SVDQuant: Absorbing Outliers by Low-Rank Component for 4-Bit Diffusion Models
Muyang Li, Yujun Lin, Zhekai Zhang, Tianle Cai, Xiuyu Li, Junxian Guo, Enze Xie, Chenlin Meng, Jun-Yan Zhu, Song Han
摘要
Prompt: a cyberpunk cat holding a huge neon sign that says "SVDQuant is lite and fast", wearing fancy goggles and a black leather jacket.
问 Lune
尽管问，回答会引用原文。
Lune 会读完全文和相关的 Paper，每个回答都附上所依据的原文段落。
引用它的顶会 Paper5
- Radial Attention: 𝒪(n log n) Sparse Attention with Energy Decay for Long Video GenerationXingyang Li, Muyang Li, Tianle Cai, Haocheng Xi 等NeurIPS 2025 · 66 次引用
- HierarchicalPrune: Position-Aware Compression for Large-Scale Diffusion ModelsYoung D. Kwon, Rui Li, Sijia Li, Da Li 等AAAI 2026 · 5 次引用
- Are Image-to-Video Models Good Zero-Shot Image Editors?Zechuan Zhang, Zhenyuan Chen, Zongxin Yang, Yi YangCVPR 2026 · 4 次引用
- QuEPT: Quantized Elastic Precision Transformers with One-Shot Calibration for Multi-Bit SwitchingKe Xu, Yixin Wang, Zhongcheng Li, Hao Cui 等AAAI 2026
- RAPID: Reusing Attention Sparsity with Inter-step Adaptation for Efficient Video DiffusionShangran Lin, Lu Lu, Jian Chen, Qiang LiuCVPR 2026
它引用的 Paper56
- Learning Transferable Visual Models From Natural Language SupervisionAlec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh 等ICML 2021 · 47,906 次引用
- Denoising Diffusion Probabilistic ModelsJonathan Ho, Ajay Jain, Pieter AbbeelNeurIPS 2020 · 35,902 次引用
- LoRA: Low-Rank Adaptation of Large Language ModelsEdward J. Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu 等ICLR 2022 · 18,833 次引用
- High-Resolution Image Synthesis with Latent Diffusion ModelsRobin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser 等CVPR 2022 · 13,123 次引用
- Adding Conditional Control to Text-to-Image Diffusion ModelsLvmin Zhang, Anyi Rao, Maneesh AgrawalaICCV 2023 · 6,759 次引用
相关 Paper
- SnapGen-V: Generating a Five-Second Video within Five Seconds on a Mobile DeviceYushu Wu, Zhixing Zhang, Yanyu Li, Yanwu Xu 等CVPR 2025
- S2Q-VDiT: Accurate Quantized Video Diffusion Transformer with Salient Data and Sparse Token DistillationWeilun Feng, Haotong Qin, Chuanguang Yang, Xiangqi Li 等NeurIPS 2025 · 1 次引用
- Beyond Simple Edits: X-Planner for Complex Instruction-Based Image EditingChun-Hsiao Yeh, Yilin Wang, Nanxuan Zhao, Richard Zhang 等AAAI 2026
- Align Your Latents: High-Resolution Video Synthesis with Latent Diffusion ModelsAndreas Blattmann, Robin Rombach, Huan Ling, Tim Dockhorn 等CVPR 2023
- RAVE: Randomized Noise Shuffling for Fast and Consistent Video Editing with Diffusion ModelsOzgur Kara, Bariscan Kurtkaya, Hidir Yesiltepe, James M. Rehg 等CVPR 2024
