🧑‍🔬 Saining Xie — all works

86 works · ← Saining Xie

1. Momentum Contrast for Unsupervised Visual Representation LearningIEEE Computer Society Conference on Computer Vision and Pattern RecognitionKaiming He, Haoqi Fan, Yuxin Wu, et al.2019 · 13,302 citations
2. Aggregated Residual Transformations for Deep Neural Networks ↗IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yetSaining Xie et al.2017 · 12,133 citations
3. A ConvNet for the 2020s ↗IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yetZhuang Liu et al.2022 · 8,531 citations
4. Holistically-Nested Edge Detection ↗IEEE International Conference on Computer Vision (ICCV) · no summary yetSaining Xie, Zhuowen Tu A2015 · 3,162 citations
5. Scalable Diffusion Models with TransformersIEEE/CVF International Conference on Computer Vision (ICCV)William Peebles, Saining Xie2022 · 2,670 citations
6. ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders ↗IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yetSanghyun Woo et al.2023 · 1,708 citations
7. An Empirical Study of Training Self-Supervised Vision Transformers ↗IEEE/CVF International Conference on Computer Vision (ICCV) · no summary yetXinlei Chen, Saining Xie, Kaiming He2021 · 1,658 citations
8. Rethinking Spatiotemporal Feature Learning: Speed-Accuracy Trade-offs in Video Classification ↗Lecture notes in computer science · no summary yetSaining Xie et al.2018 · 1,494 citations
9. Deeply-Supervised Nets ↗arXiv (Cornell University) · no summary yetChen‐Yu Lee et al.2014 · 1,062 citations
10. Holistically-Nested Edge Detection ↗International Journal of Computer Vision · no summary yetSaining Xie, Zhuowen Tu A2017 · 679 citations
11. PointContrast: Unsupervised Pre-training for 3D Point Cloud Understanding ↗Lecture notes in computer science · no summary yetSaining Xie et al.2020 · 621 citations
12. Masked Autoencoders Are Scalable Vision LearnersarXiv:2111.06377Kaiming He, Xinlei Chen, Saining Xie, et al.2021 · 596 citations
13. Masked Feature Prediction for Self-Supervised Visual Pre-Training ↗IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yetChen Wei et al.2022 · 595 citations
14. Exploring Randomly Wired Neural Networks for Image Recognition ↗IEEE/CVF International Conference on Computer Vision (ICCV) · no summary yetSaining Xie et al.2019 · 365 citations
15. FBNetV2: Differentiable Neural Architecture Search for Spatial and Channel Dimensions ↗IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yetAlvin Wan et al.2020 · 345 citations
16. Attentional ShapeContextNet for Point Cloud Recognition ↗IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yetSaining Xie et al.2018 · 345 citations
17. Eyes Wide Shut? Exploring the Visual Shortcomings of Multimodal LLMsIEEE Computer Society Conference on Computer Vision and Pattern RecognitionShengbang Tong, Zhuang Liu, Yuexiang Zhai, et al.2024 · 321 citations
18. SLIP: Self-supervision Meets Language-Image Pre-training ↗Lecture notes in computer science · no summary yetNorman Mu et al.2022 · 301 citations
19. Exploring Data-Efficient 3D Scene Understanding with Contrastive Scene Contexts ↗IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yetJi Hou et al.2021 · 287 citations
20. Decoupling Representation and Classifier for Long-Tailed Recognition ↗arXiv (Cornell University) · no summary yetBingyi Kang et al.2019 · 257 citations
21. Thinking in Space: How Multimodal Large Language Models See, Remember, and Recall Spaces ↗arXiv:2412.14171 · no summary yetJihan Yang et al.2024 · 182 citations
22. Hyper-class augmented and regularized deep learning for fine-grained image classification ↗IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yetSaining Xie et al.2015 · 171 citations
23. SiT: Exploring Flow and Diffusion-Based Generative Models with Scalable Interpolant Transformers ↗Lecture notes in computer science · no summary yetNanye Ma et al.2024 · 163 citations
24. SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-trainingarXiv:2501.17161Tianzhe Chu, Yuexiang Zhai, Jihan Yang, et al.2025 · 160 citations
25. V*: Guided Visual Search as a Core Mechanism in Multimodal LLMs ↗arXiv:2312.14135 · no summary yetPenghao Wu, Saining Xie2023 · 152 citations
26. On Network Design Spaces for Visual Recognition ↗IEEE/CVF International Conference on Computer Vision (ICCV) · no summary yetIlija Radosavovic et al.2019 · 128 citations
27. Benchmarking Detection Transfer Learning with Vision Transformers ↗arXiv (Cornell University) · no summary yetYanghao Li et al.2021 · 86 citations
