Xianzhi Du - RankMe

62 papers A* 12A 3B 5C 2Journal 34Unranked 5

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	CHIMERA: Compact Synthetic Data for Generalizable LLM Reasoning. CoRR Xinyu Zhu, Yihao Feng, Yanchao Sun, Xianzhi Du, Pingzhi Li, Olli Saarikivi, Yun Zhu, Yu Meng
2025	J	`jnl`	AXLearn: Modular Large Model Training on Heterogeneous Infrastructure. CoRR Mark Lee, Tom Gunter, Chang Lan, John Peebles, Hanzhi Zhou, Kelvin Zou, Sneha Bangalore, Chung-Cheng Chiu, Nan Du, Xianzhi Du, Philipp Dufter, Ruixuan Hou, Haoshuo Huang, Dongseong Hwang, Xiang Kong, Jinhao Lei, Tao Lei, Meng Li, Li Li, Jiarui Lu, Zhiyun Lu, Yiping Ma, David Qiu, Vivek Rathod, Senyu Tong, Zhucheng Tu, Jianyu Wang, Yongqiang Wang, Zirui Wang, Floris Weers, Sam Wiseman, Guoli Yin, Bowen Zhang, Xiyou Zhou, Danyang Zhuo, Cheng Leong, Ruoming Pang
2025	—	`conf`	CLIP-UP: A Simple and Efficient Mixture-of-Experts CLIP Training Recipe with Sparse Upcycling. EMNLP (Findings) Xinze Wang, Chen Chen, Yinfei Yang, Hong-You Chen, Bowen Zhang, Aditya Pal, Xiangxin Zhu, Xianzhi Du
2025	J	`jnl`	CLIP-UP: A Simple and Efficient Mixture-of-Experts CLIP Training Recipe with Sparse Upcycling. CoRR Xinze Wang, Chen Chen, Yinfei Yang, Hong-You Chen, Bowen Zhang, Aditya Pal, Xiangxin Zhu, Xianzhi Du
2025	J	`jnl`	Finding Fantastic Experts in MoEs: A Unified Study for Expert Dropping Strategies and Observations. CoRR Ajay Jaiswal, Jianyu Wang, Yixiao Li, Pingzhi Li, Tianlong Chen, Zhangyang Wang, Chong Wang, Ruoming Pang, Xianzhi Du
2025	J	`jnl`	IDEA Prune: An Integrated Enlarge-and-Prune Pipeline in Generative Language Model Pretraining. CoRR Yixiao Li, Xianzhi Du, Ajay Jaiswal, Tao Lei, Tuo Zhao, Chong Wang, Jianyu Wang
2025	J	`jnl`	MANZANO: A Simple and Scalable Unified Multimodal Model with a Hybrid Vision Tokenizer. CoRR Yanghao Li, Rui Qian, Bowen Pan, Haotian Zhang, Haoshuo Huang, Bowen Zhang, Jialing Tong, Haoxuan You, Xianzhi Du, Zhe Gan, Hyunjik Kim, Chao Jia, Zhenbang Wang, Yinfei Yang, Mingfei Gao, Zi-Yi Dou, Wenze Hu, Chang Gao, Dongxu Li, Philipp Dufter, Zirui Wang, Guoli Yin, Zhengdong Zhang, Chen Chen, Yang Zhao, Ruoming Pang, Zhifeng Chen
2025	A*	`conf`	MM1.5: Methods, Analysis & Insights from Multimodal LLM Fine-tuning. ICLR Haotian Zhang, Mingfei Gao, Zhe Gan, Philipp Dufter, Nina Wenzel, Forrest Huang, Dhruti Shah, Xianzhi Du, Bowen Zhang, Yanghao Li, Sam Dodge, Keen You, Zhen Yang, Aleksei Timofeev, Mingze Xu, Hong-You Chen, Jean-Philippe Fauconnier, Zhengfeng Lai, Haoxuan You, Zirui Wang, et al.
