang , Lei Ren

Time series prediction plays a crucial role in various industrial fields. In recent years, neural networks with a transformer backbone have achieved remarkable success in many domains, including computer vision and NLP. In time series…

Machine Learning · Computer Science 2023-10-10 Qingkui Chen , Yiqin Zhang

Despite rapid advancements, machine learning, particularly deep learning, is hindered by the need for large amounts of labeled data to learn meaningful patterns without overfitting and immense demands for computation and storage, which…

Machine Learning · Computer Science 2025-06-30 Xiaobo Zhao , Aaron Hurst , Panagiotis Karras , Daniel E. Lucani

We introduce a novel generative framework for functions by integrating Implicit Neural Representations (INRs) and Transformer-based hypernetworks into latent variable models. Unlike prior approaches that rely on MLP-based hypernetworks with…

Machine Learning · Computer Science 2025-11-04 Ignacio Peis , Batuhan Koyuncu , Isabel Valera , Jes Frellsen

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

This work introduces a Transformer-based image compression system. It has the flexibility to switch between the standard image reconstruction and the denoising reconstruction from a single compressed bitstream. Instead of training separate…

Image and Video Processing · Electrical Eng. & Systems 2024-02-21 Yi-Hsin Chen , Kuan-Wei Ho , Shiau-Rung Tsai , Guan-Hsun Lin , Alessandro Gnutti , Wen-Hsiao Peng , Riccardo Leonardi

In this paper, we introduce a method to compress intermediate feature maps of deep neural networks (DNNs) to decrease memory storage and bandwidth requirements during inference. Unlike previous works, the proposed method is based on…

Computer Vision and Pattern Recognition · Computer Science 2018-08-17 Denis A. Gudovskiy , Alec Hodgkinson , Luca Rigazio

Self-attention performs well in long context but has quadratic complexity. Existing RNN layers have linear complexity, but their performance in long context is limited by the expressive power of their hidden states. We present a practical…

Understanding how Transformer-based Language Models (LMs) learn and recall information is a key goal of the deep learning community. Recent interpretability methods project weights and hidden states obtained from the forward pass to the…

Computation and Language · Computer Science 2024-02-21 Shahar Katz , Yonatan Belinkov , Mor Geva , Lior Wolf

In this work, we study how well the learned weights of a neural network utilize the space available to them. This notion is related to capacity, but additionally incorporates the interaction of the network architecture with the dataset.…

Computer Vision and Pattern Recognition · Computer Science 2024-07-09 Isha Garg , Christian Koguchi , Eshan Verma , Daniel Ulbricht

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
‹ Prev 1 8 9 10 Next ›