Cover Image

DeLeaker: Dynamic Inference-Time Reweighting For Semantic Leakage Mitigation in Text-to-Image Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Ventura, Mor, Toker, Michael, Patashnik, Or, Belinkov, Yonatan, Reichart, Roi
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition Artificial Intelligence Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Diffusion Lens: Interpreting Text Encoders in Text-to-Image Pipelines
by: Toker, Michael, et al.
Published: (2024)

NL-Eye: Abductive NLI for Images
by: Ventura, Mor, et al.
Published: (2024)

Editor's Choice: Evaluating Abstract Intent in Image Editing through Atomic Entity Analysis
by: Ventura, Mor, et al.
Published: (2026)

ReFACT: Updating Text-to-Image Models by Editing the Text Encoder
by: Arad, Dana, et al.
Published: (2023)

Padding Tone: A Mechanistic Analysis of Padding Tokens in T2I Models
by: Toker, Michael, et al.
Published: (2025)

MulTaBench: Benchmarking Multimodal Tabular Learning with Text and Image
by: Arazi, Alan, et al.
Published: (2026)

Follow the Flow: On Information Flow Across Textual Tokens in Text-to-Image Models
by: Kaplan, Guy, et al.
Published: (2025)

Navigating Cultural Chasms: Exploring and Unlocking the Cultural POV of Text-To-Image Models
by: Ventura, Mor, et al.
Published: (2023)

Semantic Token Reweighting for Interpretable and Controllable Text Embeddings in CLIP
by: Kim, Eunji, et al.
Published: (2024)

LLMs Know More Than They Show: On the Intrinsic Representation of LLM Hallucinations
by: Orgad, Hadas, et al.
Published: (2024)

Mismatch Quest: Visual and Textual Feedback for Image-Text Misalignment
by: Gordon, Brian, et al.
Published: (2023)

Dynamic Token Reweighting for Robust Vision-Language Models
by: Jiang, Tanqiu, et al.
Published: (2025)

Multi-Head Attention Driven Dynamic Visual-Semantic Embedding for Enhanced Image-Text Matching
by: Chen, Wenjing
Published: (2024)

Emergent Visual-Semantic Hierarchies in Image-Text Representations
by: Alper, Morris, et al.
Published: (2024)

LIBERTy: A Causal Framework for Benchmarking Concept-Based Explanations of LLMs with Structural Counterfactuals
by: Toker, Gilat, et al.
Published: (2026)

Text-guided Image Restoration and Semantic Enhancement for Text-to-Image Person Retrieval
by: Liu, Delong, et al.
Published: (2023)

Semantic Leakage from Image Embeddings
by: Chen, Yiyi, et al.
Published: (2026)

Leveraging NTPs for Efficient Hallucination Detection in VLMs
by: Azachi, Ofir, et al.
Published: (2025)

DeHate: A Stable Diffusion-based Multimodal Approach to Mitigate Hate Speech in Images
by: Dalal, Dwip, et al.
Published: (2025)

Text2Model: Text-based Model Induction for Zero-shot Image Classification
by: Amosy, Ohad, et al.
Published: (2022)

FairImagen: Post-Processing for Bias Mitigation in Text-to-Image Models
by: Fu, Zihao, et al.
Published: (2025)

Leveraging Prototypical Representations for Mitigating Social Bias without Demographic Information
by: Iskander, Shadi, et al.
Published: (2024)

A Dataset for Metaphor Detection in Early Medieval Hebrew Poetry
by: Toker, Michael, et al.
Published: (2024)

ScaleCap: Inference-Time Scalable Image Captioning via Dual-Modality Debiasing
by: Xing, Long, et al.
Published: (2025)

ESREAL: Exploiting Semantic Reconstruction to Mitigate Hallucinations in Vision-Language Models
by: Kim, Minchan, et al.
Published: (2024)

Image2Text2Image: A Novel Framework for Label-Free Evaluation of Image-to-Text Generation with Text-to-Image Diffusion Models
by: Huang, Jia-Hong, et al.
Published: (2024)

ImageInWords: Unlocking Hyper-Detailed Image Descriptions
by: Garg, Roopal, et al.
Published: (2024)

Inside-Out: Hidden Factual Knowledge in LLMs
by: Gekhman, Zorik, et al.
Published: (2025)

Multimodal LLM-Guided Semantic Correction in Text-to-Image Diffusion
by: Lv, Zheqi, et al.
Published: (2025)

LADR: Locality-Aware Dynamic Rescue for Efficient Text-to-Image Generation with Diffusion Large Language Models
by: Wang, Chenglin, et al.
Published: (2026)

TextTIGER: Text-based Intelligent Generation with Entity Prompt Refinement for Text-to-Image Generation
by: Ozaki, Shintaro, et al.
Published: (2025)

Optimizing Prompts for Text-to-Image Generation
by: Hao, Yaru, et al.
Published: (2022)

Backward Lens: Projecting Language Model Gradients into the Vocabulary Space
by: Katz, Shahar, et al.
Published: (2024)

Dynamic Relation Inference via Verb Embeddings
by: Suissa, Omri, et al.
Published: (2025)

ContraSim -- Analyzing Neural Representations Based on Contrastive Learning
by: Rahamim, Adir, et al.
Published: (2023)

Fast Prompt Alignment for Text-to-Image Generation
by: Mrini, Khalil, et al.
Published: (2024)

Vision Language Models Map Logos to Text via Semantic Entanglement in the Visual Projector
by: Li, Sifan, et al.
Published: (2025)

Spatial Semantic Recurrent Mining for Referring Image Segmentation
by: Yang, Jiaxing, et al.
Published: (2024)

SatSynth: Augmenting Image-Mask Pairs through Diffusion Models for Aerial Semantic Segmentation
by: Toker, Aysim, et al.
Published: (2024)

Precision or Recall? An Analysis of Image Captions for Training Text-to-Image Generation Model
by: Cheng, Sheng, et al.
Published: (2024)