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
46.08/100
前 10.3%
全站排名 #6,655
发表论文13 篇
平均评分
年均产出4.3 篇/年
Ziheng Qin
研究方向
Large scale training · Machine Learning efficiency · Data · Optimizer · Multimodal Learning · Continual Learning · Parameter Generation
19
ASCIIEval: Benchmarking Models' Visual Perception in Text Strings via ASCII Art
ICLR 2026Poster
22
DD-Ranking: Rethinking the Evaluation of Dataset Distillation
ICLR 2026Rejected
6
Towards Personalized Parameter Generation via Data-Conditioned Mapping
ICLR 2026Rejected
一作6
QuantGen: Parameter Generation for Controllable Model Quantization
ICLR 2026Rejected
5
Faster Vision Mamba is Rebuilt in Minutes via Merged Token Re-training
ICLR 2026Withdrawn
14
On-the-Fly Data Augmentation via Gradient-Guided and Sample-Aware Influence Estimation
ICLR 2026Rejected
5
ResearchGPT: Benchmarking and Training LLMs for End-to-End Computer Science Research Workflows
ICLR 2026Withdrawn
15
MERIT: Maximum-normalized Element-wise Ratio for Language Model Large-batch Training
ICML 2025Poster
三作25
Visual Perception in Text Strings
ICLR 2025Rejected
11
Info-Coevolution: An Efficient Framework for Data Model Coevolution
ICML 2025Poster
一作32
MERIT: Maximum-normalized Element-wise Ratio for Language Model Large-batch Training
ICLR 2025Rejected
三作