YX
Yuanjun Xiong
cs.CVcs.LGcs.AIcs.CLcs.MMcs.GRcs.CYcs.DCcs.ITeess.IV
On Valency
published · living versionsW_hcxxvb56·v1 · currentpublished
EditAgent: Rethinking Agentic Image Editing
with Haiyang Xu, Tianyu Wang, Jialu Li, Jiteng Mu +3
1 version
Preprints & journals
58 papers in the corpus · 2014–2026ShellElastic: Scalable Elastic Pretraining with Simultaneous Maximal Updates and Hyperparameter Transfer2610.15124v1 · Can Jin, Yan Kang, Yifan Gong et al.2026 · 0 citationsarXiv
On the Diffusibility of High-Dimensional Latents2609.28473v1 · Chao Feng, Zhiyang Xu, Bowei Chen et al.2026 · 0 citationsarXiv
Complete-muE: Optimal Hyperparameter Transfer and Scaling for MoE Models2605.23893v2 · Hongwu Peng, Ohiremen Dibua, Yuanjun Xiong et al.2026 · 0 citationsarXiv
Soft Tail-dropping for Adaptive Visual Tokenization2601.14246v1 · Zeyuan Chen, Kai Zhang, Zhuowen Tu et al.2026 · 0 citationsarXiv
RAR: Retrieving And Ranking Augmented MLLMs for Visual Recognition.41525633 · Liu, Ziyu, Sun, Zeyi, Zang, Yuhang et al.2026 · 5 citationsIEEE transactions on image processing : a publication of the IEEE Signal Processing Society. 2026;PP
AlignTok: Aligning Visual Foundation Encoders to Tokenizers for Diffusion Models2509.25162v2 · Bowei Chen, Sai Bi, Hao Tan et al.2025 · 0 citationsarXiv
KnapFormer: An Online Load Balancer for Efficient Diffusion Transformers Training2508.06001v1 · Kai Zhang, Peng Wang, Sai Bi et al.2025 · 0 citationsarXiv
X-Prompt: Towards Universal In-Context Image Generation in Auto-Regressive Vision Language Foundation Models2412.01824v2 · Zeyi Sun, Ziyang Chu, Pan Zhang et al.2024 · 0 citationsarXiv
MIA-DPO: Multi-Image Augmented Direct Preference Optimization For Large Vision-Language Models2410.17637v1 · Ziyu Liu, Yuhang Zang, Xiaoyi Dong et al.2024 · 0 citationsarXiv
MMDU: A Multi-Turn Multi-Image Dialog Understanding Benchmark and Instruction-Tuning Dataset for LVLMs2406.11833v2 · Ziyu Liu, Tao Chu, Yuhang Zang et al.2024 · 8 citationsarXiv
RetinaGS: Scalable Training for Dense Scene Rendering with Billion-Scale 3D Gaussians2406.11836v2 · Bingling Li, Shengyi Chen, Luchao Wang et al.2024 · 0 citationsarXiv
Image and Video Tokenization with Binary Spherical Quantization2406.07548v1 · Yue Zhao, Yuanjun Xiong, Philipp Krahenbuhl2024 · 0 citationsarXiv
Bootstrap3D: Improving Multi-view Diffusion Model with Synthetic Data2406.00093v2 · Zeyi Sun, Tong Wu, Pan Zhang et al.2024 · 1 citationarXiv
A Full-duplex Speech Dialogue Scheme Based On Large Language Models2405.19487v2 · Peng Wang, Songshuo Lu, Yaohua Tang et al.2024 · 2 citationsarXiv
ELODI: Ensemble Logit Difference Inhibition for Positive-Congruent Training.38652615 · Zhao, Yue, Shen, Yantao, Xiong, Yuanjun et al.2024 · 2 citationsIEEE transactions on pattern analysis and machine intelligence. 2024;PP
Alpha-CLIP: A CLIP Model Focusing on Wherever You Want2312.03818v2 · Zeyi Sun, Ye Fang, Tong Wu et al.2023 · 108 citationsarXiv
Towards Regression-Free Neural Networks for Diverse Compute Platforms2209.13740v1 · Rahul Duggal, Hao Zhou, Shuo Yang et al.2022 · 2 citationsarXiv
Mitigating Representation Bias in Action Recognition: Algorithms and Benchmarks2209.09393v1 · Haodong Duan, Yue Zhao, Kai Chen et al.2022 · 4 citationsarXiv
Stochastic Backpropagation: A Memory Efficient Strategy for Training Video Models2203.16755v1 · Feng Cheng, Mingze Xu, Yuanjun Xiong et al.2022 · 11 citationsarXiv
MeMOT: Multi-Object Tracking with Memory2203.16761v1 · Jiarui Cai, Mingze Xu, Wei Li et al.2022 · 258 citationsarXiv
Contrastive Neighborhood Alignment2201.01922v1 · Pengkai Zhu, Zhaowei Cai, Yuanjun Xiong et al.2022 · 3 citationsarXiv
Long Short-Term Transformer for Online Action Detection2107.03377v3 · Mingze Xu, Yuanjun Xiong, Hao Chen et al.2021 · 98 citationsarXiv
Semi-TCL: Semi-Supervised Track Contrastive Representation Learning2107.02396v1 · Wei Li, Yuanjun Xiong, Shuo Yang et al.2021 · 35 citationsarXiv
Learning Hierarchical Graph Neural Networks for Image Clustering2107.01319v2 · Yifan Xing, Tong He, Tianjun Xiao et al.2021 · 35 citationsarXiv
