Image de couverture de livre

Q-VDiT: Towards Accurate Quantization and Distillation of Video-Generation Diffusion Transformers

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Feng, Weilun, Yang, Chuanguang, Qin, Haotong, Li, Xiangqi, Wang, Yu, An, Zhulin, Huang, Libo, Diao, Boyu, Zhao, Zixiang, Xu, Yongjun, Magno, Michele
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

S$^2$Q-VDiT: Accurate Quantized Video Diffusion Transformer with Salient Data and Sparse Token Distillation
par: Feng, Weilun, et autres
Publié: (2025)

QuantSparse: Comprehensively Compressing Video Diffusion Transformer with Model Quantization and Attention Sparsification
par: Feng, Weilun, et autres
Publié: (2025)

MPQ-DM: Mixed Precision Quantization for Extremely Low Bit Diffusion Models
par: Feng, Weilun, et autres
Publié: (2024)

MPQ-DMv2: Flexible Residual Mixed Precision Quantization for Low-Bit Diffusion Models with Temporal Distillation
par: Feng, Weilun, et autres
Publié: (2025)

Relational Diffusion Distillation for Efficient Image Generation
par: Feng, Weilun, et autres
Publié: (2024)

Quantized Visual Geometry Grounded Transformer
par: Feng, Weilun, et autres
Publié: (2025)

Teacher-Guided Student Self-Knowledge Distillation Using Diffusion Model
par: Wang, Yu, et autres
Publié: (2026)

WorldCache: Accelerating World Models for Free via Heterogeneous Token Caching
par: Feng, Weilun, et autres
Publié: (2026)

CLIP-KD: An Empirical Study of CLIP Model Distillation
par: Yang, Chuanguang, et autres
Publié: (2023)

Echo-Forcing: A Scene Memory Framework for Interactive Long Video Generation
par: Wu, Mingqiang, et autres
Publié: (2026)

Efficient Continual Learning through Frequency Decomposition and Integration
par: Liu, Ruiqi, et autres
Publié: (2025)

Multi-party Collaborative Attention Control for Image Customization
par: Yang, Han, et autres
Publié: (2025)

Parameterized Prompt for Incremental Object Detection
par: An, Zijia, et autres
Publié: (2025)

Online Policy Distillation with Decision-Attention
par: Yu, Xinqiang, et autres
Publié: (2024)

Low-redundancy Distillation for Continual Learning
par: Liu, RuiQi, et autres
Publié: (2023)

PrePrompt: Predictive prompting for class incremental learning
par: Huang, Libo, et autres
Publié: (2025)

Q-SAM2: Accurate Quantization for Segment Anything Model 2
par: Farronato, Nicola, et autres
Publié: (2025)

Continual Learning in the Frequency Domain
par: Liu, Ruiqi, et autres
Publié: (2024)

IOR: Inversed Objects Replay for Incremental Object Detection
par: An, Zijia, et autres
Publié: (2024)

Multi-Teacher Knowledge Distillation with Reinforcement Learning for Visual Recognition
par: Yang, Chuanguang, et autres
Publié: (2025)

Q-MambaIR: Accurate Quantized Mamba for Efficient Image Restoration
par: Chen, Yujie, et autres
Publié: (2025)

SRKD: Towards Efficient 3D Point Cloud Segmentation via Structure- and Relation-aware Knowledge Distillation
par: Li, Yuqi, et autres
Publié: (2025)

Exemplar-Free Class Incremental Learning via Incremental Representation
par: Huang, Libo, et autres
Publié: (2024)

Post-Training Quantization for Video Matting
par: Zhu, Tianrui, et autres
Publié: (2025)

A Nonlinear Hash-based Optimization Method for SpMV on GPUs
par: Yan, Chen, et autres
Publié: (2025)

BinaryDM: Accurate Weight Binarization for Efficient Diffusion Models
par: Zheng, Xingyu, et autres
Publié: (2024)

Dynamical Adapter Fusion: Constructing A Global Adapter for Pre-Trained Model-based Class-Incremental Learning
par: Liu, Ruiqi, et autres
Publié: (2026)

First-Order Error Matters: Accurate Compensation for Quantized Large Language Models
par: Zheng, Xingyu, et autres
Publié: (2025)

ViDiT-Q: Efficient and Accurate Quantization of Diffusion Transformers for Image and Video Generation
par: Zhao, Tianchen, et autres
Publié: (2024)

BiVM: Accurate Binarized Neural Network for Efficient Video Matting
par: Qin, Haotong, et autres
Publié: (2025)

From Isolation to Integration: Building an Adaptive Expert Forest for Pre-Trained Model-based Class-Incremental Learning
par: Liu, Ruiqi, et autres
Publié: (2026)

Frequency-Aligned Knowledge Distillation for Lightweight Spatiotemporal Forecasting
par: Li, Yuqi, et autres
Publié: (2025)

Accurate LoRA-Finetuning Quantization of LLMs via Information Retention
par: Qin, Haotong, et autres
Publié: (2024)

Event-Priori-Based Vision-Language Model for Efficient Visual Understanding
par: Qin, Haotong, et autres
Publié: (2025)

Semantic-Guided Dynamic Sparsification for Pre-Trained Model-based Class-Incremental Learning
par: Liu, Ruiqi, et autres
Publié: (2026)

Q&C: When Quantization Meets Cache in Efficient Image Generation
par: Ding, Xin, et autres
Publié: (2025)

MultiAnimate: Pose-Guided Image Animation Made Extensible
par: Hu, Yingcheng, et autres
Publié: (2026)

DVD-Quant: Data-free Video Diffusion Transformers Quantization
par: Li, Zhiteng, et autres
Publié: (2025)

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

Q-DiT4SR: Exploration of Detail-Preserving Diffusion Transformer Quantization for Real-World Image Super-Resolution
par: Zhang, Xun, et autres
Publié: (2026)