From September 2019 to December 2021, I studied at National University of Defense Technology (NUDT) University and obtained a Master degree in Computer Science and Technology.

From March 2022 to December 2025, I studied at National University of Defense Technology (NUDT) University and obtained a Ph.D. degree in Computer Science and Technology.

Since 2026, I have been working as a postdoctoral researcher at the National University of Defense Technology (NUDT).

My current research focuses on multimodal large model reasoning and perception, open-world perception, and multimodal learning. As the first author, I have published papers at top-tier AI venues, including ICML, AAAI, ACM MM, and IEEE TIP. I also serve as a reviewer for leading conferences such as ICML, NeurIPS, CVPR, ICCV, AAAI, and ACM MM.

If you are seeking any form of academic cooperation, please feel free to email me (heyulin@nudt.edu.cn).

🔥 News

• 2026.05:  🎉🎉 One paper is accepted in ICML’26 (CCF-A).
• 2026.03:  🎉🎉 Two paper are accepted in ICME’26 (CCF-B).
• 2025.11:  🎉🎉 One paper is accepted in AAAI’26 (CCF-A).
• 2025.08:  🎉🎉 One paper is accepted in PG’25 (CCF-B).
• 2025.03:  🎉🎉 One paper is accepted in ICME’25 (CCF-B).
• 2024.12:  🎉🎉 One paper is accepted in AAAI’25 (CCF-A).
• 2024.12:  🎉🎉 One paper is accepted in ICASSP’25 (CCF-B).
• 2024.09:  🎉🎉 One paper is accepted in TIP’24 (CCF-A).
• 2024.07:  🎉🎉 One paper is accepted in ACM MM’24 (CCF-A).
• 2024.03:  🎉🎉 Two paper are accepted in ICME’24 (CCF-B).
• 2023.02:  🎉🎉 One paper is accepted in ICASSP’23 (CCF-B).
• 2021.07:  🎉🎉 One paper is accepted in ACM MM’21 (CCF-A).

📝 Publications

Main Publications

MLLM Reasoning Segmentation

ICML 2026

DR$^2$Seg: Decomposed Two-Stage Rollouts for Efficient Reasoning Segmentation in Multimodal Large Language Models

Yulin He, Wei Chen, Zhikang Jian, Tianhang Guo, Wenjuan Zhou, Minglong Li, Shaowu Yang, and Wenjing Yang.

ICML 2026 (CCF A)

MLLM Reasoning Detection

AAAI 2026

Attention to Threat-Relevant Objects: Reasoning Detection in Autonomous Driving via Multimodal Large Language Models

Yulin He, Wei Chen, Xinbiao Gan, Siqi Wang, Haotian Wang, and Yusong Tan.

AAAI 2026 (CCF A)

3D Occupancy Prediction

AAAI 2025

Achieving Speed-Accuracy Balance in Vision-based 3D Occupancy Prediction via Geometric-Semantic Disentanglement

Yulin He, Wei Chen, Siqi Wang, Tianci Xun, and Yusong Tan.

AAAI 2025 (CCF A)

Open-World Object Detection

ACM MM 2024

Sniffing Threatening Open-World Objects in Autonomous Driving by Open-Vocabulary Models

Yulin He, Siqi Wang, Wei Chen, Tianci Xun, and Yusong Tan.

ACM MM 2024 (CCF A)

Open-World Object Detection

TIP 24

Recalling Unknowns Without Losing Precision: An Effective Solution to Large Model-Guided Open World Object Detection

Yulin He, Wei Chen, Siqi Wang, Tianrui Liu, and Meng Wang.

TIP 2024 (CCF A)

Lane Detection

ACM MM 21

Fast and Accurate Lane Detection via Frequency Domain Learning

Yulin He, Wei Chen, Zhengfa Liang, Dan Chen, Yusong Tan, Xin Luo, Chen Li, and Yulan Guo.

ACM MM 2021 (CCF A)