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
23.64/100
前 33.7%
全站排名 #21,723
发表论文4 篇
平均评分
年均产出4.0 篇/年
Wentong Li
研究方向
Multi-modal Large Language Models · Vision-Language Models · Image/Video Understanding · Visual Detection & Segmentation
22
Point2RBox-v3: Self-Bootstrapping from Point Annotations via Integrated Pseudo-Label Refinement and Utilization
ICLR 2026Poster
25
VisionTrim: Unified Vision Token Compression for Training-Free MLLM Acceleration
ICLR 2026Poster
二作20
DTR: Towards optimal token compression with data-driven token ranking for efficient visual-language model inference
ICLR 2026Rejected
17
Tailored Teaching with Balanced Difficulty: Elevating Reasoning in Multimodal Chain-of-Thought via Prompt Curriculum
ICLR 2026Withdrawn