图像生成

TractShapeNet: Efficient Multi-Shape Learning with 3D Tractography Point Clouds

Yui Lo, Yuqian Chen, Dongnan Liu, Jon Haitz Legarreta, Leo Zekelman, Fan Zhang, Jarrett Rushmore, Yogesh Rathi, Nikos Makris, Alexandra J. Golby, Weidong Cai, Lauren J. O'Donnell

专题命中 效率与蒸馏 ：diffusion(abstract)；分类 cs.CV

Comments 10 pages, 2 figures, 4 tables. This work has been accepted to 2025 IEEE 22nd International Symposium on Biomedical Imaging (ISBI)

GMem: A Modular Approach for Ultra-Efficient Generative Models

Yi Tang, Peng Sun, Zhenglin Cheng, Tao Lin

专题命中 效率与蒸馏 ：diffusion(abstract)；分类 cs.CV

Comments 9 pages, 5 figures, 3 tables

Optimizing Knowledge Distillation in Transformers: Enabling Multi-Head Attention without Alignment Barriers

Zhaodong Bing, Linze Li, Jiajun Liang

专题命中 效率与蒸馏 ：image generation(abstract)；分类 cs.CV

QLIP: Text-Aligned Visual Tokenization Unifies Auto-Regressive Multimodal Understanding and Generation

Yue Zhao, Fuzhao Xue, Scott Reed, Linxi Fan, Yuke Zhu, Jan Kautz, Zhiding Yu, Philipp Krähenbühl, De-An Huang

专题命中 效率与蒸馏 ：image generation(abstract)；分类 cs.CV

Comments Tech report. Project page: https://nvlabs.github.io/QLIP/

UniCP: A Unified Caching and Pruning Framework for Efficient Video Generation

Wenzhang Sun, Qirui Hou, Donglin Di, Jiahui Yang, Yongjia Ma, Jianxun Cui

专题命中 效率与蒸馏 ：diffusion(abstract)；分类 cs.CV

A Survey of Sample-Efficient Deep Learning for Change Detection in Remote Sensing: Tasks, Strategies, and Challenges

Lei Ding, Danfeng Hong, Maofan Zhao, Hongruixuan Chen, Chenyu Li, Jie Deng, Naoto Yokoya, Lorenzo Bruzzone, Jocelyn Chanussot

专题命中 效率与蒸馏 ：image generation(abstract)；分类 cs.CV

Comments Accepted in IEEE GRSM

AdaFV: Rethinking of Visual-Language alignment for VLM acceleration

Jiayi Han, Liang Du, Yiwen Wu, Xiangguo Zhou, Hongwei Du, Weibo Zheng

专题命中 效率与蒸馏 ：text-to-image(abstract)；分类 cs.CV

Comments 14 pages, 9 figures

On Computational Limits and Provably Efficient Criteria of Visual Autoregressive Models: A Fine-Grained Complexity Analysis

Yekun Ke, Xiaoyu Li, Yingyu Liang, Zhizhou Sha, Zhenmei Shi, Zhao Song

专题命中 效率与蒸馏 ：image generation(abstract)；分类 cs.CV

Counterfactuals and Uncertainty-Based Explainable Paradigm for the Automated Detection and Segmentation of Renal Cysts in Computed Tomography Images: A Multi-Center Study

Zohaib Salahuddin, Abdalla Ibrahim, Sheng Kuang, Yousif Widaatalla, Razvan L. Miclea, Oliver Morin, Spencer Behr, Marnix P. M. Kop, Tom Marcelissen, Patricia Zondervan, Auke Jager, Philippe Lambin, Henry C Woodruff

专题命中 效率与蒸馏 ：image generation(abstract)；分类 cs.CV

Dissecting Bit-Level Scaling Laws in Quantizing Vision Generative Models

Xin Ding, Shijie Cao, Ting Cao, Zhibo Chen

专题命中 效率与蒸馏 ：diffusion(abstract)；分类 cs.CV

Consistent Flow Distillation for Text-to-3D Generation

Runjie Yan, Yinbo Chen, Xiaolong Wang

专题命中 效率与蒸馏 ：diffusion(abstract)；分类 cs.CV

Comments Project page: https://runjie-yan.github.io/cfd/

ContextMRI: Enhancing Compressed Sensing MRI through Metadata Conditioning

Hyungjin Chung, Dohun Lee, Zihui Wu, Byung-Hoon Kim, Katherine L. Bouman, Jong Chul Ye

专题命中 效率与蒸馏 ：diffusion(abstract)；分类 cs.CV

Comments 29 pages, 9 figures. Code is available at https://github.com/DoHunLee1/ContextMRI

DDIM sampling for Generative AIBIM, a faster intelligent structural design framework

Zhili He, Yu-Hsing Wang

专题命中 效率与蒸馏 ：diffusion(abstract)；分类 cs.CV

Comments the 10th International Conference on Innovative Production and Construction (IPC 2024), Perth, Australia. https://ipcannual.com/proceedings/

