paper-with-me

홈 › Papers

Neural ODE Transformers: Analyzing Internal Dynamics and Adaptive Fine-tuning

2025-03-03 · Anh Tong, Thanh Nguyen-Tang, Dongeun Lee, Duc Nguyen, Toan Tran, David Hall, Cheongwoong Kang, Jaesik Choi

Recent advancements in large language models (LLMs) based on transformer architectures have sparked significant interest in understanding their inner workings. In this paper, we introduce a novel approach to modeling transformer architectures using highly flexible non-autonomous neural ordinary differential equations (ODEs). Our proposed model parameterizes all weights of attention and feed-forward blocks through neural networks, expressing these weights as functions of a continuous layer index. Through spectral analysis of the model's dynamics, we uncover an increase in eigenvalue magnitude that challenges the weight-sharing assumption prevalent in existing theoretical studies. We also leverage the Lyapunov exponent to examine token-level sensitivity, enhancing model interpretability. Our neural ODE transformer demonstrates performance comparable to or better than vanilla transformers across various configurations and datasets, while offering flexible fine-tuning capabilities that can adapt to different architectural constraints.

📄 PDF Abstract BibTeX arXiv:2503.01329

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

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 $x$…
Attention 설명 없음

Similar Papers 제목 키워드 기반

Adaptive inference and function vectors in deep transformers

2026-06-15 · Ravin Raj, Gautam Reddy arxiv

Transformers are widely used as a general-purpose substrate for learning complex correlations between a large collection of coupled variables, but their internal mechanisms have remained mysterious. We introduce a theory…

Toward Manifest Relationality in Transformers via Symmetry Reduction

2026-02-21 · J. François, L. Ravera arxiv

Transformer models contain substantial internal redundancy arising from coordinate-dependent representations and continuous symmetries, in model space and in head space, respectively. While recent approaches address this…

Dynamics of Transient Structure in In-Context Linear Regression Transformers

2025-01-29 · Liam Carroll, Jesse Hoogland, Matthew Farrugia-Roberts, Daniel Murfet

Modern deep neural networks display striking examples of rich internal computational structure. Uncovering principles governing the development of such structure is a priority for the science of deep learning. In this pa…

DiversityModel Selectionregression

From Sequence to Structure: Uncovering Substructure Reasoning in Transformers

2025-07-11 · Xinnan Dai, Kai Yang, Jay Revolinsky, Kai Guo 외 arxiv

Recent studies suggest that large language models (LLMs) possess the capability to solve graph reasoning tasks. Notably, even when graph structures are embedded within textual descriptions, LLMs can still effectively ans…

Liquid Reasoning Transformers: A Sudoku-Based Prototype for Chess-Scale Algorithmic Tasks

2025-12-14 · Shivansh Sahni, Wenzhi Zhang arxiv

The Liquid Reasoning Transformer (LRT) is a transformer architecture designed for inference with adaptive depths using iterative changes, discard-based correction, and a learned stopping mechanism. Instead of relying on …