2024	A*	`conf`	Compressing LLMs: The Truth is Rarely Pure and Never Simple. ICLR Ajay Kumar Jaiswal, Zhe Gan, Xianzhi Du, Bowen Zhang, Zhangyang Wang, Yinfei Yang
2024	A	`conf`	Empowering Unsupervised Domain Adaptation with Large-scale Pre-trained Vision-Language Models. WACV Zhengfeng Lai, Haoping Bai, Haotian Zhang, Xianzhi Du, Jiulong Shan, Yinfei Yang, Chen-Nee Chuah, Meng Cao
2024	A*	`conf`	Ferret: Refer and Ground Anything Anywhere at Any Granularity. ICLR Haoxuan You, Haotian Zhang, Zhe Gan, Xianzhi Du, Bowen Zhang, Zirui Wang, Liangliang Cao, Shih-Fu Chang, Yinfei Yang
2024	A*	`conf`	Guiding Instruction-based Image Editing via Multimodal Large Language Models. ICLR Tsu-Jui Fu, Wenze Hu, Xianzhi Du, William Yang Wang, Yinfei Yang, Zhe Gan
2024	J	`jnl`	MM1.5: Methods, Analysis & Insights from Multimodal LLM Fine-tuning. CoRR Haotian Zhang, Mingfei Gao, Zhe Gan, Philipp Dufter, Nina Wenzel, Forrest Huang, Dhruti Shah, Xianzhi Du, Bowen Zhang, Yanghao Li, Sam Dodge, Keen You, Zhen Yang, Aleksei Timofeev, Mingze Xu, Hong-You Chen, Jean-Philippe Fauconnier, Zhengfeng Lai, Haoxuan You, Zirui Wang, Afshin Dehghan, Peter Grasch, Yinfei Yang
2024	J	`jnl`	MM1: Methods, Analysis & Insights from Multimodal LLM Pre-training. CoRR Brandon McKinzie, Zhe Gan, Jean-Philippe Fauconnier, Sam Dodge, Bowen Zhang, Philipp Dufter, Dhruti Shah, Xianzhi Du, Futang Peng, Floris Weers, Anton Belyi, Haotian Zhang, Karanjeet Singh, Doug Kang, Ankur Jain, Hongyu Hè, Max Schwarzer, Tom Gunter, Xiang Kong, Aonan Zhang, Jianyu Wang, Chong Wang, Nan Du, Tao Lei, Sam Wiseman, Guoli Yin, Mark Lee, Zirui Wang, Ruoming Pang, Peter Grasch, Alexander Toshev, Yinfei Yang
2024	—	`conf`	MM1: Methods, Analysis and Insights from Multimodal LLM Pre-training. ECCV (29) Brandon McKinzie, Zhe Gan, Jean-Philippe Fauconnier, Sam Dodge, Bowen Zhang, Philipp Dufter, Dhruti Shah, Xianzhi Du, Futang Peng, Anton Belyi, Haotian Zhang, Karanjeet Singh, Doug Kang, Hongyu Hè, Max Schwarzer, Tom Gunter, Xiang Kong, Aonan Zhang, Jianyu Wang, Chong Wang, Nan Du, Tao Lei, Sam Wiseman, Mark Lee, Zirui Wang, Ruoming Pang, Peter Grasch, Alexander Toshev, Yinfei Yang
2024	A*	`conf`	MOFI: Learning Image Representations from Noisy Entity Annotated Images. ICLR Wentao Wu, Aleksei Timofeev, Chen Chen, Bowen Zhang, Kun Duan, Shuangning Liu, Yantao Zheng, Jonathon Shlens, Xianzhi Du, Yinfei Yang
2024	J	`jnl`	Revisiting MoE and Dense Speed-Accuracy Comparisons for LLM Training. CoRR Xianzhi Du, Tom Gunter, Xiang Kong, Mark Lee, Zirui Wang, Aonan Zhang, Nan Du, Ruoming Pang
