Sicong Leng
Scholar

Sicong Leng

Google Scholar ID: xQsBP6YAAAAJ
Nanyang Technological University
Multi-modal Learning
Citations & Impact
All-time
Citations
1,341
 
H-index
9
 
i10-index
9
 
Publications
20
 
Co-authors
19
list available
Resume (English only)
Academic Achievements
  • Published several papers including 'MMR1: Enhancing Multimodal Reasoning with Variance-Aware Sampling and Open Resources', 'VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understanding' and more; received awards like NeurIPS 2025 Oral, CVPR 2025 Highlight, CVPR 2024 Highlight, ACL 2023 Area Chair Award, and Best Paper Nomination.
Research Experience
  • Involved in multiple research projects such as MMR1, VideoLLaMA 3, Inf-CLIP, and has presented papers at various international conferences.
Education
  • Ph.D. student at Nanyang Technological University, supervised by Prof. Lu Shijian (NTU) and Dr. Bing Lidong (Alibaba-DAMO Academy), specializing in Deep Learning and Multi-modality AI.
Background
  • Research Interests: Multimodality and Embodied AI, specifically Language+Vision and Language+Vision+Action. Specialization: Deep Learning with a focus on Multi-modality and Embodied AI research.
Miscellany
  • Personal interests not mentioned