Scholar
Yuqian Yuan
Google Scholar ID: 7D7QL9MAAAAJ
PhD student, Zhejiang University
Citations & Impact
Citations
516
H-index
8
i10-index
7
Publications
13
Co-authors
12
list available
Contact
Publications
Resume (English only)
Academic Achievements
- Oct 2025: Released PixelRefer, a unified pixel-level MLLM framework for fine-grained regional understanding.
- Sep 2025: Paper 'EOC-Bench' accepted by NeurIPS 2025.
- Aug 2025: Released RynnEC, a video MLLM designed for embodied cognition tasks.
- Jun 2025: Released EOC-Bench, an object-centric embodied cognition benchmark in dynamic egocentric scenarios.
- May 2025: Paper 'TokenPacker' accepted by IJCV 2025.
- Apr 2025: VideoRefer and VideoRefer-Bench adopted by NVIDIA & UC Berkeley in their DAM work.
- Feb 2025: Two papers accepted by CVPR 2025; released VideoRefer-700K dataset on HuggingFace.
- Jan 2025: Released VideoLLaMA 3, a frontier multimodal foundation model for image and video understanding.
- Published multiple high-impact works including PixelRefer (Arxiv 2025), RynnEC (Technical Report 2025), EOC-Bench (NeurIPS 2025), VideoRefer Suite (CVPR 2025), ECBench (CVPR 2025), TokenPacker (IJCV 2025), and VideoLLaMA 3 (Technical Report 2025).
