Scholar
Lanqing HONG
Google Scholar ID: 2p7x6OUAAAAJ
National University of Singapore, Huawei Noah's Ark Lab
Citations & Impact
Citations
3,930
H-index
35
i10-index
67
Publications
20
Co-authors
7
list available
Publications
Browse publications on Google Scholar (top-right) ↗
Resume (English only)
Academic Achievements
- 2025: One paper accepted by NAACL 2025; two papers accepted by ICLR 2025.
- 2024: Two papers accepted by WACV 2025; two by NeurIPS 2024; one by EMNLP 2024; one by COLM 2024; two by ECCV 2024; two by CVPR 2024; three by ICLR 2024.
- Released EMOVA, the first end-to-end omni-modal LLM achieving SOTA performance on both vision-language and speech benchmarks while supporting emotionally expressive spoken dialogue.
- MagicDrive, as a core video generation feature of PanGu Large Model 5.0, was unveiled at Huawei Developer Conference 2024 (HDC 2024).
- Proposed Mistake Analysis (ICLR) and ECSO (ECCV) frameworks, improving LLM safety pass rates by over 20%; established CoSafe (EMNLP), a benchmark for multi-turn dialogue safety evaluation.
- Developed physics-informed controllable video generation frameworks for autonomous driving corner cases, including GeoDiffusion (ICLR), MagicDrive (ICLR), and DetDiffusion (CVPR).
- Organized the ECCV 2024 Workshop “W-CODA: Multimodal Perception and Comprehension of Corner Cases in Autonomous Driving” in Milan, Italy.
- Launched the First Autonomous Driving Corner Case Understanding and Video Generation Challenge in June 2024.
