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
19/100
前 44%
全站排名 #28,298
发表论文11 篇
平均评分
年均产出3.7 篇/年
Jingqun Tang
研究方向
Large multimodal model · Document understanding · Text detection & recognition
12
ChineseVideoBench: Benchmarking Multi-modal Large Models for Chinese Video Question Answering
ICLR 2026Rejected
27
DTP: A Simple yet Effective Distracting Token Pruning Framework for Vision-Language Action Models
ICLR 2026Rejected
通讯6
Curvature-Aware Residual Prediction for Stable and Faithful Diffusion Transformer Acceleration Under Large Sampling Intervals
ICLR 2026Rejected
通讯5
Vision as LoRA
ICLR 2026Withdrawn
6
MTVQA: Benchmarking Multilingual Text-Centric Visual Question Answering
ICLR 2025Withdrawn
一作21
A Bounding Box is Worth One Token: Interleaving Layout and Text in a Large Language Model for Document Understanding
ICLR 2025Rejected
5
TextSquare: Scaling up Text-Centric Visual Instruction Tuning
ICLR 2025Withdrawn
一作6
MCTBench: Multimodal Cognition towards Text-Rich Visual Scenes Benchmark
ICLR 2025Rejected