Image de couverture de livre

AnchorDiff: Training-Free Concept Grounding for MM-DiTs via Anchor-Based Graph Propagation

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Zhang, Jian, Zhang, Zhijun
Format:	Preprint
Publié:	2026
Sujets:	Computer Vision and Pattern Recognition Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Unveiling Redundancy in Diffusion Transformers (DiTs): A Systematic Study
par: Sun, Xibo, et autres
Publié: (2024)

Rethinking Multi-Condition DiTs: Eliminating Redundant Attention via Position-Alignment and Keyword-Scoping
par: Zhou, Chao, et autres
Publié: (2026)

Beyond Fixed Anchors: Precisely Erasing Concepts with Sibling Exclusive Counterparts
par: Zhang, Tong, et autres
Publié: (2025)

AttAnchor: Guiding Cross-Modal Token Alignment in VLMs with Attention Anchors
par: Zhang, Junyang, et autres
Publié: (2025)

PMG: Progressive Motion Generation via Sparse Anchor Postures Curriculum Learning
par: Xi, Yingjie, et autres
Publié: (2025)

U-DiTs: Downsample Tokens in U-Shaped Diffusion Transformers
par: Tian, Yuchuan, et autres
Publié: (2024)

Q-DiT: Accurate Post-Training Quantization for Diffusion Transformers
par: Chen, Lei, et autres
Publié: (2024)

HeadRouter: A Training-free Image Editing Framework for MM-DiTs by Adaptively Routing Attention Heads
par: Xu, Yu, et autres
Publié: (2024)

HQ-DiT: Efficient Diffusion Transformer with FP4 Hybrid Quantization
par: Liu, Wenxuan, et autres
Publié: (2024)

PANC: Prior-Aware Normalized Cut via Anchor-Augmented Token Graphs
par: Gutiérrez, Juan, et autres
Publié: (2026)

MAP-Diff: Multi-Anchor Guided Diffusion for Progressive 3D Whole-Body Low-Dose PET Denoising
par: Jing, Peiyuan, et autres
Publié: (2026)

TAR-TVG: Enhancing VLMs with Timestamp Anchor-Constrained Reasoning for Temporal Video Grounding
par: Guo, Chaohong, et autres
Publié: (2025)

Remix-DiT: Mixing Diffusion Transformers for Multi-Expert Denoising
par: Fang, Gongfan, et autres
Publié: (2024)

PBADet: A One-Stage Anchor-Free Approach for Part-Body Association
par: Gao, Zhongpai, et autres
Publié: (2024)

ResAF-Net: An Anchor-Free Attention-Based Network for Tree Detection and Agricultural Mapping in Palestine
par: Al-Qasem, Rabee
Publié: (2026)

DragFlow: Unleashing DiT Priors with Region Based Supervision for Drag Editing
par: Zhou, Zihan, et autres
Publié: (2025)

ACPO: Anchor-Constrained Perceptual Optimization for Diffusion Models with No-Reference Quality Guidance
par: Yang, Yang, et autres
Publié: (2026)

Shiva-DiT: Residual-Based Differentiable Top-$k$ Selection for Efficient Diffusion Transformers
par: Zhang, Jiaji, et autres
Publié: (2026)

Language-Driven Anchors for Zero-Shot Adversarial Robustness
par: Li, Xiao, et autres
Publié: (2023)

Bi-Anchor Interpolation Solver for Accelerating Generative Modeling
par: Chen, Hongxu, et autres
Publié: (2026)

AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
par: Wang, Zun, et autres
Publié: (2026)

Ortho-Hydra: Orthogonalized Experts for DiT LoRA
par: Ji, Seunghyun
Publié: (2026)

RobuQ: Pushing DiTs to W1.58A2 via Robust Activation Quantization
par: Yang, Kaicheng, et autres
Publié: (2025)

EPiC: Efficient Video Camera Control Learning with Precise Anchor-Video Guidance
par: Wang, Zun, et autres
Publié: (2025)

Training-Free Acceleration of ViTs with Delayed Spatial Merging
par: Heo, Jung Hwan, et autres
Publié: (2023)

MM-Diff: High-Fidelity Image Personalization via Multi-Modal Condition Integration
par: Wei, Zhichao, et autres
Publié: (2024)

CLASP: Cross-modal Salient Anchor-based Semantic Propagation for Weakly-supervised Dense Audio-Visual Event Localization
par: Zhou, Jinxing, et autres
Publié: (2025)

Untwisting RoPE: Frequency Control for Shared Attention in DiTs
par: Mikaeili, Aryan, et autres
Publié: (2026)

MMFace-DiT: A Dual-Stream Diffusion Transformer for High-Fidelity Multimodal Face Generation
par: Krishnamurthy, Bharath, et autres
Publié: (2026)

DC-DiT: Adaptive Compute and Elastic Inference for Visual Generation via Dynamic Chunking
par: Haridas, Akash, et autres
Publié: (2026)

AnchorFlow: Training-Free 3D Editing via Latent Anchor-Aligned Flows
par: Zhou, Zhenglin, et autres
Publié: (2025)

VQ4DiT: Efficient Post-Training Vector Quantization for Diffusion Transformers
par: Deng, Juncan, et autres
Publié: (2024)

AG-VAS: Anchor-Guided Zero-Shot Visual Anomaly Segmentation with Large Multimodal Models
par: Qu, Zhen, et autres
Publié: (2026)

Why Do DiT Editors Drift? Plug-and-Play Low Frequency Alignment in VAE Latent Space
par: Wang, Xiaoce, et autres
Publié: (2026)

Handling Spatial-Temporal Data Heterogeneity for Federated Continual Learning via Tail Anchor
par: Yu, Hao, et autres
Publié: (2024)

BAMI: Training-Free Bias Mitigation in GUI Grounding
par: Zhang, Borui, et autres
Publié: (2026)

Proxy-Anchor and EVT-Driven Continual Learning Method for Generalized Category Discovery
par: Fathalizadeh, Alireza, et autres
Publié: (2025)

Segmenting Visuals With Querying Words: Language Anchors For Semi-Supervised Image Segmentation
par: Nadeem, Numair, et autres
Publié: (2025)

MeshCraft: Exploring Efficient and Controllable Mesh Generation with Flow-based DiTs
par: He, Xianglong, et autres
Publié: (2025)

SimO Loss: Anchor-Free Contrastive Loss for Fine-Grained Supervised Contrastive Learning
par: Bouhsine, Taha, et autres
Publié: (2024)