SX
Saining Xie
cs.CVcs.LGcs.AIcs.CLcs.GRstat.MLcs.NEAlgorithmsArtificial IntelligenceClustering
On Valency
published · living versionsW_cy2bmu9n·v1 · currentpublished
Learning the 4D World through Point Trajectory Forecasting
with Byungwoo Jeon, Sunghwan Hong, Dohyeon Kim, Jonghoon Lee +8
1 version
Preprints & journals
77 papers in the corpus · 2013–2026RepFusion: Leveraging Multimodal Priors for Denoising in Representation Space2606.14700v1 · Xichen Pan, Aashu Singh, Satya Narayan Shukla et al.2026 · 0 citationsarXiv
Benchmarking Visual State Tracking in Multimodal Video Understanding2606.03920v1 · Sihyun Yu, Nanye Ma, Pinzhi Huang et al.2026 · 0 citationsarXiv
PaintBench: Deterministic Evaluation of Precise Visual Editing2606.00188v1 · Kai Xu, Ellis Brown, Shrikar Madhu et al.2026 · 0 citationsarXiv
Cambrian-P: Pose-Grounded Video Understanding2605.22819v2 · Jihan Yang, Zifan Zhao, Xichen Pan et al.2026 · 0 citationsarXiv
Improved Baselines with Representation Autoencoders2605.18324v2 · Jaskirat Singh, Boyang Zheng, Zongze Wu et al.2026 · 0 citationsarXiv
Image Generators are Generalist Vision Learners2604.20329v3 · Valentin Gabeur, Shangbang Long, Songyou Peng et al.2026 · 0 citationsarXiv
Repurposing Geometric Foundation Models for Multi-view Diffusion2603.22275v1 · Wooseok Jang, Seonghu Jeon, Jisang Han et al.2026 · 0 citationsarXiv
Beyond Language Modeling: An Exploration of Multimodal Pretraining2603.03276v1 · Shengbang Tong, David Fan, John Nguyen et al.2026 · 0 citationsarXiv
Solaris: Building a Multiplayer Video World Model in Minecraft2602.22208v2 · Georgy Savva, Oscar Michel, Daohan Lu et al.2026 · 0 citationsarXiv
Self-Refining Video Sampling2601.18577v2 · Sangwon Jang, Taekyung Ki, Jaehyeong Jo et al.2026 · 0 citationsarXiv
Scaling Text-to-Image Diffusion Transformers with Representation Autoencoders2601.16208v1 · Shengbang Tong, Boyang Zheng, Ziteng Wang et al.2026 · 0 citationsarXiv
Transition Matching Distillation for Fast Video Generation2601.09881v2 · Weili Nie, Julius Berner, Nanye Ma et al.2026 · 0 citationsProc. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026, pp. 4645-4655
VULCAN: Tool-Augmented Multi Agents for Iterative 3D Object Arrangement2512.22351v2 · Zhengfei Kuang, Rui Lin, Long Zhao et al.2025 · 0 citationsarXiv
Thinking in 360{\deg}: Humanoid Visual Search in the Wild2511.20351v2 · Heyang Yu, Yinan Han, Xiangyu Zhang et al.2025 · 0 citationsarXiv
DASIP: Dynamic Test-Time Compute Scaling for Robot Control with Stochastic Interpolant Policies2511.20906v2 · Inkook Chun, Seungjae Lee, Michael S. Albergo et al.2025 · 0 citationsarXiv
CLM: Removing the GPU Memory Barrier for 3D Gaussian Splatting2511.04951v1 · Hexu Zhao, Xiwen Min, Xiaoteng Liu et al.2025 · 1 citationarXiv
Benchmark Designers Should "Train on the Test Set" to Expose Exploitable Non-Visual Shortcuts2511.04655v2 · Ellis Brown, Jihan Yang, Shusheng Yang et al.2025 · 0 citationsarXiv
SIMS-V: Simulated Instruction-Tuning for Spatial Video Understanding2511.04668v2 · Ellis Brown, Arijit Ray, Ranjay Krishna et al.2025 · 0 citationsarXiv
Cambrian-S: Towards Spatial Supersensing in Video2511.04670v1 · Shusheng Yang, Jihan Yang, Pinzhi Huang et al.2025 · 0 citationsarXiv
Meta CLIP 2: A Worldwide Scaling Recipe2507.22062v3 · Yung-Sung Chuang, Yang Li, Dong Wang et al.2025 · 7 citationsarXiv
MindCube: Spatial Mental Modeling from Limited Views2506.21458v2 · Qineng Wang, Baiqiao Yin, Pingyue Zhang et al.2025 · 1 citationarXiv
Traveling Across Languages: Benchmarking Cross-Lingual Consistency in Multimodal LLMs2505.15075v5 · Hao Wang, Pinzhi Huang, Jihan Yang et al.2025 · 0 citationsarXiv
Exploring the Deep Fusion of Large Language Models and Diffusion Transformers for Text-to-Image Synthesis2505.10046v1 · Bingda Tang, Boyang Zheng, Xichen Pan et al.2025 · 4 citationsarXiv
BLIP3-o: A Family of Fully Open Unified Multimodal Models-Architecture, Training and Dataset2505.09568v1 · Jiuhai Chen, Zhiyang Xu, Xichen Pan et al.2025 · 1 citationarXiv
