Author

Le Xue

Observed name: Xue, Le

Institutions: Fudan University, Salesforce (United States)

Observed institutions: Fudan University, Salesforce (United States), University of Pennsylvania

ORCID: 0000-0003-2810-770X

Observed ORCID: 0000-0003-2810-770X

OpenAlex ID: A5100733668

BLIP3-o: A Family of Fully Open Unified Multimodal Models-Architecture, Training and Dataset

2025 · Chen, Jiuhai, Xu, Zhiyang, et al. · arXiv (Cornell University) · 382

PDF

ULIP: Learning a Unified Representation of Language, Images, and Point Clouds for 3D Understanding

2023 · Le Xue, Mingfei Gao, et al. · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · 336

PDF

ULIP-2: Towards Scalable Multimodal Pre-Training for 3D Understanding

2024 · Le Xue, Ning Yu, et al. · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · 219

PDF

BOLAA: Benchmarking and Orchestrating LLM-augmented Autonomous Agents

2023 · Liu, Zhiwei, Yao, Weiran, et al. · arXiv (Cornell University) · 113

PDF

Retroformer: Retrospective Large Language Agents with Policy Gradient Optimization

2023 · Yao, Weiran, Heinecke, Shelby, et al. · arXiv (Cornell University) · 106

PDF

X-InstructBLIP: A Framework for Aligning Image, 3D, Audio, Video to LLMs and its Emergent Cross-Modal Reasoning

2024 · Artemis Panagopoulou, Le Xue, et al. · Lecture notes in computer science · 90

PDF

BLIP3o-NEXT: Next Frontier of Native Image Generation

2025 · Chen, Jiuhai, Xue, Le, et al. · arXiv (Cornell University) · 54

PDF

Artificial intelligence for medicine 2025: Navigating the endless frontier

2025 · Ji Dai, Huiyu Xu, et al. · The Innovation Medicine · 39

MINT-1T: Scaling Open-Source Multimodal Data by 10x: A Multimodal Dataset with One Trillion Tokens

2024 · Anas Awadalla, Le Xue, et al. · neural information processing systems · 34

PDF

xGen-MM-Vid (BLIP-3-Video): You Only Need 32 Tokens to Represent a Video Even in VLMs

2024 · Ryoo, Michael S., Zhou, Honglu, et al. · arXiv (Cornell University) · 26

PDF

SegAnyPET: Universal Promptable Segmentation from Positron Emission Tomography Images

2025 · Yichi Zhang, Le Xue, et al. · IEEE/CVF International Conference on Computer Vision (ICCV) · 13

PDF

REX: Rapid Exploration and eXploitation for AI Agents

2023 · Murthy, Rithesh, Heinecke, Shelby, et al. · arXiv (Cornell University) · 13

PDF

BLIP3-KALE: Knowledge Augmented Large-Scale Dense Captions

2024 · Awadalla, Anas, Xue, Le, et al. · arXiv (Cornell University) · 12

PDF

LLAVIDAL : A Large LAnguage VIsion Model for Daily Activities of Living

2025 · Dominick Reilly, Rajatsubhra Chakraborty, et al. · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · 11

PDF

Hierarchical Point Attention for Indoor 3D Object Detection

2024 · Manli Shu, Le Xue, et al. · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · 10

PDF

xGen-VideoSyn-1: High-Fidelity Text-to-Video Synthesis with Compressed Representations

2025 · Can Qin, Congying Xia, et al. · Lecture notes in computer science · 9

PDF

Future Optical Flow Prediction Improves Robot Control & Video Generation

2026 · Kanchana Ranasinghe, Honglu Zhou, et al. · 8

Robustness Evaluation of Transformer-Based Form Field Extractors via Form Attacks

2023 · Le Xue, Mingfei Gao, et al. · Lecture notes in computer science · 4

PDF