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
56.81/100
前 5.8%
全站排名 #3,718
发表论文12 篇
平均评分
年均产出4.0 篇/年
Zeyu Qin
研究方向
Synthetic Data · AI Safety · Machine Learning · Adversarial Machine Learning · Federated Learning
38
On Stable Long-Form Generation: Benchmarking and Mitigating Length Volatility
ICLR 2026Rejected
23
Concept Concentration for Faithful Representation Intervention
ICLR 2026Rejected
三作20
Reasoning Path Divergence: A New Metric and Curation Strategy to Unlock LLM Diverse Thinking
ICLR 2026Withdrawn
二作25
Merge-of-Thought Distillation
ICLR 2026Rejected
二作17
UltraHorizon: Benchmarking LLM-Agent Capabilities in Ultra Long-Horizon Scenarios
ICLR 2026Rejected
17
Socratic Personalized Medical Teaching with Multi-Agent Simulation
ICLR 2026Withdrawn
三作19
Safety Reasoning with Guidelines
ICML 2025Poster
二作27
Scaling Laws of Synthetic Data for Language Model
COLM 2025Poster
一作20
RoMa: A Robust Model Watermarking Scheme for Protecting IP in Diffusion Models
NeurIPS 2025Poster
三作24
Lifelong Safety Alignment for Language Models
NeurIPS 2025Poster
三作22
Preserving Diversity in Supervised Fine-Tuning of Large Language Models
ICLR 2025Poster