Science-T2I: Addressing Scientific Illusions in Image Synthesis2504.13129v2 · Jialuo Li, Wenhao Chai, Xingyu Fu et al.2025 · 3 citationsarXiv
REPA-E: Unlocking VAE for End-to-End Tuning with Latent Diffusion Transformers2504.10483v3 · Xingjian Leng, Jaskirat Singh, Yunzhong Hou et al.2025 · 18 citationsarXiv
PISA Experiments: Exploring Physics Post-Training for Video Diffusion Models by Watching Stuff Drop2503.09595v1 · Chenyu Li, Oscar Michel, Xichen Pan et al.2025 · 0 citationsarXiv
SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training2501.17161v2 · Tianzhe Chu, Yuexiang Zhai, Jihan Yang et al.2025 · 7 citationsarXiv
Inference-Time Scaling for Diffusion Models beyond Scaling Denoising Steps2501.09732v1 · Nanye Ma, Shangyuan Tong, Haolin Jia et al.2025 · 5 citationsarXiv
MetaMorph: Multimodal Understanding and Generation via Instruction Tuning2412.14164v1 · Shengbang Tong, David Fan, Jiachen Zhu et al.2024 · 18 citationsarXiv
Thinking in Space: How Multimodal Large Language Models See, Remember, and Recall Spaces2412.14171v2 · Jihan Yang, Shusheng Yang, Anjali W. Gupta et al.2024 · 120 citationsarXiv
Altogether: Image Captioning via Re-aligning Alt-text2410.17251v3 · Hu Xu, Po-Yao Huang, Xiaoqing Ellen Tan et al.2024 · 5 citationsarXiv
Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think2410.06940v4 · Sihyun Yu, Sangkyung Kwak, Huiwon Jang et al.2024 · 6 citationsarXiv
DiffusionGuard: A Robust Defense Against Malicious Diffusion-based Image Editing2410.05694v2 · June Suk Choi, Kyungmin Lee, Jongheon Jeong et al.2024 · 0 citationsarXiv
AuroraCap: Efficient, Performant Video Detailed Captioning and a New Benchmark2410.03051v4 · Wenhao Chai, Enxin Song, Yilun Du et al.2024 · 3 citationsarXiv
Fast Encoding and Decoding for Implicit Video Representation2409.19429v2 · Hao Chen, Saining Xie, Ser-Nam Lim et al.2024 · 5 citationsarXiv
On Scaling Up 3D Gaussian Splatting Training2406.18533v2 · Hexu Zhao, Haoyang Weng, Daohan Lu et al.2024 · 21 citationsarXiv
Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs2406.16860v2 · Shengbang Tong, Ellis Brown, Penghao Wu et al.2024 · 68 citationsarXiv
Fine-Tuning Large Vision-Language Models as Decision-Making Agents via Reinforcement Learning2405.10292v3 · Yuexiang Zhai, Hao Bai, Zipeng Lin et al.2024 · 35 citationsarXiv
MoDE: CLIP Data Experts via Clustering2404.16030v1 · Jiawei Ma, Po-Yao Huang, Saining Xie et al.2024 · 10 citationsarXiv
V-IRL: Grounding Virtual Intelligence in Real Life2402.03310v3 · Jihan Yang, Runyu Ding, Ellis Brown et al.2024 · 14 citationsarXiv
Deconstructing Denoising Diffusion Models for Self-Supervised Learning2401.14404v1 · Xinlei Chen, Zhuang Liu, Saining Xie et al.2024 · 20 citationsarXiv
SiT: Exploring Flow and Diffusion-based Generative Models with Scalable Interpolant Transformers2401.08740v2 · Nanye Ma, Mark Goldstein, Michael S. Albergo et al.2024 · 110 citationsarXiv
Eyes Wide Shut? Exploring the Visual Shortcomings of Multimodal LLMs2401.06209v2 · Shengbang Tong, Zhuang Liu, Yuexiang Zhai et al.2024 · 189 citationsarXiv
Image Sculpting: Precise Object Editing with 3D Geometry Control2401.01702v1 · Jiraphon Yenphraphai, Xichen Pan, Sainan Liu et al.2024 · 22 citationsarXiv
V*: Guided Visual Search as a Core Mechanism in Multimodal LLMs2312.14135v2 · Penghao Wu, Saining Xie2023 · 74 citationsarXiv
Demystifying CLIP Data2309.16671v6 · Hu Xu, Saining Xie, Xiaoqing Ellen Tan et al.2023 · 34 citationsarXiv
Going Denser with Open-Vocabulary Part Segmentation2305.11173v1 · Peize Sun, Shoufa Chen, Chenchen Zhu et al.2023 · 52 citationsarXiv
CiT: Curation in Training for Effective Vision-Language Data2301.02241v1 · Hu Xu, Saining Xie, Po-Yao Huang et al.2023 · 12 citationsarXiv
ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders2301.00808v1 · Sanghyun Woo, Shoubhik Debnath, Ronghang Hu et al.2023 · 1,777 citationsarXiv
Career total: at least 97 works. 77 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.