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
64.21/100
前 3.7%
全站排名 #2,393
发表论文14 篇
平均评分
年均产出4.7 篇/年
Wenbin Li
研究方向
Few-shot Learning · Meta-learning · Self-supervised Learning · Unsupervised Learning · Continual Learning · Multimodal Foundation Models
21
Retain and Adapt: Auto-Balanced Model Editing for Open-Vocabulary Object Detection under Domain Shifts
ICLR 2026Poster
16
A Faster Parameter-Free Regret Matching Algorithm
ICLR 2026Poster
18
QPrompt-R1: Real-Time Reasoning for Domain-Generalized Semantic Segmentation via Group-Relative Query Alignment
ICLR 2026Poster
5
HERA: Efficient Test-Time Adaptation for Cross-Domain Few-Shot Segmentation with Vision Foundation Models
ICLR 2026Withdrawn
三作21
SmartSAM: Segment Ambiguous Objects like Smart Annotators
ICLR 2026Rejected
21
DON’T NEED RETRAINING: A Mixture of DETR and Vision Foundation Models for Cross-Domain Few-Shot Object Detection
NeurIPS 2025Poster
10
Reducing Variance of Stochastic Optimization for Approximating Nash Equilibria in Normal-Form Games
ICML 2025Spotlight
三作32
Efficient Last-Iterate Convergence in Solving Extensive-Form Games
NeurIPS 2025Poster
33
Last-Iterate Convergence of Smooth Regret Matching$^+$ Variants in Learning Nash Equilibria
NeurIPS 2025Poster
17
Last-Iterate Convergence of Smooth Regret Matching$^+$ Variants in Learning Nash Equilibria
ICLR 2025Rejected
7
Adapting Informative Structures for Cross-Domain Few-Shot Segmentation
ICLR 2025Withdrawn
32
Learning Nash Equilibria in Normal-Form Games via Approximating Stationary Points
ICLR 2025Rejected