paper-with-me

Papers

DINT Transformer

2025-01-29 · Yueyang Cang, Yuhang Liu, Xiaoteng Zhang, Erlu Zhao, Li Shi

DIFF Transformer addresses the issue of irrelevant context interference by introducing a differential attention mechanism that enhances the robustness of local attention. However, it has two critical limitations: the lack of global context modeling, which is essential for identifying globally significant tokens, and numerical instability due to the absence of strict row normalization in the attention matrix. To overcome these challenges, we propose DINT Transformer, which extends DIFF Transformer by incorporating a differential-integral mechanism. By computing global importance scores and integrating them into the attention matrix, DINT Transformer improves its ability to capture global dependencies. Moreover, the unified parameter design enforces row-normalized attention matrices, improving numerical stability. Experimental results demonstrate that DINT Transformer excels in accuracy and robustness across various practical applications, such as long-context language modeling and key information retrieval. These results position DINT Transformer as a highly effective and promising architecture.

📄 PDF Abstract BibTeX arXiv:2501.17486

Code (0)

등록된 구현이 없습니다.

Tasks

Information RetrievalLanguage ModelingLanguage Modelling

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Adam 설명 없음
Residual Connection 설명 없음
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.

Similar Papers 제목 키워드 기반

DinTucker: Scaling up Gaussian process models on multidimensional arrays with billions of elements

2013-11-12 · Shandian Zhe, Yuan Qi, Youngja Park, Ian Molloy 외

Infinite Tucker Decomposition (InfTucker) and random function prior models, as nonparametric Bayesian models on infinite exchangeable arrays, are more powerful models than widely-used multilinear factorization methods in…

Tensor DecompositionVariational Inference

DMDIntel: Interpreting Large Language Models via Dynamic Mode Decomposition

2026-08-13 · Amogh Joshi, Animesh Mukherjee, Sergey Utyuzhnikov arxiv

In this work, we introduce DMDIntel which uses dynamic mode decomposition (DMD) to make the predictions made by LLMs in a classification task interpretable. It develops an input attribution pipeline, that first decompose…

Federated Learning with Intermediate Representation Regularization

2022-10-28 · Ye Lin Tun, Chu Myaet Thwal, Yu Min Park, Seong-Bae Park 외

In contrast to centralized model training that involves data collection, federated learning (FL) enables remote clients to collaboratively train a model without exposing their private data. However, model performance usu…

Federated Learning

A Survey of Task-Based Machine Learning Content Extraction Services for VIDINT

2022-07-09 · Joshua Brunk, Nathan Jermann, Ryan Sharp, Carl D. Hoover

This paper provides a comparison of current video content extraction tools with a focus on comparing commercial task-based machine learning services. Video intelligence (VIDINT) data has become a critical intelligence so…

BIG-bench Machine LearningMachine TranslationObject RecognitionTranslation

RFpredInterval: An R Package for Prediction Intervals with Random Forests and Boosted Forests

2021-06-15 · Cansu Alakus, Denis Larocque, Aurelie Labbe

Like many predictive models, random forests provide point predictions for new observations. Besides the point prediction, it is important to quantify the uncertainty in the prediction. Prediction intervals provide inform…

PredictionPrediction Intervals