Imagen de Portada

Delta Score Matters! Spatial Adaptive Multi Guidance in Diffusion Models

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Li, Haosen, Chen, Wenshuo, Wang, Lei, Liang, Shaofeng, Tian, Bowen, Lai, Soning, Yue, Yutao
Formato:	Preprint
Publicado:	2026
Materias:	Computer Vision and Pattern Recognition
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Guided Path Sampling: Steering Diffusion Models Back on Track with Principled Path Guidance
por: Li, Haosen, et al.
Publicado: (2025)

POLARIS: Projection-Orthogonal Least Squares for Robust and Adaptive Inversion in Diffusion Models
por: Chen, Wenshuo, et al.
Publicado: (2025)

$Z^2$-Sampling: Zero-Cost Zigzag Trajectories for Semantic Alignment in Diffusion Models
por: Li, Haosen, et al.
Publicado: (2026)

Oracle Noise: Faster Semantic Spherical Alignment for Interpretable Latent Optimization
por: Li, Haosen, et al.
Publicado: (2026)

Learning to Think in Physics: Breaking Shortcut Learning in Scientific Diffusion via Representation Alignment
por: Jia, Haozhe, et al.
Publicado: (2026)

ANT: Adaptive Neural Temporal-Aware Text-to-Motion Model
por: Chen, Wenshuo, et al.
Publicado: (2025)

LUMA: Low-Dimension Unified Motion Alignment with Dual-Path Anchoring for Text-to-Motion Diffusion Model
por: Jia, Haozhe, et al.
Publicado: (2025)

Wolf2Pack: The AutoFusion Framework for Dynamic Parameter Fusion
por: Tian, Bowen, et al.
Publicado: (2024)

Physics-Informed Representation Alignment for Sparse Radio-Map Reconstruction
por: Jia, Haozhe, et al.
Publicado: (2025)

Guarding the Gate: ConceptGuard Battles Concept-Level Backdoors in Concept Bottleneck Models
por: Lai, Songning, et al.
Publicado: (2024)

Free-T2M: Robust Text-to-Motion Generation for Humanoid Robots via Frequency-Domain
por: Chen, Wenshuo, et al.
Publicado: (2025)

RadioFlow: Efficient Radio Map Construction Framework with Flow Matching
por: Jia, Haozhe, et al.
Publicado: (2025)

PEPL: Precision-Enhanced Pseudo-Labeling for Fine-Grained Image Classification in Semi-Supervised Learning
por: Tian, Bowen, et al.
Publicado: (2024)

Improving the Classification Effect of Clinical Images of Diseases for Multi-Source Privacy Protection
por: Bowen, Tian, et al.
Publicado: (2024)

Before the Body Moves: Learning Anticipatory Joint Intent for Language-Conditioned Humanoid Control
por: Jia, Haozhe, et al.
Publicado: (2026)

Adaptive Context Matters: Towards Provable Multi-Modality Guidance for Super-Resolution
por: Luo, Jinyi, et al.
Publicado: (2026)

Learning Quantized Adaptive Conditions for Diffusion Models
por: Liang, Yuchen, et al.
Publicado: (2024)

CoEmoGen: Towards Semantically-Coherent and Scalable Emotional Image Content Generation
por: Yuan, Kaishen, et al.
Publicado: (2025)

Cognitive Disentanglement for Referring Multi-Object Tracking
por: Liang, Shaofeng, et al.
Publicado: (2025)

Data Adaptive Traceback for Vision-Language Foundation Models in Image Classification
por: Peng, Wenshuo, et al.
Publicado: (2024)

Neural Electromagnetic Fields for High-Resolution Material Parameter Reconstruction
por: Chen, Zhe, et al.
Publicado: (2026)

Score-based Membership Inference on Diffusion Models
por: Rao, Mingxing, et al.
Publicado: (2025)

Adaptive Guidance Learning for Camouflaged Object Detection
por: Chen, Zhennan, et al.
Publicado: (2024)

Adaptive and Iterative Point Cloud Denoising with Score-Based Diffusion Model
por: Wang, Zhaonan, et al.
Publicado: (2025)

Normalized Attention Guidance: Universal Negative Guidance for Diffusion Models
por: Chen, Dar-Yen, et al.
Publicado: (2025)

Training-Free Object-Background Compositional T2I via Dynamic Spatial Guidance and Multi-Path Pruning
por: Deng, Yang, et al.
Publicado: (2026)

ECHO: Edge-Cloud Humanoid Orchestration for Language-to-Motion Control
por: Jia, Haozhe, et al.
Publicado: (2026)

Routing Matters in MoE: Scaling Diffusion Transformers with Explicit Routing Guidance
por: Wei, Yujie, et al.
Publicado: (2025)

Adaptive H&E-IHC information fusion staining framework based on feature extra
por: Jia, Yifan, et al.
Publicado: (2025)

Learning New Concepts, Remembering the Old: Continual Learning for Multimodal Concept Bottleneck Models
por: Lai, Songning, et al.
Publicado: (2024)

SPARKE: Scalable Prompt-Aware Diversity and Novelty Guidance in Diffusion Models via RKE Score
por: Jalali, Mohammad, et al.
Publicado: (2025)

DALDA: Data Augmentation Leveraging Diffusion Model and LLM with Adaptive Guidance Scaling
por: Jung, Kyuheon, et al.
Publicado: (2024)

Exploiting the Exact Denoising Posterior Score in Training-Free Guidance of Diffusion Models
por: Bellchambers, Gregory
Publicado: (2025)

Geometric Autoencoder for Diffusion Models
por: Liu, Hangyu, et al.
Publicado: (2026)

DreamWalk: Style Space Exploration using Diffusion Guidance
por: Shu, Michelle, et al.
Publicado: (2024)

Mitigating Spurious Background Bias in Multimedia Recognition with Disentangled Concept Bottlenecks
por: Huang, Gaoxiang, et al.
Publicado: (2025)

Exploring the Potential of Large Foundation Models for Open-Vocabulary HOI Detection
por: Lei, Ting, et al.
Publicado: (2024)

SJD-PAC: Accelerating Speculative Jacobi Decoding via Proactive Drafting and Adaptive Continuation
por: Kang, Jialiang, et al.
Publicado: (2026)

Feedback Guidance of Diffusion Models
por: Koulischer, Felix, et al.
Publicado: (2025)

DRM: Diffusion-based Reward Model With Step-wise Guidance
por: Zhang, Jaxon, et al.
Publicado: (2026)