2024	—	`conf`	VeCLIP: Improving CLIP Training via Visual-Enriched Captions. ECCV (42) Zhengfeng Lai, Haotian Zhang, Bowen Zhang, Wentao Wu, Haoping Bai, Aleksei Timofeev, Xianzhi Du, Zhe Gan, Jiulong Shan, Chen-Nee Chuah, Yinfei Yang, Meng Cao
2023	A*	`conf`	AdaMV-MoE: Adaptive Multi-Task Vision Mixture-of-Experts. ICCV Tianlong Chen, Xuxi Chen, Xianzhi Du, Abdullah Rashwan, Fan Yang, Huizhong Chen, Zhangyang Wang, Yeqing Li
2023	J	`jnl`	Compressing LLMs: The Truth is Rarely Pure and Never Simple. CoRR Ajay Jaiswal, Zhe Gan, Xianzhi Du, Bowen Zhang, Zhangyang Wang, Yinfei Yang
2023	J	`jnl`	Ferret: Refer and Ground Anything Anywhere at Any Granularity. CoRR Haoxuan You, Haotian Zhang, Zhe Gan, Xianzhi Du, Bowen Zhang, Zirui Wang, Liangliang Cao, Shih-Fu Chang, Yinfei Yang
2023	J	`jnl`	From Scarcity to Efficiency: Improving CLIP Training via Visual-enriched Captions. CoRR Zhengfeng Lai, Haotian Zhang, Wentao Wu, Haoping Bai, Aleksei Timofeev, Xianzhi Du, Zhe Gan, Jiulong Shan, Chen-Nee Chuah, Yinfei Yang, Meng Cao
2023	J	`jnl`	Guiding Instruction-based Image Editing via Multimodal Large Language Models. CoRR Tsu-Jui Fu, Wenze Hu, Xianzhi Du, William Yang Wang, Yinfei Yang, Zhe Gan
2023	B	`conf`	ISAA: Boost Repair Process by Constructing the Degree Constrained Optimal Repair Tree for Erasure-coded Systems. ICPADS Xianzhi Du, Bing Zhu, Zhihang Deng, Kenneth W. Shum, Weiping Wang
2023	J	`jnl`	Less is More: Removing Text-regions Improves CLIP Training Efficiency and Robustness. CoRR Liangliang Cao, Bowen Zhang, Chen Chen, Yinfei Yang, Xianzhi Du, Wencong Zhang, Zhiyun Lu, Yantao Zheng
2023	J	`jnl`	MOFI: Learning Image Representations from Noisy Entity Annotated Images. CoRR Wentao Wu, Aleksei Timofeev, Chen Chen, Bowen Zhang, Kun Duan, Shuangning Liu, Yantao Zheng, Jonathon Shlens, Xianzhi Du, Zhe Gan, Yinfei Yang
2023	J	`jnl`	Mobile V-MoEs: Scaling Down Vision Transformers via Sparse Mixture-of-Experts. CoRR Erik A. Daxberger, Floris Weers, Bowen Zhang, Tom Gunter, Ruoming Pang, Marcin Eichner, Michael Emmersberger, Yinfei Yang, Alexander Toshev, Xianzhi Du
2022	B	`conf`	A Genetic Algorithm-based Construction of Fractional Repetition Codes. GLOBECOM Zhihang Deng, Bing Zhu, Xianzhi Du, Kenneth W. Shum
2022	—	`conf`	A Simple Single-Scale Vision Transformer for Object Detection and Instance Segmentation. ECCV (10) Wuyang Chen, Xianzhi Du, Fan Yang, Lucas Beyer, Xiaohua Zhai, Tsung-Yi Lin, Huizhong Chen, Jing Li, Xiaodan Song, Zhangyang Wang, Denny Zhou
2022	A*	`conf`	Auto-scaling Vision Transformers without Training. ICLR Wuyang Chen, Wei Huang, Xianzhi Du, Xiaodan Song, Zhangyang Wang, Denny Zhou
