Jinsheng Wang

Selected Projects

Core contributions as (co-)first author.

Emu3.5: Native Multimodal Models are World Learners

Emu3.5-Team

A large-scale multimodal world model that natively predicts the next vision-language state. Trained with unified next-token prediction over interleaved vision-language sequences, it processes and generates visual-text sequences without modality adapters. Large-scale reinforcement learning enhances reasoning and generation quality, enabling spatiotemporally consistent world exploration and open-world embodied manipulation.

Emu3: Next-Token Prediction is All You Need

Emu3-Team

Nature 2025 - Breakthrough in multimodal scaling laws and native unified generation/understanding across text, image, and video modalities through next-token prediction.

EVA-CLIP-18B: Scaling CLIP to 18 Billion Parameters

Quan Sun*, Jinsheng Wang*, Qiying Yu*, Yufeng Cui, Fan Zhang, Xiaosong Zhang, Xinlong Wang

The largest open-source CLIP model demonstrating efficient weak-to-strong scaling methodologies, achieving exceptional 80.7% zero-shot top-1 accuracy averaged across 27 widely recognized image classification benchmarks with optimized training strategies.

Uni3D: Exploring Unified 3D Representation at Scale

Junsheng Zhou*, Jinsheng Wang*, Baorui Ma*, Yu-Shen Liu, Tiejun Huang, Xinlong Wang

ICLR 2024 (Spotlight) - Pioneering scaling roadmap for 3D foundation models, establishing the first billion-parameter 3D understanding framework.

GANet: A Keypoint-based Global Association Network for Lane Detection

Jinsheng Wang*, Yinchao Ma*, Shaofei Huang*, Tianrui Hui, Fei Wang, Chen Qian, Tianzhu Zhang

CVPR 2022 - Efficient lane detection achieving SOTA accuracy and high FPS. Successfully deployed in production with automotive industry partners (Bosch, Horizon Robotics). Demo available with YOLO integration.

Experience

Alibaba

Technical Staff

ATH Token Foundry

Jan 2026 - Present
Beijing Academy of Artificial Intelligence

Technical Staff

Multimodal Foundation Model Research Center

Jul 2023 - Jan 2026
Microsoft Research Asia

Research Intern

Visual Computing Group

Jun 2022 - Dec 2022
Baidu Research

Research Intern

Robotics and Autonomous Driving Lab (RAL)

Dec 2021 - May 2022

Selected Awards

[2019] National Scholarship
[2019] RoboMaster Robotics Competition - World Finals Special Prize (Rank 3/173) (Team Lead)
[2018] RoboMaster Robotics Competition - Regional Champion

Misc

Unforgettable experiences in robotics competitions, emphasizing teamwork and pursuit of excellence.