Image de couverture de livre

Temporal Concept Dynamics in Diffusion Models via Prompt-Conditioned Interventions

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Gorgun, Ada, Sammani, Fawaz, Deligiannis, Nikos, Schiele, Bernt, Fischer, Jonas
Format:	Preprint
Publié:	2025
Sujets:	Computer Vision and Pattern Recognition
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

CLIP-Free, Label Free, Unsupervised Concept Bottleneck Models
par: Sammani, Fawaz, et autres
Publié: (2025)

Interpreting and Analysing CLIP's Zero-Shot Image Classification via Mutual Knowledge
par: Sammani, Fawaz, et autres
Publié: (2024)

VITAL: More Understandable Feature Visualization through Distribution Alignment and Relevant Information Flow
par: Gorgun, Ada, et autres
Publié: (2025)

When Negation Is a Geometry Problem in Vision-Language Models
par: Sammani, Fawaz, et autres
Publié: (2026)

FaCT: Faithful Concept Traces for Explaining Neural Network Decisions
par: Parchami-Araghi, Amin, et autres
Publié: (2025)

CFM: Language-aligned Concept Foundation Model for Vision
par: Wittenmayer, Kai, et autres
Publié: (2026)

Interpretable 3D Neural Object Volumes for Robust Conceptual Reasoning
par: Pham, Nhi, et autres
Publié: (2025)

Discover-then-Name: Task-Agnostic Concept Bottlenecks via Automated Concept Discovery
par: Rao, Sukrut, et autres
Publié: (2024)

OrCo: Towards Better Generalization via Orthogonality and Contrast for Few-Shot Class-Incremental Learning
par: Ahmed, Noor, et autres
Publié: (2024)

Optimising for Interpretability: Convolutional Dynamic Alignment Networks
par: Böhle, Moritz, et autres
Publié: (2021)

Certified Circuits: Stability Guarantees for Mechanistic Circuits
par: Anani, Alaa, et autres
Publié: (2026)

Interpretability Without Tradeoffs: Disentangling Polysemanticity At Equal Predictive Performance
par: Bağcı, Doğukan, et autres
Publié: (2026)

DWDN: Deep Wiener Deconvolution Network for Non-Blind Image Deblurring
par: Dong, Jiangxin, et autres
Publié: (2021)

AIM: Amending Inherent Interpretability via Self-Supervised Masking
par: Alshami, Eyad, et autres
Publié: (2025)

Sp2360: Sparse-view 360 Scene Reconstruction using Cascaded 2D Diffusion Priors
par: Paul, Soumava, et autres
Publié: (2024)

Scalable Context-Preserving Model-Aware Deep Clustering for Hyperspectral Images
par: Li, Xianlu, et autres
Publié: (2025)

HowToCaption: Prompting LLMs to Transform Video Annotations at Scale
par: Shvetsova, Nina, et autres
Publié: (2023)

MTR++: Multi-Agent Motion Prediction with Symmetric Scene Modeling and Guided Intention Querying
par: Shi, Shaoshuai, et autres
Publié: (2023)

Rewis3d: Reconstruction Improves Weakly-Supervised Semantic Segmentation
par: Ernst, Jonas, et autres
Publié: (2026)

What is Missing? Explaining Neurons Activated by Absent Concepts
par: Hesse, Robin, et autres
Publié: (2026)

Better Understanding Differences in Attribution Methods via Systematic Evaluations
par: Rao, Sukrut, et autres
Publié: (2023)

Walker: Self-supervised Multiple Object Tracking by Walking on Temporal Appearance Graphs
par: Segu, Mattia, et autres
Publié: (2024)

Towards Better Understanding Attribution Methods
par: Rao, Sukrut, et autres
Publié: (2022)

How to Probe: Simple Yet Effective Techniques for Improving Post-hoc Explanations
par: Gairola, Siddhartha, et autres
Publié: (2025)

ClipTTT: CLIP-Guided Test-Time Training Helps LVLMs See Better
par: Nath, Mriganka, et autres
Publié: (2026)

B-cos Alignment for Inherently Interpretable CNNs and Vision Transformers
par: Böhle, Moritz, et autres
Publié: (2023)

MTA-CLIP: Language-Guided Semantic Segmentation with Mask-Text Alignment
par: Das, Anurag, et autres
Publié: (2024)

X-MIC: Cross-Modal Instance Conditioning for Egocentric Action Generalization
par: Kukleva, Anna, et autres
Publié: (2024)

SSL-R1: Self-Supervised Visual Reinforcement Post-Training for Multimodal Large Language Models
par: Xie, Jiahao, et autres
Publié: (2026)

Number it: Temporal Grounding Videos like Flipping Manga
par: Wu, Yongliang, et autres
Publié: (2024)

PersonaHOI: Effortlessly Improving Personalized Face with Human-Object Interaction Generation
par: Hu, Xinting, et autres
Publié: (2025)

SimNP: Learning Self-Similarity Priors Between Neural Points
par: Wewer, Christopher, et autres
Publié: (2023)

Spatial Reasoning with Denoising Models
par: Wewer, Christopher, et autres
Publié: (2025)

ReferGPT: Towards Zero-Shot Referring Multi-Object Tracking
par: Chamiti, Tzoulio, et autres
Publié: (2025)

Toward a Diffusion-Based Generalist for Dense Vision Tasks
par: Fan, Yue, et autres
Publié: (2024)

Pixel-level Certified Explanations via Randomized Smoothing
par: Anani, Alaa, et autres
Publié: (2025)

Adversarial Training against Location-Optimized Adversarial Patches
par: Rao, Sukrut, et autres
Publié: (2020)

Unbiasing through Textual Descriptions: Mitigating Representation Bias in Video Benchmarks
par: Shvetsova, Nina, et autres
Publié: (2025)

R-CoV: Region-Aware Chain-of-Verification for Alleviating Object Hallucinations in LVLMs
par: Xie, Jiahao, et autres
Publié: (2026)

GATA2Floor: Graph attention for floor counting in street-view facades
par: Le, Ngoc Tan, et autres
Publié: (2026)