影响力指数
论文质量、代表作、近期表现、广度与样本量置信度综合计算
14.25/100
超过 43.6%
全站排名 #36,292
发表论文7 篇
平均评分
年均产出3.5 篇/年
Guanbin Li
研究方向
Embodied Vision Comprehension · Multi-modal visual comtent understanding and generation · Vision and Language · Object Detection · Salient object detection
27
MaskCLIP++: A Mask-Based CLIP Fine-tuning Framework for Open-Vocabulary Image Segmentation
ICLR 2025Rejected
39
GeoSplating: Towards Geometry Guided Gaussian Splatling for Physically-based Inverse Rendering
ICLR 2025Rejected
三作7
UMVMap: Improving Vectorized Map Construction via Multi-vehicle Perspectives
ICLR 2025Rejected
通讯6
Video Q-Former: Multimodal Large Language Model with Spatio-Temporal Querying Transformer Towards Video Understanding
ICLR 2025Rejected
通讯6
LLMs Synergy : From Closed-Source Prototyping to Open-Source Model based Instruction Following
ICLR 2025Withdrawn
三作