Single Trajectory Distillation for Accelerating Image and Video Style Transfer

Sijie Xu, Runqi Wang, Wei Zhu, Dejia Song, Nemo Chen, Xu Tang, Yao Hu

专题命中 效率与蒸馏 ：diffusion(abstract)；分类 cs.CV

TrojFlow: Flow Models are Natural Targets for Trojan Attacks

Zhengyang Qi, Xiaohua Xu

专题命中 效率与蒸馏 ：diffusion(abstract)；分类 cs.CV

Comments 6 pages, 4 figures

Relation-Guided Adversarial Learning for Data-free Knowledge Transfer

Yingping Liang, Ying Fu

专题命中 效率与蒸馏 ：image synthesis(abstract)；分类 cs.CV

Rapid Reconstruction of Extremely Accelerated Liver 4D MRI via Chained Iterative Refinement

Di Xu, Xin Miao, Hengjie Liu, Jessica E. Scholey, Wensha Yang, Mary Feng, Michael Ohliger, Hui Lin, Yi Lao, Yang Yang, Ke Sheng

专题命中 效率与蒸馏 ：diffusion(abstract)；分类 cs.CV

Catch-Up Distillation: You Only Need to Train Once for Accelerating Sampling

Shitong Shao, Xu Dai, Lujun Li, Huanran Chen, Yang Hu, Shouyi Yin

专题命中 效率与蒸馏 ：diffusion(abstract)；分类 cs.CV

EMOv2: Pushing 5M Vision Model Frontier

Jiangning Zhang, Teng Hu, Haoyang He, Zhucun Xue, Yabiao Wang, Chengjie Wang, Yong Liu, Xiangtai Li, Dacheng Tao

专题命中 效率与蒸馏 ：image generation(abstract)；分类 cs.CV

Efficient Continuous Video Flow Model for Video Prediction

Gaurav Shrivastava, Abhinav Shrivastava

专题命中 效率与蒸馏 ：diffusion(abstract)；分类 cs.CV

Mixture of Physical Priors Adapter for Parameter-Efficient Fine-Tuning

Zhaozhi Wang, Conghu Li, Qixiang Ye, Tong Zhang

专题命中 效率与蒸馏 ：diffusion(abstract)；分类 cs.CV

Comments 14 pages, 7 figures, 9 tables

3D representation in 512-Byte:Variational tokenizer is the key for autoregressive 3D generation

Jinzhi Zhang, Feng Xiong, Mu Xu

专题命中 效率与蒸馏 ：image generation(abstract)；分类 cs.CV

Comments 22 pages, 21 figures

Efficient Text-driven Motion Generation via Latent Consistency Training

Mengxian Hu, Minghao Zhu, Xun Zhou, Qingqing Yan, Shu Li, Chengju Liu, Qijun Chen

专题命中 效率与蒸馏 ：diffusion(abstract)；分类 cs.CV

Collaborative Decoding Makes Visual Auto-Regressive Modeling Efficient

Zigeng Chen, Xinyin Ma, Gongfan Fang, Xinchao Wang

专题命中 效率与蒸馏 ：image generation(abstract)；分类 cs.CV

Comments Working in progress. Code repository: https://github.com/czg1225/CoDe

Factorized Visual Tokenization and Generation

Zechen Bai, Jianxiong Gao, Ziteng Gao, Pichao Wang, Zheng Zhang, Tong He, Mike Zheng Shou

专题命中 效率与蒸馏 ：image generation(abstract)；分类 cs.CV

PoM: Efficient Image and Video Generation with the Polynomial Mixer

David Picard, Nicolas Dufour

专题命中 效率与蒸馏 ：diffusion(abstract)；分类 cs.CV

PLA4D: Pixel-Level Alignments for Text-to-4D Gaussian Splatting

Qiaowei Miao, JinSheng Quan, Kehan Li, Yawei Luo

专题命中 效率与蒸馏 ：diffusion(abstract)；分类 cs.CV

BrightDreamer: Generic 3D Gaussian Generative Framework for Fast Text-to-3D Synthesis

Lutao Jiang, Xu Zheng, Yuanhuiyi Lyu, Jiazhou Zhou, Lin Wang

专题命中 效率与蒸馏 ：text-to-image(abstract)；分类 cs.CV

SamRobNODDI: Q-Space Sampling-Augmented Continuous Representation Learning for Robust and Generalized NODDI

Taohui Xiao, Jian Cheng, Wenxin Fan, Enqing Dong, Hairong Zheng, Shanshan Wang

专题命中 效率与蒸馏 ：diffusion(abstract)；分类 cs.CV

Sampling Strategies in Bayesian Inversion: A Study of RTO and Langevin Methods

Remi Laumont, Yiqiu Dong, Martin Skovgaard Andersen

专题命中 效率与蒸馏 ：inpainting(abstract)；分类 cs.CV