Harnessing Unrecognizable Faces for Improving Face Recognition2106.04112v2 · Siqi Deng, Yuanjun Xiong, Meng Wang et al.2021 · 12 citationsarXiv
SSCAP: Self-supervised Co-occurrence Action Parsing for Unsupervised Temporal Action Segmentation2105.14158v3 · Zhe Wang, Hao Chen, Xinyu Li et al.2021 · 31 citationsarXiv
Compatibility-aware Heterogeneous Visual Search2105.06047v1 · Rahul Duggal, Hao Zhou, Shuo Yang et al.2021 · 20 citationsarXiv
Regression Bugs Are In Your Model! Measuring, Reducing and Analyzing Regressions In NLP Model Updates2105.03048v1 · Yuqing Xie, Yi-an Lai, Yuanjun Xiong et al.2021 · 8 citationsarXiv
TubeR: Tubelet Transformer for Video Action Detection2104.00969v5 · Jiaojiao Zhao, Yanyi Zhang, Xinyu Li et al.2021 · 101 citationsarXiv
CelebA-Spoof Challenge 2020 on Face Anti-Spoofing: Methods and Results2102.12642v2 · Yuanhan Zhang, Zhenfei Yin, Jing Shao et al.2021 · 10 citationsarXiv
DeeperForensics Challenge 2020 on Real-World Face Forgery Detection: Methods and Results2102.09471v1 · Liming Jiang, Zhengkui Guo, Wayne Wu et al.2021 · 6 citationsarXiv
Learning Self-Consistency for Deepfake Detection2012.09311v2 · Tianchen Zhao, Xiang Xu, Mingze Xu et al.2020 · 383 citationsarXiv
A Comprehensive Study of Deep Video Action Recognition2012.06567v1 · Yi Zhu, Xinyu Li, Chunhui Liu et al.2020 · 121 citationsarXiv
Positive-Congruent Training: Towards Regression-Free Model Updates2011.09161v3 · Sijie Yan, Yuanjun Xiong, Kaustav Kundu et al.2020 · 36 citationsarXiv
SMOT: Single-Shot Multi Object Tracking2010.16031v1 · Wei Li, Yuanjun Xiong, Shuo Yang et al.2020 · 10 citationsarXiv
Online Action Detection in Streaming Videos with Time Buffers2010.03016v1 · Bowen Zhang, Hao Chen, Meng Wang et al.2020 · 1 citationarXiv
3D-Aided Data Augmentation for Robust Face Understanding2010.01246v2 · Yifan Xing, Yuanjun Xiong, Wei Xia2020 · 1 citationarXiv
Towards causal benchmarking of bias in face analysis algorithms2007.06570v1 · Guha Balakrishnan, Yuanjun Xiong, Wei Xia et al.2020 · 45 citationsarXiv
On Improving Temporal Consistency for Online Face Liveness Detection2006.06756v1 · Xiang Xu, Yuanjun Xiong, Wei Xia2020 · 1 citationarXiv
Motion Guided 3D Pose Estimation from Videos2004.13985v1 · Jingbo Wang, Sijie Yan, Yuanjun Xiong et al.2020 · 225 citationsarXiv
Omni-sourced Webly-supervised Learning for Video Recognition2003.13042v2 · Haodong Duan, Yue Zhao, Yuanjun Xiong et al.2020 · 95 citationsarXiv
Towards Backward-Compatible Representation Learning2003.11942v3 · Yantao Shen, Yuanjun Xiong, Wei Xia et al.2020 · 75 citationsarXiv
Action recognition with spatial-temporal discriminative filter banks1908.07625v1 · Brais Martinez, Davide Modolo, Yuanjun Xiong et al.2019 · 76 citationsarXiv
WIDER Face and Pedestrian Challenge 2018: Methods and Results1902.06854v1 · Chen Change Loy, Dahua Lin, Wanli Ouyang et al.2019 · 23 citationsarXiv
Temporal Segment Networks for Action Recognition in Videos.30183621 · Wang, Limin, Xiong, Yuanjun, Wang, Zhe et al.2020 · 923 citationsIEEE transactions on pattern analysis and machine intelligence. 2019;41(11):2740-2755
From Trailers to Storylines: An Efficient Way to Learn from Movies1806.05341v1 · Qingqiu Huang, Yuanjun Xiong, Yu Xiong et al.2018 · 15 citationsarXiv
Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination1805.01978v1 · Zhirong Wu, Yuanjun Xiong, Stella Yu et al.2018 · 176 citationsarXiv
Optimizing Video Object Detection via a Scale-Time Lattice1804.05472v1 · Kai Chen, Jiaqi Wang, Shuo Yang et al.2018 · 118 citationsarXiv
Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition1801.07455v2 · Sijie Yan, Yuanjun Xiong, Dahua Lin2018 · 5,396 citationsarXiv
Face Detection through Scale-Friendly Deep Convolutional Networks1706.02863v1 · Shuo Yang, Yuanjun Xiong, Chen Change Loy et al.2017 · 104 citationsarXiv
Career total: 86 works. 58 are in this corpus.Showing the 50 most recent.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.