Image de couverture de livre

A Reproduction Study: The Kernel PCA Interpretation of Self-Attention Fails Under Scrutiny

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Sarıtaş, Karahan, Yıldız, Çağatay
Format:	Preprint
Publié:	2025
Sujets:	Machine Learning Artificial Intelligence Computation and Language Computer Vision and Pattern Recognition
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Unveiling the Hidden Structure of Self-Attention via Kernel Principal Component Analysis
par: Teo, Rachel S. Y., et autres
Publié: (2024)

Evaluating Self-Supervised Learning in Medical Imaging: A Benchmark for Robustness, Generalizability, and Multi-Domain Impact
par: Bundele, Valay, et autres
Publié: (2024)

Complexity in Complexity: Understanding Visual Complexity Through Structure, Color, and Surprise
par: Sarıtaş, Karahan, et autres
Publié: (2025)

Improving Prediction Performance and Model Interpretability through Attention Mechanisms from Basic and Applied Research Perspectives
par: Kitada, Shunsuke
Publié: (2023)

Elliptical Attention
par: Nielsen, Stefan K., et autres
Publié: (2024)

Self-Attention through Kernel-Eigen Pair Sparse Variational Gaussian Processes
par: Chen, Yingyi, et autres
Publié: (2024)

Continual Learning Using a Kernel-Based Method Over Foundation Models
par: Momeni, Saleh, et autres
Publié: (2024)

Voila-A: Aligning Vision-Language Models with User's Gaze Attention
par: Yan, Kun, et autres
Publié: (2023)

Unified Lexical Representation for Interpretable Visual-Language Alignment
par: Li, Yifan, et autres
Publié: (2024)

A Concept-based Interpretable Model for the Diagnosis of Choroid Neoplasias using Multimodal Data
par: Wu, Yifan, et autres
Publié: (2024)

LatentLLM: Attention-Aware Joint Tensor Compression
par: Koike-Akino, Toshiaki, et autres
Publié: (2025)

Interpreting and Controlling Model Behavior via Constitutions for Atomic Concept Edits
par: Kalibhat, Neha, et autres
Publié: (2026)

Object-level Self-Distillation for Vision Pretraining
par: Hızlı, Çağlar, et autres
Publié: (2025)

Divide & Bind Your Attention for Improved Generative Semantic Nursing
par: Li, Yumeng, et autres
Publié: (2023)

Out-of-Distribution Detection with Attention Head Masking for Multimodal Document Classification
par: Constantinou, Christos, et autres
Publié: (2024)

AttnLRP: Attention-Aware Layer-Wise Relevance Propagation for Transformers
par: Achtibat, Reduan, et autres
Publié: (2024)

UI-Voyager: A Self-Evolving GUI Agent Learning via Failed Experience
par: Lin, Zichuan, et autres
Publié: (2026)

Cyclic Vision-Language Manipulator: Towards Reliable and Fine-Grained Image Interpretation for Automated Report Generation
par: Fang, Yingying, et autres
Publié: (2024)

Self-Supervised Visual Preference Alignment
par: Zhu, Ke, et autres
Publié: (2024)

Contrastive-to-Self-Supervised: A Two-Stage Framework for Script Similarity Learning
par: Roman, Claire, et autres
Publié: (2026)

LLM as a Neural Architect: Controlled Generation of Image Captioning Models Under Strict API Contracts
par: Jesani, Krunal, et autres
Publié: (2025)

Diving into Self-Evolving Training for Multimodal Reasoning
par: Liu, Wei, et autres
Publié: (2024)

Contextual Experience Replay for Self-Improvement of Language Agents
par: Liu, Yitao, et autres
Publié: (2025)

RewardHarness: Self-Evolving Agentic Post-Training
par: Zhang, Yuxuan, et autres
Publié: (2026)

Efficient Self-Improvement in Multimodal Large Language Models: A Model-Level Judge-Free Approach
par: Deng, Shijian, et autres
Publié: (2024)

Translution: Unifying Self-attention and Convolution for Adaptive and Relative Modeling
par: Fan, Hehe, et autres
Publié: (2025)

Through the Lens of Contrast: Self-Improving Visual Reasoning in VLMs
par: Pan, Zhiyu, et autres
Publié: (2026)

MHA2MLA-VLM: Enabling DeepSeek's Economical Multi-Head Latent Attention across Vision-Language Models
par: Fan, Xiaoran, et autres
Publié: (2026)

VisPlay: Self-Evolving Vision-Language Models from Images
par: He, Yicheng, et autres
Publié: (2025)

SQ-LLaVA: Self-Questioning for Large Vision-Language Assistant
par: Sun, Guohao, et autres
Publié: (2024)

Self-Play Fine-Tuning of Diffusion Models for Text-to-Image Generation
par: Yuan, Huizhuo, et autres
Publié: (2024)

Vision-Language Models Can Self-Improve Reasoning via Reflection
par: Cheng, Kanzhi, et autres
Publié: (2024)

COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training
par: Kim, Sanghwan, et autres
Publié: (2024)

Have the VLMs Lost Confidence? A Study of Sycophancy in VLMs
par: Li, Shuo, et autres
Publié: (2024)

Federated Document Visual Question Answering: A Pilot Study
par: Nguyen, Khanh, et autres
Publié: (2024)

Uni-Mlip: Unified Self-supervision for Medical Vision Language Pre-training
par: Bawazir, Ameera, et autres
Publié: (2024)

A Comprehensive Study of Decoder-Only LLMs for Text-to-Image Generation
par: Wang, Andrew Z., et autres
Publié: (2025)

Mitigating Object and Action Hallucinations in Multimodal LLMs via Self-Augmented Contrastive Alignment
par: Chang, Kai-Po, et autres
Publié: (2025)

Counteracting Matthew Effect in Self-Improvement of LVLMs through Head-Tail Re-balancing
par: Guo, Xin, et autres
Publié: (2025)

Adaptation Odyssey in LLMs: Why Does Additional Pretraining Sometimes Fail to Improve?
par: Öncel, Fırat, et autres
Publié: (2024)