Copertina

ConceptAttention: Diffusion Transformers Learn Highly Interpretable Features

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Helbling, Alec, Meral, Tuna Han Salih, Hoover, Ben, Yanardag, Pinar, Chau, Duen Horng
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computer Vision and Pattern Recognition Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

MotionFlow: Attention-Driven Motion Transfer in Video Diffusion Models
di: Meral, Tuna Han Salih, et al.
Pubblicazione: (2024)

MotionShop: Zero-Shot Motion Transfer in Video Diffusion Models with Mixture of Score Guidance
di: Yesiltepe, Hidir, et al.
Pubblicazione: (2024)

Contrastive Test-Time Composition of Multiple LoRA Models for Image Generation
di: Meral, Tuna Han Salih, et al.
Pubblicazione: (2024)

Infinity-RoPE: Action-Controllable Infinite Video Generation Emerges From Autoregressive Self-Rollout
di: Yesiltepe, Hidir, et al.
Pubblicazione: (2025)

Aligning Latent Geometry for Spherical Flow Matching in Image Generation
di: Meral, Tuna Han Salih, et al.
Pubblicazione: (2026)

VideoMLA: Low-Rank Latent KV Cache for Minute-Scale Autoregressive Video Diffusion
di: Yesiltepe, Hidir, et al.
Pubblicazione: (2026)

Diffusion Explorer: Interactive Exploration of Diffusion Models
di: Helbling, Alec, et al.
Pubblicazione: (2025)

ClickDiffusion: Harnessing LLMs for Interactive Precise Image Editing
di: Helbling, Alec, et al.
Pubblicazione: (2024)

From Zero to Hero: Training-Free Custom Concept Spawning in World Models
di: Akdemir, Kiymet, et al.
Pubblicazione: (2026)

LoRAShop: Training-Free Multi-Concept Image Generation and Editing with Rectified Flow Transformers
di: Dalva, Yusuf, et al.
Pubblicazione: (2025)

Effective Guidance for Model Attention with Simple Yes-no Annotations
di: Lee, Seongmin, et al.
Pubblicazione: (2024)

GANTASTIC: GAN-based Transfer of Interpretable Directions for Disentangled Image Editing in Text-to-Image Diffusion Models
di: Dalva, Yusuf, et al.
Pubblicazione: (2024)

Conditional Information Gain Trellis
di: Bicici, Ufuk Can, et al.
Pubblicazione: (2024)

MIST: Mitigating Intersectional Bias with Disentangled Cross-Attention Editing in Text-to-Image Diffusion Models
di: Yesiltepe, Hidir, et al.
Pubblicazione: (2024)

ORACLE: Leveraging Mutual Information for Consistent Character Generation with LoRAs in Diffusion Models
di: Akdemir, Kiymet, et al.
Pubblicazione: (2024)

Explaining in Diffusion: Explaining a Classifier Through Hierarchical Semantics with Text-to-Image Diffusion Models
di: Kazimi, Tahira, et al.
Pubblicazione: (2024)

Self-Supervised Pre-Training for Table Structure Recognition Transformer
di: Peng, ShengYun, et al.
Pubblicazione: (2024)

FluxSpace: Disentangled Semantic Editing in Rectified Flow Transformers
di: Dalva, Yusuf, et al.
Pubblicazione: (2024)

LoRAverse: A Submodular Framework to Retrieve Diverse Adapters for Diffusion Models
di: Sonmezer, Mert, et al.
Pubblicazione: (2025)

Audit & Repair: An Agentic Framework for Consistent Story Visualization in Text-to-Image Diffusion Models
di: Akdemir, Kiymet, et al.
Pubblicazione: (2025)

AdaState: Self-Evolving Anchors for Streaming Video Generation
di: Dalva, Yusuf, et al.
Pubblicazione: (2026)

SafetyPairs: Isolating Safety Critical Image Features with Counterfactual Image Generation
di: Helbling, Alec, et al.
Pubblicazione: (2025)

LoRACLR: Contrastive Adaptation for Customization of Diffusion Models
di: Simsar, Enis, et al.
Pubblicazione: (2024)

Dynamic View Synthesis as an Inverse Problem
di: Yesiltepe, Hidir, et al.
Pubblicazione: (2025)

RAVEL: Rare Concept Generation and Editing via Graph-driven Relational Guidance
di: Venkatesh, Kavana, et al.
Pubblicazione: (2024)

Diverse Video Generation with Determinantal Point Process-Guided Policy Optimization
di: Kazimi, Tahira, et al.
Pubblicazione: (2025)

CREA: A Collaborative Multi-Agent Framework for Creative Image Editing and Generation
di: Venkatesh, Kavana, et al.
Pubblicazione: (2025)

The Curious Case of End Token: A Zero-Shot Disentangled Image Editing using CLIP
di: Yesiltepe, Hidir, et al.
Pubblicazione: (2024)

Personalized Image Editing in Text-to-Image Diffusion Models via Collaborative Direct Preference Optimization
di: Dunlop, Connor, et al.
Pubblicazione: (2025)

Plot'n Polish: Zero-shot Story Visualization and Disentangled Editing with Text-to-Image Diffusion Models
di: Akdemir, Kiymet, et al.
Pubblicazione: (2025)

What Time Is It? How Data Geometry Makes Time Conditioning Optional for Flow Matching
di: Helbling, Alec, et al.
Pubblicazione: (2026)

Semi-Truths: A Large-Scale Dataset of AI-Augmented Images for Evaluating Robustness of AI-Generated Image detectors
di: Pal, Anisha, et al.
Pubblicazione: (2024)

UniTable: Towards a Unified Framework for Table Recognition via Self-Supervised Pretraining
di: Peng, ShengYun, et al.
Pubblicazione: (2024)

Deep Learning-based Average Shear Wave Velocity Prediction using Accelerometer Records
di: Yılmaz, Barış, et al.
Pubblicazione: (2024)

DTG-Restore: Training-Free Diffusion Refinement for Generative Video Super-Resolution
di: Yesiltepe, Hidir, et al.
Pubblicazione: (2026)

Stylebreeder: Exploring and Democratizing Artistic Styles through Text-to-Image Models
di: Zheng, Matthew, et al.
Pubblicazione: (2024)

Concept-Attention Whitening for Interpretable Skin Lesion Diagnosis
di: Hou, Junlin, et al.
Pubblicazione: (2024)

Transformer Explainer: Interactive Learning of Text-Generative Models
di: Cho, Aeree, et al.
Pubblicazione: (2024)

SALAD: Achieve High-Sparsity Attention via Efficient Linear Attention Tuning for Video Diffusion Transformer
di: Fang, Tongcheng, et al.
Pubblicazione: (2026)

ACE: Attentional Concept Erasure in Diffusion Models
di: Carter, Finn
Pubblicazione: (2025)