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
21.35/100
前 38.5%
全站排名 #24,784
发表论文11 篇
平均评分
年均产出5.5 篇/年
Yingshui Tan
研究方向
Large Language Model · Safety · Computer vision · Multi-task Learning · Recommender System · Uncertainty quantification
31
IF-VidCap: Can Video Caption Models Follow Instructions?
ICLR 2026Poster
32
Mesa and Mask: A Benchmark for Detecting and Classifying Deceptive Behaviors in LLMs
ICLR 2026Rejected
14
QuadSentinel: Sequent Safety for Machine-Checkable Control in Multi-agent Systems
ICLR 2026Rejected
16
Beyond Refusals: Fine-grained Safety Alignment for Reasoning LLMs
ICLR 2026Rejected
15
Beyond Safe Answers: A Benchmark for Evaluating True Risk Awareness in Large Reasoning Models
ICLR 2026Rejected
5
USB: A Comprehensive and Unified Safety Evaluation Benchmark for Multimodal Large Language Models
ICLR 2026Withdrawn
5
VideoShield: A Unified Framework for Multimodal Risk Detection and Control in Video Generative Models
ICLR 2026Withdrawn
19
KORGym: A Dynamic Game Platform for LLM Reasoning Evaluation
NeurIPS 2025Spotlight
21
Towards Visualization-of-Thought Jailbreak Attack against Large Visual Language Models
NeurIPS 2025Poster
12
Truly Safe & Truly Helpful: Achieving Harmonious Balance for Large Language Model
ICLR 2025Rejected
一作12
Adaptive dense reward:Understanding the Gap Between Action and Reward Space in Alignment
ICLR 2025Withdrawn