I am a first-year Ph.D. student in Computer Science and Technology at Harbin Institute of Technology (HIT), advised by Prof. Jie Liu. My research focuses on embodied intelligence, vision-language-action (VLA) models, world models, and efficient vision-language models for embodiment.

I am also a research intern at the International Digital Economy Academy (IDEA) and the Embodied Intelligence Laboratory of Guangdong Province (Futian Laboratory), where I am advised by Prof. Lei Zhang and work on full-stack embodied policy development, including robot and teleoperation platforms, data infrastructure, model pretraining and post-training, and evaluation.

Before beginning my Ph.D., I received a B.Eng. in Thermophysics from HIT’s School of Energy Science and Engineering.

Research Interests

• Embodied intelligence and robot learning
• Vision-language-action models
• World models
• Efficient vision-language models for embodiment

Selected Publications

ECCV 2026

Guide, Think, Act: Interactive Embodied Reasoning in Vision-Language-Action Models

Yiran Ling^*, Qing Lian^*, Jinghang Li, Qing Jiang, Tianming Zhang, Xiaoke Jiang, Chuanxiu Liu, Jie Liu, and Lei Zhang

* Equal contribution

European Conference on Computer Vision (ECCV), 2026

GTA-VLA introduces spatially steerable embodied reasoning: a user can provide an affordance point, box, or trace to resolve ambiguity and guide a robot policy toward accurate execution. The method reaches an 81.2% success rate on the SimplerEnv WidowX benchmark and improves robustness under out-of-domain visual shifts.

EMNLP 2026

CoFiE: Coarse-to-Fine Evidence Selection for Efficient Streaming Video Understanding

Jing Jiang^*, Yiran Ling^*, Ruonan Li, Dimitrios Stamoulis^†, and Jie Liu^†

* Equal contribution · † Corresponding authors

Conference on Empirical Methods in Natural Language Processing (EMNLP), 2026

CoFiE accelerates streaming video understanding through coarse-to-fine evidence selection. It removes redundant frames before visual encoding, then refines query-relevant evidence during multimodal prefill, reaching state-of-the-art accuracy-efficiency trade-offs with up to 2.54× lower end-to-end inference latency.

Selected Honors

• Ranked 1st of 157 students in academics and graduate recommendation evaluation
• National Scholarship, awarded twice (top 1%)
• Chunhui Innovation Achievement Award, the highest student innovation and entrepreneurship honor at Harbin Institute of Technology (Top 18 across all HIT campuses)
• Nominee for the Li Chang Award, Harbin Institute of Technology (Top 23 across all HIT campuses)
• Outstanding Graduate of Heilongjiang Province and Harbin Institute of Technology
• Outstanding Student of Heilongjiang Province (top 3%)
• First-Class People’s Scholarship (top 3%)