Copertina

Attention, May I Have Your Decision? Localizing Generative Choices in Diffusion Models

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Zaleska, Katarzyna, Popek, Łukasz, Wysoczańska, Monika, Deja, Kamil
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Computer Vision and Pattern Recognition
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Precise Parameter Localization for Textual Generation in Diffusion Models
di: Staniszewski, Łukasz, et al.
Pubblicazione: (2025)

There and Back Again: On the relation between Noise and Image Inversions in Diffusion Models
di: Staniszewski, Łukasz, et al.
Pubblicazione: (2024)

Low-Rank Continual Personalization of Diffusion Models
di: Staniszewski, Łukasz, et al.
Pubblicazione: (2024)

OVFact: Measuring and Improving Open-Vocabulary Factuality for Long Caption Models
di: Wysoczańska, Monika, et al.
Pubblicazione: (2025)

Mediffusion: Joint Diffusion for Self-Explainable Semi-Supervised Classification and Medical Image Generation
di: Kaleta, Joanna, et al.
Pubblicazione: (2024)

Generative Diffusion Models for Fast Simulations of Particle Collisions at CERN
di: Kita, Mikołaj, et al.
Pubblicazione: (2024)

TADA! Tuning Audio Diffusion Models through Activation Steering
di: Staniszewski, Łukasz, et al.
Pubblicazione: (2026)

Deep Generative Models for Proton Zero Degree Calorimeter Simulations in ALICE, CERN
di: Będkowski, Patryk, et al.
Pubblicazione: (2024)

Boosting Visual Instruction Tuning with Self-Supervised Guidance
di: Sirko-Galouchenko, Sophia, et al.
Pubblicazione: (2026)

Test-time Contrastive Concepts for Open-world Semantic Segmentation with Vision-Language Models
di: Wysoczańska, Monika, et al.
Pubblicazione: (2024)

CLIP-DINOiser: Teaching CLIP a few DINO tricks for open-vocabulary semantic segmentation
di: Wysoczańska, Monika, et al.
Pubblicazione: (2023)

ExpertSim: Fast Particle Detector Simulation Using Mixture-of-Generative-Experts
di: Będkowski, Patryk, et al.
Pubblicazione: (2025)

VideoVerse: Does Your T2V Generator Have World Model Capability to Synthesize Videos?
di: Wang, Zeqing, et al.
Pubblicazione: (2025)

Attention to Neural Plagiarism: Diffusion Models Can Plagiarize Your Copyrighted Images!
di: Zou, Zihang, et al.
Pubblicazione: (2026)

Attention Surgery: An Efficient Recipe to Linearize Your Video Diffusion Transformer
di: Ghafoorian, Mohsen, et al.
Pubblicazione: (2025)

REGLUE Your Latents with Global and Local Semantics for Entangled Diffusion
di: Petsangourakis, Giorgos, et al.
Pubblicazione: (2025)

Exploring Local Memorization in Diffusion Models via Bright Ending Attention
di: Chen, Chen, et al.
Pubblicazione: (2024)

LIME: Localized Image Editing via Attention Regularization in Diffusion Models
di: Simsar, Enis, et al.
Pubblicazione: (2023)

Fast Sampling Through The Reuse Of Attention Maps In Diffusion Models
di: Hunter, Rosco, et al.
Pubblicazione: (2023)

One Last Attention for Your Vision-Language Model
di: Chen, Liang, et al.
Pubblicazione: (2025)

Attention! Your Vision Language Model Could Be Maliciously Manipulated
di: Wang, Xiaosen, et al.
Pubblicazione: (2025)

From Text to Mask: Localizing Entities Using the Attention of Text-to-Image Diffusion Models
di: Xiao, Changming, et al.
Pubblicazione: (2023)

CLUENet: Cluster Attention Makes Neural Networks Have Eyes
di: Song, Xiangshuai, et al.
Pubblicazione: (2025)

Recurrent Autoregressive Diffusion: Global Memory Meets Local Attention
di: Chen, Taiye, et al.
Pubblicazione: (2025)

TIIF-Bench: How Does Your T2I Model Follow Your Instructions?
di: Wei, Xinyu, et al.
Pubblicazione: (2025)

Layout Control and Semantic Guidance with Attention Loss Backward for T2I Diffusion Model
di: Li, Guandong
Pubblicazione: (2024)

MaterialFusion: High-Quality, Zero-Shot, and Controllable Material Transfer with Diffusion Models
di: Garifullin, Kamil, et al.
Pubblicazione: (2025)

Understanding Cell Fate Decisions with Temporal Attention
di: Bürger, Florian, et al.
Pubblicazione: (2026)

How I Met Your Bias: Investigating Bias Amplification in Diffusion Models
di: Roos, Nathan, et al.
Pubblicazione: (2025)

Evolutionary Caching to Accelerate Your Off-the-Shelf Diffusion Model
di: Aggarwal, Anirud, et al.
Pubblicazione: (2025)

TRACE: Your Diffusion Model is Secretly an Instance Edge Detector
di: Jo, Sanghyun, et al.
Pubblicazione: (2025)

Scale Your Instructions: Enhance the Instruction-Following Fidelity of Unified Image Generation Model by Self-Adaptive Attention Scaling
di: Zhou, Chao, et al.
Pubblicazione: (2025)

Rotate Your Character: Revisiting Video Diffusion Models for High-Quality 3D Character Generation
di: Wang, Jin, et al.
Pubblicazione: (2026)

AI-T2I: Aggregating-and-Isolating Cross-Attention to Diffusion Models for Text-to-Image Synthesis
di: Cao, Shipeng, et al.
Pubblicazione: (2026)

LaMamba-Diff: Linear-Time High-Fidelity Diffusion Models Based on Local Attention and Mamba
di: Fu, Yunxiang, et al.
Pubblicazione: (2024)

Training-Free Anomaly Generation via Dual-Attention Enhancement in Diffusion Model
di: Zuo, Zuo, et al.
Pubblicazione: (2025)

Attention to Detail: Global-Local Attention for High-Resolution AI-Generated Image Detection
di: Han, Lawrence
Pubblicazione: (2026)

It's All About Your Sketch: Democratising Sketch Control in Diffusion Models
di: Koley, Subhadeep, et al.
Pubblicazione: (2024)

Swap Attention in Spatiotemporal Diffusions for Text-to-Video Generation
di: Wang, Wenjing, et al.
Pubblicazione: (2023)

Local Action-Guided Motion Diffusion Model for Text-to-Motion Generation
di: Jin, Peng, et al.
Pubblicazione: (2024)