Imagen de Portada

Layer-Wise Evolution of Representations in Fine-Tuned Transformers: Insights from Sparse AutoEncoders

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autor principal:	Nadipalli, Suneel
Formato:	Preprint
Publicado:	2025
Materias:	Computation and Language Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Quasi-symbolic Semantic Geometry over Transformer-based Variational AutoEncoder
por: Zhang, Yingji, et al.
Publicado: (2022)

EBFT: Effective and Block-Wise Fine-Tuning for Sparse LLMs
por: Guo, Song, et al.
Publicado: (2024)

Sparse Auto-Encoders and Holism about Large Language Models
por: Grindrod, Jumbly
Publicado: (2026)

Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation
por: Shu, Huizhen, et al.
Publicado: (2025)

SafeMERGE: Preserving Safety Alignment in Fine-Tuned Large Language Models via Selective Layer-Wise Model Merging
por: Djuhera, Aladin, et al.
Publicado: (2025)

Middle-Layer Representation Alignment for Cross-Lingual Transfer in Fine-Tuned LLMs
por: Liu, Danni, et al.
Publicado: (2025)

HalluSAE: Detecting Hallucinations in Large Language Models via Sparse Auto-Encoders
por: Chen, Boshui, et al.
Publicado: (2026)

SAEdit: Token-level control for continuous image editing via Sparse AutoEncoder
por: Kamenetsky, Ronen, et al.
Publicado: (2025)

LLMCache: Layer-Wise Caching Strategies for Accelerated Reuse in Transformer Inference
por: Bansal, Harsh Vardhan
Publicado: (2025)

Representation Learning of Lab Values via Masked AutoEncoders
por: Restrepo, David, et al.
Publicado: (2025)

Fine-tuning Transformer-based Encoder for Turkish Language Understanding Tasks
por: Yildirim, Savas
Publicado: (2024)

Guiding Evolutionary AutoEncoder Training with Activation-Based Pruning Operators
por: Jorgensen, Steven, et al.
Publicado: (2025)

AudioSAE: Towards Understanding of Audio-Processing Models with Sparse AutoEncoders
por: Aparin, Georgii, et al.
Publicado: (2026)

How to Alleviate Catastrophic Forgetting in LLMs Finetuning? Hierarchical Layer-Wise and Element-Wise Regularization
por: Song, Shezheng, et al.
Publicado: (2025)

How to Tune a Multilingual Encoder Model for Germanic Languages: A Study of PEFT, Full Fine-Tuning, and Language Adapters
por: Oji, Romina, et al.
Publicado: (2025)

Refining Salience-Aware Sparse Fine-Tuning Strategies for Language Models
por: Liu, Xinxin, et al.
Publicado: (2024)

CwA-T: A Channelwise AutoEncoder with Transformer for EEG Abnormality Detection
por: Zhao, Youshen, et al.
Publicado: (2024)

Hidden Heroes and Gradient Bloats: Layer-Wise Redundancy Inverts Attribution in Transformers
por: Ye, Donald
Publicado: (2026)

SparseGrad: A Selective Method for Efficient Fine-tuning of MLP Layers
por: Chekalina, Viktoriia, et al.
Publicado: (2024)

Scaling Sparse Fine-Tuning to Large Language Models
por: Ansell, Alan, et al.
Publicado: (2024)

SAEN-BGS: Energy-Efficient Spiking AutoEncoder Network for Background Subtraction
por: Zhang, Zhixuan, et al.
Publicado: (2025)

AutoPEFT: Automatic Configuration Search for Parameter-Efficient Fine-Tuning
por: Zhou, Han, et al.
Publicado: (2023)

Tracing Representation Progression: Analyzing and Enhancing Layer-Wise Similarity
por: Jiang, Jiachen, et al.
Publicado: (2024)

WilKE: Wise-Layer Knowledge Editor for Lifelong Knowledge Editing
por: Hu, Chenhui, et al.
Publicado: (2024)

AEMLO: AutoEncoder-Guided Multi-Label Oversampling
por: Zhou, Ao, et al.
Publicado: (2024)

Crown, Frame, Reverse: Layer-Wise Scaling Variants for LLM Pre-Training
por: Baroian, Andrei, et al.
Publicado: (2025)

Hierarchical Alignment: Surgical Fine-Tuning via Functional Layer Specialization in Large Language Models
por: Zhang, Yukun, et al.
Publicado: (2025)

GradPruner: Gradient-Guided Layer Pruning Enabling Efficient Fine-Tuning and Inference for LLMs
por: Huang, Wei, et al.
Publicado: (2026)

Dial-MAE: ConTextual Masked Auto-Encoder for Retrieval-based Dialogue Systems
por: Su, Zhenpeng, et al.
Publicado: (2023)

Penrose Tiled Low-Rank Compression and Section-Wise Q&A Fine-Tuning: A General Framework for Domain-Specific Large Language Model Adaptation
por: Kuo, Chuan-Wei, et al.
Publicado: (2025)

Adaptive Layer Selection for Layer-Wise Token Pruning in LLM Inference
por: Taniguchi, Rei, et al.
Publicado: (2026)

LPCD: Unified Framework from Layer-Wise to Submodule Quantization
por: Ichikawa, Yuma, et al.
Publicado: (2025)

AttnLRP: Attention-Aware Layer-Wise Relevance Propagation for Transformers
por: Achtibat, Reduan, et al.
Publicado: (2024)

Comparative Analysis of Efficient Adapter-Based Fine-Tuning of State-of-the-Art Transformer Models
por: Siddiqui, Saad Mashkoor, et al.
Publicado: (2025)

HUT: A More Computation Efficient Fine-Tuning Method With Hadamard Updated Transformation
por: Zhang, Geyuan, et al.
Publicado: (2024)

Surprising Efficacy of Fine-Tuned Transformers for Fact-Checking over Larger Language Models
por: Setty, Vinay
Publicado: (2024)

Parameter-Efficient Fine-Tuning with Discrete Fourier Transform
por: Gao, Ziqi, et al.
Publicado: (2024)

Evaluate Summarization in Fine-Granularity: Auto Evaluation with LLM
por: Yuan, Dong, et al.
Publicado: (2024)

SelfSwapper: Self-Supervised Face Swapping via Shape Agnostic Masked AutoEncoder
por: Lee, Jaeseong, et al.
Publicado: (2024)

Physics Informed Capsule Enhanced Variational AutoEncoder for Underwater Image Enhancement
por: Martinel, Niki, et al.
Publicado: (2025)