Imagen de Portada

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

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Shabalin, Stepan, Panda, Ayush, Kharlapenko, Dmitrii, Ali, Abdur Raheem, Hao, Yixiong, Conmy, Arthur
Formato:	Preprint
Publicado:	2025
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Scaling sparse feature circuit finding for in-context learning
por: Kharlapenko, Dmitrii, et al.
Publicado: (2025)

Patterns and Mechanisms of Contrastive Activation Engineering
por: Hao, Yixiong, et al.
Publicado: (2025)

Binary Sparse Coding for Interpretability
por: Quirke, Lucia, et al.
Publicado: (2025)

Transcoders Beat Sparse Autoencoders for Interpretability
por: Paulo, Gonçalo, et al.
Publicado: (2025)

Is Value Functions Estimation with Classification Plug-and-play for Offline Reinforcement Learning?
por: Tarasov, Denis, et al.
Publicado: (2024)

Fluid Representations in Reasoning Models
por: Kharlapenko, Dmitrii, et al.
Publicado: (2026)

Improving Dictionary Learning with Gated Sparse Autoencoders
por: Rajamanoharan, Senthooran, et al.
Publicado: (2024)

Interpreting Attention Layer Outputs with Sparse Autoencoders
por: Kissane, Connor, et al.
Publicado: (2024)

Automatically Finding Reward Model Biases
por: Wang, Atticus, et al.
Publicado: (2026)

Base Models Know How to Reason, Thinking Models Learn When
por: Venhoff, Constantin, et al.
Publicado: (2025)

Improving Steering Vectors by Targeting Sparse Autoencoder Features
por: Chalnev, Sviatoslav, et al.
Publicado: (2024)

Applying sparse autoencoders to unlearn knowledge in language models
por: Farrell, Eoin, et al.
Publicado: (2024)

DICTDIS: Dictionary Constrained Disambiguation for Improved NMT
por: Maheshwari, Ayush, et al.
Publicado: (2022)

Scaling laws for activation steering with Llama 2 models and refusal mechanisms
por: Ali, Sheikh Abdur Raheem, et al.
Publicado: (2025)

Understanding Reasoning in Thinking Language Models via Steering Vectors
por: Venhoff, Constantin, et al.
Publicado: (2025)

Simple LLM Baselines are Competitive for Model Diffing
por: Kempf, Elias, et al.
Publicado: (2026)

Robust Learning-Augmented Dictionaries
por: Zeynali, Ali, et al.
Publicado: (2024)

Measuring Progress in Dictionary Learning for Language Model Interpretability with Board Game Models
por: Karvonen, Adam, et al.
Publicado: (2024)

Eliciting Secret Knowledge from Language Models
por: Cywiński, Bartosz, et al.
Publicado: (2025)

Learning Interpretable Characteristic Kernels via Decision Forests
por: Panda, Sambit, et al.
Publicado: (2018)

Multi-Scale Feature Fusion Quantum Depthwise Convolutional Neural Networks for Text Classification
por: Chen, Yixiong, et al.
Publicado: (2024)

Thought Anchors: Which LLM Reasoning Steps Matter?
por: Bogdan, Paul C., et al.
Publicado: (2025)

Diffusion Adaptive Text Embedding for Text-to-Image Diffusion Models
por: Na, Byeonghu, et al.
Publicado: (2025)

Interpretable Model Drift Detection
por: Panda, Pranoy, et al.
Publicado: (2025)

Physics-Informed Neural Network Digital Twin for Dynamic Tray-Wise Modeling of Distillation Columns under Transient Operating Conditions
por: Patra, Debadutta, et al.
Publicado: (2026)

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

DreamReader: An Interpretability Toolkit for Text-to-Image Models
por: Prakash, Nirmalendu, et al.
Publicado: (2026)

Dictionary Learning Improves Patch-Free Circuit Discovery in Mechanistic Interpretability: A Case Study on Othello-GPT
por: He, Zhengfu, et al.
Publicado: (2024)

Topological Dictionary Learning
por: Grimaldi, Enrico, et al.
Publicado: (2025)

Diverse Dictionary Learning
por: Zheng, Yujia, et al.
Publicado: (2026)

Competition Report: Finding Universal Jailbreak Backdoors in Aligned LLMs
por: Rando, Javier, et al.
Publicado: (2024)

Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders
por: Rajamanoharan, Senthooran, et al.
Publicado: (2024)

A Unified Theory of Sparse Dictionary Learning in Mechanistic Interpretability: Piecewise Biconvexity and Spurious Minima
por: Tang, Yiming, et al.
Publicado: (2025)

SAEBench: A Comprehensive Benchmark for Sparse Autoencoders in Language Model Interpretability
por: Karvonen, Adam, et al.
Publicado: (2025)

Quriosity: Analyzing Human Questioning Behavior and Causal Inquiry through Curiosity-Driven Queries
por: Ceraolo, Roberto, et al.
Publicado: (2024)

Lightweight Conceptual Dictionary Learning for Text Classification Using Information Compression
por: Wan, Li, et al.
Publicado: (2024)

Reward-Agnostic Prompt Optimization for Text-to-Image Diffusion Models
por: Kim, Semin, et al.
Publicado: (2025)

Alignment of Diffusion Model and Flow Matching for Text-to-Image Generation
por: Ouyang, Yidong, et al.
Publicado: (2026)

FedDifRC: Unlocking the Potential of Text-to-Image Diffusion Models in Heterogeneous Federated Learning
por: Wang, Huan, et al.
Publicado: (2025)

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