2022	J	`jnl`	Auto-scaling Vision Transformers without Training. CoRR Wuyang Chen, Wei Huang, Xianzhi Du, Xiaodan Song, Zhangyang Wang, Denny Zhou
2022	A*	`conf`	Back Razor: Memory-Efficient Transfer Learning by Self-Sparsified Backpropagation. NeurIPS Ziyu Jiang, Xuxi Chen, Xueqin Huang, Xianzhi Du, Denny Zhou, Zhangyang Wang
2022	J	`jnl`	Optimizing Anchor-based Detectors for Autonomous Driving Scenes. CoRR Xianzhi Du, Wei-Chih Hung, Tsung-Yi Lin
2022	A*	`conf`	Provable Stochastic Optimization for Global Contrastive Learning: Small Batch Does Not Harm Performance. ICML Zhuoning Yuan, Yuexin Wu, Zi-Hao Qiu, Xianzhi Du, Lijun Zhang, Denny Zhou, Tianbao Yang
2022	J	`jnl`	Provable Stochastic Optimization for Global Contrastive Learning: Small Batch Does Not Harm Performance. CoRR Zhuoning Yuan, Yuexin Wu, Zi-Hao Qiu, Xianzhi Du, Lijun Zhang, Denny Zhou, Tianbao Yang
2021	J	`jnl`	A Simple Single-Scale Vision Transformer for Object Localization and Instance Segmentation. CoRR Wuyang Chen, Xianzhi Du, Fan Yang, Lucas Beyer, Xiaohua Zhai, Tsung-Yi Lin, Huizhong Chen, Jing Li, Xiaodan Song, Zhangyang Wang, Denny Zhou
2021	J	`jnl`	Dilated SpineNet for Semantic Segmentation. CoRR Abdullah Rashwan, Xianzhi Du, Xiaoqi Yin, Jing Li
2021	J	`jnl`	Revisiting 3D ResNets for Video Recognition. CoRR Xianzhi Du, Yeqing Li, Yin Cui, Rui Qian, Jing Li, Irwan Bello
2021	A*	`conf`	Revisiting ResNets: Improved Training and Scaling Strategies. NeurIPS Irwan Bello, William Fedus, Xianzhi Du, Ekin Dogus Cubuk, Aravind Srinivas, Tsung-Yi Lin, Jonathon Shlens, Barret Zoph
2021	J	`jnl`	Revisiting ResNets: Improved Training and Scaling Strategies. CoRR Irwan Bello, William Fedus, Xianzhi Du, Ekin D. Cubuk, Aravind Srinivas, Tsung-Yi Lin, Jonathon Shlens, Barret Zoph
2021	J	`jnl`	Simple Training Strategies and Model Scaling for Object Detection. CoRR Xianzhi Du, Barret Zoph, Wei-Chih Hung, Tsung-Yi Lin
2021	J	`jnl`	Towards a Unified Foundation Model: Jointly Pre-Training Transformers on Unpaired Images and Text. CoRR Qing Li, Boqing Gong, Yin Cui, Dan Kondratyuk, Xianzhi Du, Ming-Hsuan Yang, Matthew Brown
2020	—	`conf`	Efficient Scale-Permuted Backbone with Learned Resource Distribution. ECCV (23) Xianzhi Du, Tsung-Yi Lin, Pengchong Jin, Yin Cui, Mingxing Tan, Quoc V. Le, Xiaodan Song
2020	J	`jnl`	Efficient Scale-Permuted Backbone with Learned Resource Distribution. CoRR Xianzhi Du, Tsung-Yi Lin, Pengchong Jin, Yin Cui, Mingxing Tan, Quoc V. Le, Xiaodan Song
2020	C	`conf`	FBA-AMNET: Foreground-Background Aware Atrous Multiscale Networks for Stereo Disparity Estimation. ICCE Xianzhi Du, Mostafa El-Khamy, Jungwon Lee
2020	J	`jnl`	Multitask Deep Neural Networks for Tele-Wide Stereo Matching. IEEE Access Mostafa El-Khamy, Haoyu Ren, Xianzhi Du, Jungwon Lee
