Image de couverture de livre

Interpreting Large Text-to-Image Diffusion Models with Dictionary Learning

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Shabalin, Stepan, Panda, Ayush, Kharlapenko, Dmitrii, Ali, Abdur Raheem, Hao, Yixiong, Conmy, Arthur
Format:	Preprint
Publié:	2025
Sujets:	Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Scaling sparse feature circuit finding for in-context learning
par: Kharlapenko, Dmitrii, et autres
Publié: (2025)

Patterns and Mechanisms of Contrastive Activation Engineering
par: Hao, Yixiong, et autres
Publié: (2025)

Binary Sparse Coding for Interpretability
par: Quirke, Lucia, et autres
Publié: (2025)

Transcoders Beat Sparse Autoencoders for Interpretability
par: Paulo, Gonçalo, et autres
Publié: (2025)

Is Value Functions Estimation with Classification Plug-and-play for Offline Reinforcement Learning?
par: Tarasov, Denis, et autres
Publié: (2024)

Fluid Representations in Reasoning Models
par: Kharlapenko, Dmitrii, et autres
Publié: (2026)

Improving Dictionary Learning with Gated Sparse Autoencoders
par: Rajamanoharan, Senthooran, et autres
Publié: (2024)

Interpreting Attention Layer Outputs with Sparse Autoencoders
par: Kissane, Connor, et autres
Publié: (2024)

Automatically Finding Reward Model Biases
par: Wang, Atticus, et autres
Publié: (2026)

Base Models Know How to Reason, Thinking Models Learn When
par: Venhoff, Constantin, et autres
Publié: (2025)

Improving Steering Vectors by Targeting Sparse Autoencoder Features
par: Chalnev, Sviatoslav, et autres
Publié: (2024)

Applying sparse autoencoders to unlearn knowledge in language models
par: Farrell, Eoin, et autres
Publié: (2024)

DICTDIS: Dictionary Constrained Disambiguation for Improved NMT
par: Maheshwari, Ayush, et autres
Publié: (2022)

Scaling laws for activation steering with Llama 2 models and refusal mechanisms
par: Ali, Sheikh Abdur Raheem, et autres
Publié: (2025)

Understanding Reasoning in Thinking Language Models via Steering Vectors
par: Venhoff, Constantin, et autres
Publié: (2025)

Simple LLM Baselines are Competitive for Model Diffing
par: Kempf, Elias, et autres
Publié: (2026)

Robust Learning-Augmented Dictionaries
par: Zeynali, Ali, et autres
Publié: (2024)

Measuring Progress in Dictionary Learning for Language Model Interpretability with Board Game Models
par: Karvonen, Adam, et autres
Publié: (2024)

Eliciting Secret Knowledge from Language Models
par: Cywiński, Bartosz, et autres
Publié: (2025)

Learning Interpretable Characteristic Kernels via Decision Forests
par: Panda, Sambit, et autres
Publié: (2018)

Multi-Scale Feature Fusion Quantum Depthwise Convolutional Neural Networks for Text Classification
par: Chen, Yixiong, et autres
Publié: (2024)

Thought Anchors: Which LLM Reasoning Steps Matter?
par: Bogdan, Paul C., et autres
Publié: (2025)

Diffusion Adaptive Text Embedding for Text-to-Image Diffusion Models
par: Na, Byeonghu, et autres
Publié: (2025)

Interpretable Model Drift Detection
par: Panda, Pranoy, et autres
Publié: (2025)

Physics-Informed Neural Network Digital Twin for Dynamic Tray-Wise Modeling of Distillation Columns under Transient Operating Conditions
par: Patra, Debadutta, et autres
Publié: (2026)

NeuroSep-CP-LCB: A Deep Learning-based Contextual Multi-armed Bandit Algorithm with Uncertainty Quantification for Early Sepsis Prediction
par: Zhou, Anni, et autres
Publié: (2025)

DreamReader: An Interpretability Toolkit for Text-to-Image Models
par: Prakash, Nirmalendu, et autres
Publié: (2026)

Dictionary Learning Improves Patch-Free Circuit Discovery in Mechanistic Interpretability: A Case Study on Othello-GPT
par: He, Zhengfu, et autres
Publié: (2024)

Topological Dictionary Learning
par: Grimaldi, Enrico, et autres
Publié: (2025)

Diverse Dictionary Learning
par: Zheng, Yujia, et autres
Publié: (2026)

Competition Report: Finding Universal Jailbreak Backdoors in Aligned LLMs
par: Rando, Javier, et autres
Publié: (2024)

Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders
par: Rajamanoharan, Senthooran, et autres
Publié: (2024)

A Unified Theory of Sparse Dictionary Learning in Mechanistic Interpretability: Piecewise Biconvexity and Spurious Minima
par: Tang, Yiming, et autres
Publié: (2025)

SAEBench: A Comprehensive Benchmark for Sparse Autoencoders in Language Model Interpretability
par: Karvonen, Adam, et autres
Publié: (2025)

Quriosity: Analyzing Human Questioning Behavior and Causal Inquiry through Curiosity-Driven Queries
par: Ceraolo, Roberto, et autres
Publié: (2024)

Lightweight Conceptual Dictionary Learning for Text Classification Using Information Compression
par: Wan, Li, et autres
Publié: (2024)

Reward-Agnostic Prompt Optimization for Text-to-Image Diffusion Models
par: Kim, Semin, et autres
Publié: (2025)

Alignment of Diffusion Model and Flow Matching for Text-to-Image Generation
par: Ouyang, Yidong, et autres
Publié: (2026)

FedDifRC: Unlocking the Potential of Text-to-Image Diffusion Models in Heterogeneous Federated Learning
par: Wang, Huan, et autres
Publié: (2025)

Decoding-Time Debiasing via Process Reward Models: From Controlled Fill-in to Open-Ended Generation
par: Khan, Muneeb Ur Raheem
Publié: (2026)