Follow the Flow: On Information Flow Across Textual Tokens in Text-to-Image Models

arXiv:2504.01137 · cs.CL · Submitted 2025-04-01 · Read on arXiv

cs.CL

Submitted: 2025-04-01

Updated: 2026-04-16

Code: https://github.com/tokeron/lens

Terminology

• Alignment — 21× in this paper · explained in 1 episode
• Diffusion Model — 14× in this paper · explained in 8 episodes
• Accuracy — 8× in this paper · explained in 1 episode
• Transformer — 7× in this paper · explained in 2 episodes
• Benchmark — 6× in this paper · explained in 2 episodes
• Embeddings — 6× in this paper · explained in 2 episodes
• Diffusion Models — 5× in this paper · explained in 6 episodes
• Diffusion Process — 5× in this paper · explained in 2 episodes
• Interpretability — 4× in this paper · explained in 15 episodes
• Redundancy — 4× in this paper · explained in 2 episodes
• Adam — 2× in this paper · explained in 2 episodes
• Alignment Problem — 2× in this paper · explained in 1 episode
• Generalization — 2× in this paper · explained in 13 episodes
• Grounding — 2× in this paper · explained in 3 episodes
• Tokenization — 2× in this paper · explained in 2 episodes
• Vision-Language Model (VLM) — 2× in this paper · explained in 3 episodes
• Visual Grounding — 2× in this paper · explained in 2 episodes
• Attention Mechanism — 1× in this paper · explained in 2 episodes
• Benchmarking — 1× in this paper · explained in 3 episodes
• Core — 1× in this paper · explained in 2 episodes
• Cross-Attention Mechanism — 1× in this paper · explained in 2 episodes
• Decode — 1× in this paper · explained in 2 episodes
• Distillation — 1× in this paper · explained in 2 episodes
• Generative Model — 1× in this paper · explained in 2 episodes
• Generative Modeling — 1× in this paper · explained in 3 episodes
• Generative Models — 1× in this paper · explained in 2 episodes
• Pruning — 1× in this paper · explained in 4 episodes
• RAG — 1× in this paper · explained in 3 episodes
• Robustness — 1× in this paper · explained in 5 episodes
• Semantic Alignment — 1× in this paper · explained in 3 episodes
• Sparsity — 1× in this paper · explained in 4 episodes
• Trace — 1× in this paper · explained in 2 episodes
• Transfer Learning — 1× in this paper · explained in 10 episodes
• Transferability — 1× in this paper · explained in 4 episodes

Sources

• Fine-grained Analysis of Sentence Embeddings Using Auxiliary Prediction Tasks
• On Identifiability in Transformers
• The Hidden Language of Diffusion Models
• Sparse Autoencoders Find Highly Interpretable Features in Language Models
• SAeUron: Interpretable Concept Unlearning in Diffusion Models with Sparse Autoencoders
• Training-Free Structured Diffusion Guidance for Compositional Text-to-Image Synthesis
• Token Erasure as a Footprint of Implicit Vocabulary Items in LLMs
• Patchscopes: A Unifying Framework for Inspecting Hidden Representations of Language Models
• GenEval: An Object-Focused Framework for Evaluating Text-to-Image Alignment
• Does Liking Yellow Imply Driving a School Bus? Semantic Leakage in Language Models
• From Tokens to Words: On the Inner Lexicon of LLMs
• SuperBPE: Space Travel for Language Models
• GPT-4 Technical Report
• Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
• Adversarial Diffusion Distillation
• RAGDiffusion: Faithful Cloth Generation via External Knowledge Assimilation
• Gemini: A Family of Highly Capable Multimodal Models
• Gemma: Open Models Based on Gemini Research and Technology
• Padding Tone: A Mechanistic Analysis of Padding Tokens in T2I Models
• DeLeaker: Dynamic Inference-Time Reweighting For Semantic Leakage Mitigation in Text-to-Image Models

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering