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
44.29/100
前 11.4%
全站排名 #7,363
发表论文8 篇
平均评分
年均产出2.7 篇/年
Dianbo Sui
研究方向
Game Theory · LLM · Information Extraction
13
How Stable is the Next Token? A Geometric View of LLM Prediction Stability
ICLR 2026Poster
通讯17
PSBench: Editing Image via GUI Agents in Photoshop
ICLR 2026Rejected
通讯14
Surrogate Signals from Format and Length: Reinforcement Learning for Solving Mathematical Problems without Ground Truth Answers
ICLR 2026Rejected
19
VPO: Reasoning Preferences Optimization Based on $\mathcal{V}$-Usable Information
NeurIPS 2025Spotlight
通讯12
Maximizing Intermediate Checkpoint Value in LLM Pretraining with Bayesian Optimization
ICML 2025Poster
通讯31
TMGBench: A Systematic Game Benchmark for Evaluating Strategic Reasoning Abilities of LLMs
ICLR 2025Rejected
17
M2Edit: Locate and Edit Multi-Granularity Knowledge in Multimodal Large Language Model
ICLR 2025Rejected