28. Are Labels Necessary for Neural Architecture Search? ↗Lecture notes in computer science · no summary yetChenxi Liu et al.2020 · 71 citations
29. Fine-Tuning Large Vision-Language Models as Decision-Making Agents via Reinforcement Learning ↗neural information processing systems · no summary yetYuexiang Zhai et al.2024 · 65 citations
30. Demystifying CLIP Data ↗arXiv (Cornell University) · no summary yetXu Hu et al.2023 · 64 citations
31. Pri3D: Can 3D Priors Help 2D Representation Learning? ↗IEEE/CVF International Conference on Computer Vision (ICCV) · no summary yetJi Hou et al.2021 · 62 citations
32. Sample-Efficient Neural Architecture Search by Learning Actions for Monte Carlo Tree Search ↗IEEE Transactions on Pattern Analysis and Machine Intelligence · no summary yetLinnan Wang et al.2021 · 55 citations
33. Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think ↗arXiv (Cornell University) · no summary yetSihyun Yu et al.2024 · 52 citations
34. Going Denser with Open-Vocabulary Part Segmentation ↗IEEE/CVF International Conference on Computer Vision (ICCV) · no summary yetPeize Sun et al.2023 · 52 citations
35. MetaMorph: Multimodal Understanding and Generation via Instruction Tuning ↗IEEE/CVF International Conference on Computer Vision (ICCV) · no summary yetShengbang Tong et al.2025 · 47 citations
36. On Scaling Up 3D Gaussian Splatting Training ↗arXiv:2406.18533 · no summary yetHexu Zhao et al.2024 · 47 citations
37. Combining Factorization Model and Additive Forest for Collaborative Followee Recommendation ↗no summary yetTianqi Chen et al.2012 · 44 citations
38. Top-Down Learning for Structured Labeling with Convolutional Pseudoprior ↗Lecture notes in computer science · no summary yetSaining Xie, Xun Huang, Zhuowen Tu A2016 · 40 citations
39. Sample-Efficient Neural Architecture Search by Learning Action Space ↗arXiv (Cornell University) · no summary yetLinnan Wang et al.2019 · 35 citations
40. BLIP3-o: A Family of Fully Open Unified Multimodal Models-Architecture, Training and Dataset ↗arXiv (Cornell University) · no summary yetJiuhai Chen et al.2025 · 33 citations
41. REPA-E: Unlocking VAE for End-to-End Tuning with Latent Diffusion Transformers ↗IEEE/CVF International Conference on Computer Vision (ICCV) · no summary yetXingjian Leng et al.2025 · 26 citations
42. Pairwise constrained concept factorization for data representation ↗Neural Networks · no summary yetYangcheng He et al.2013 · 26 citations
43. Deconstructing Denoising Diffusion Models for Self-Supervised Learning ↗arXiv (Cornell University) · no summary yetXinlei Chen et al.2024 · 25 citations
44. Image Sculpting: Precise Object Editing with 3D Geometry Control ↗IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yetJiraphon Yenphraphai et al.2024 · 23 citations
45. V-IRL: Grounding Virtual Intelligence in Real Life ↗Lecture notes in computer science · no summary yetJihan Yang et al.2024 · 19 citations
46. Scaling Inference Time Compute for Diffusion Models ↗IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yetNanye Ma et al.2025 · 18 citations
47. Semi-supervised non-negative matrix factorization for image clustering with graph Laplacian ↗Multimedia Tools and Applications · no summary yetYangcheng He, Hongtao Lu, Saining Xie2013 · 18 citations
48. AuroraCap: Efficient, Performant Video Detailed Captioning and a New Benchmark ↗arXiv (Cornell University) · no summary yetWenhao Chai et al.2024 · 17 citations
49. CiT: Curation in Training for Effective Vision-Language Data ↗IEEE/CVF International Conference on Computer Vision (ICCV) · no summary yetXu Hu et al.2023 · 17 citations
50. Inference-Time Scaling for Diffusion Models beyond Scaling Denoising Steps ↗arXiv (Cornell University) · no summary yetNanye Ma et al.2025 · 16 citations
51. MoDE: CLIP Data Experts via Clustering ↗IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yetJiawei Ma et al.2024 · 15 citations
52. On Interaction Between Augmentations and Corruptions in Natural Corruption Robustness ↗arXiv (Cornell University) · no summary yetEric Mintun, Kirillov, Alexander, Saining Xie2021 · 12 citations
53. Order-Aware Generative Modeling Using the 3D-Craft Dataset ↗IEEE/CVF International Conference on Computer Vision (ICCV) · no summary yetZhuoyuan Chen et al.2019 · 12 citations
54. MindCube: Spatial Mental Modeling from Limited Views ↗arXiv (Cornell University) · no summary yetWang, Qineng et al.2025 · 11 citations
55. Cambrian-S: Towards Spatial Supersensing in Video ↗arXiv (Cornell University) · no summary yetShusheng Yang et al.2025 · 11 citations
56. Meta CLIP 2: A Worldwide Scaling Recipe ↗neural information processing systems · no summary yetYung-Sung Chuang et al.2025 · 10 citations