2020	A*	`conf`	SpineNet: Learning Scale-Permuted Backbone for Recognition and Localization. CVPR Xianzhi Du, Tsung-Yi Lin, Pengchong Jin, Golnaz Ghiasi, Mingxing Tan, Yin Cui, Quoc V. Le, Xiaodan Song
2019	J	`jnl`	AMNet: Deep Atrous Multiscale Stereo Disparity Estimation Networks. CoRR Xianzhi Du, Mostafa El-Khamy, Jungwon Lee
2019	B	`conf`	Boundary-sensitive Network for Portrait Segmentation. FG Xianzhi Du, Xiaolong Wang, Dawei Li, Jingwen Zhu, Serafettin Tasci, Cameron Upright, Stephen Walsh, Larry S. Davis
2019	B	`conf`	Multi-Task Learning of Depth from Tele and Wide Stereo Image Pairs. ICIP Mostafa El-Khamy, Xianzhi Du, Haoyu Ren, Jungwon Lee
2019	J	`jnl`	SpineNet: Learning Scale-Permuted Backbone for Recognition and Localization. CoRR Xianzhi Du, Tsung-Yi Lin, Pengchong Jin, Golnaz Ghiasi, Mingxing Tan, Yin Cui, Quoc V. Le, Xiaodan Song
2019	J	`jnl`	TW-SMNet: Deep Multitask Learning of Tele-Wide Stereo Matching. CoRR Mostafa El-Khamy, Haoyu Ren, Xianzhi Du, Jungwon Lee
2018	J	`jnl`	Fused Deep Neural Networks for Efficient Pedestrian Detection. CoRR Xianzhi Du, Mostafa El-Khamy, Vlad I. Morariu, Jungwon Lee, Larry S. Davis
2017	J	`jnl`	Boundary-sensitive Network for Portrait Segmentation. CoRR Xianzhi Du, Xiaolong Wang, Dawei Li, Jingwen Zhu, Serafettin Tasci, Cameron Upright, Stephen Walsh, Larry S. Davis
2017	—	`—`	Computer Vision and Deep Learning with Applications to Object Detection, Segmentation, and Document Analysis. Xianzhi Du
2017	C	`conf`	Cyber-physical system enabled nearby traffic flow modelling for autonomous vehicles. IPCCC Baiyu Chen, Zhengyu Yang, Siyu Huang, Xianzhi Du, Zhiwei Cui, Janki Bhimani, Xin Xie, Ningfang Mi
2017	A	`conf`	Fused DNN: A Deep Neural Network Fusion Approach to Fast and Robust Pedestrian Detection. WACV Xianzhi Du, Mostafa El-Khamy, Jungwon Lee, Larry S. Davis
2016	J	`jnl`	Fused DNN: A deep neural network fusion approach to fast and robust pedestrian detection. CoRR Xianzhi Du, Mostafa El-Khamy, Jungwon Lee, Larry S. Davis
2015	A*	`conf`	A graphical model approach for matching partial signatures. CVPR Xianzhi Du, David S. Doermann, Wael Abd-Almageed
2014	B	`conf`	Signature Matching Using Supervised Topic Models. ICPR Xianzhi Du, David S. Doermann, Wael Abd-Almageed
2013	A	`conf`	Large-Scale Signature Matching Using Multi-stage Hashing. ICDAR Xianzhi Du, Wael Abd-Almageed, David S. Doermann
2011	J	`jnl`	A Novel Wideband Spatial Power Combining Amplifier Based on Turnstile-Junction Waveguide Divider/Combiner. IEICE Trans. Electron. Haiyan Jin, Xianzhi Du, Fulin Xiao, Guangjun Wen