57. Scaling Text-to-Image Diffusion Transformers with Representation Autoencoders ↗arXiv (Cornell University) · no summary yetShengbang Tong et al.2026 · 9 citations
58. Exploring Long-Sequence Masked Autoencoders ↗arXiv (Cornell University) · no summary yetRonghang Hu et al.2022 · 9 citations
59. A Fistful of Words: Learning Transferable Visual Models from Bag-of-Words Supervision ↗arXiv (Cornell University) · no summary yetAjinkya Tejankar et al.2021 · 7 citations
60. Beyond Language Modeling: An Exploration of Multimodal Pretraining ↗arXiv (Cornell University) · no summary yetShengbang Tong et al.2026 · 6 citations
61. SIMS-V: Simulated Instruction-Tuning for Spatial Video Understanding ↗arXiv (Cornell University) · no summary yetEllis Brown et al.2025 · 6 citations
62. Altogether: Image Captioning via Re-aligning Alt-text ↗Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing · no summary yetHu Xu et al.2024 · 6 citations
63. Image Generators are Generalist Vision Learners ↗arXiv (Cornell University) · no summary yetValentin Gabeur et al.2026 · 5 citations
64. Solaris: Building a Multiplayer Video World Model in Minecraft ↗arXiv (Cornell University) · no summary yetGeorgy Savva et al.2026 · 5 citations
65. Benchmark Designers Should "Train on the Test Set" to Expose Exploitable Non-Visual Shortcuts ↗arXiv (Cornell University) · no summary yetEllis Brown et al.2025 · 5 citations
66. Science-T2I: Addressing Scientific Illusions in Image Synthesis ↗IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yetJialuo Li et al.2025 · 5 citations
67. Exploring the Deep Fusion of Large Language Models and Diffusion Transformers for Text-to-Image Synthesis ↗IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yetBingda Tang et al.2025 · 5 citations
68. Fast Encoding and Decoding for Implicit Video Representation ↗Lecture notes in computer science · no summary yetHao Chen et al.2024 · 5 citations
69. Improved Baselines with Representation Autoencoders ↗arXiv (Cornell University) · no summary yetJaskirat Singh et al.2026 · 4 citations
70. Neural Architecture Search by Learning Action Space for Monte Carlo Tree Search ↗no summary yetLinnan Wang et al.2019 · 4 citations
71. Transition Matching Distillation for Fast Video Generation ↗arXiv (Cornell University) · no summary yetWeili Nie et al.2026 · 3 citations
72. Transferring Task Goals via Hierarchical Reinforcement Learning ↗no summary yetSaining Xie et al.2018 · 3 citations
73. PISA Experiments: Exploring Physics Post-Training for Video Diffusion Models by Watching Stuff Drop ↗arXiv (Cornell University) · no summary yetChenyu Li et al.2025 · 2 citations
74. Repurposing Geometric Foundation Models for Multi-view Diffusion ↗Lecture notes in computer science · no summary yetWooseok Jang et al.2026 · 1 citation
75. DASIP: Dynamic Test-Time Compute Scaling for Robot Control with Stochastic Interpolant Policies ↗arXiv (Cornell University) · no summary yetChun, Inkook et al.2025 · 1 citation
76. DiffusionGuard: A Robust Defense Against Malicious Diffusion-based Image Editing ↗arXiv (Cornell University) · no summary yetJune Suk Choi et al.2024 · 1 citation
77. Self-Refining Video Sampling ↗arXiv (Cornell University) · no summary yetSangwon Jang et al.2026
78. PaintBench: Deterministic Evaluation of Precise Visual Editing ↗arXiv (Cornell University) · no summary yetXu, Kai et al.2026
79. RepFusion: Leveraging Multimodal Priors for Denoising in Representation Space ↗arXiv (Cornell University) · no summary yetXichen Pan et al.2026
80. Cambrian-P: Pose-Grounded Video Understanding ↗Lecture notes in computer science · no summary yetJihan Yang et al.2026
81. Benchmarking Visual State Tracking in Multimodal Video Understanding ↗arXiv (Cornell University) · no summary yetSihyun Yu et al.2026
82. Dynamic Test-Time Compute Scaling in Control Policy: Difficulty-Aware Stochastic Interpolant Policy ↗neural information processing systems · no summary yetInkook Chun et al.2025
83. VULCAN: Tool-Augmented Multi Agents for Iterative 3D Object Arrangement ↗arXiv (Cornell University) · no summary yetZhengfei Kuang et al.2025
84. Thinking in 360°: Humanoid Visual Search in the Wild ↗arXiv (Cornell University) · no summary yetHeyang Yu et al.2025
85. ラベルはニューラルアーキテクチャ探索に必要か?【JST・京大機械翻訳】 ↗Lecture notes in computer science · no summary yetLiu Chenxi et al.2020
86. Perception Preserving Projections ↗British Machine Vision Conference (BMVC) · no summary yetSaining Xie et al.2013

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/authors/saining-xie/works/