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
90.22/100
前 0.6%
全站排名 #362
发表论文27 篇
平均评分
年均产出9.0 篇/年
Mikhail Yurochkin
研究方向
Large Language Models · Algorithmic Fairness · Optimal Transport · Federated Learning · Bayesian Nonparametrics
20
Bridging Human and LLM Judgments: Understanding and Narrowing the Gap
NeurIPS 2025Poster
三作18
Sloth: scaling laws for LLM skills to predict multi-benchmark performance across families
NeurIPS 2025Poster
通讯15
Compress then Serve: Serving Thousands of LoRA Adapters with Little Overhead
ICML 2025Poster
18
A transfer learning framework for weak to strong generalization
ICLR 2025Poster
12
Limitations of refinement methods for weak to strong generalization
COLM 2025Poster
三作13
Speculate, then Collaborate: Fusing Knowledge of Language Models during Decoding
ICML 2025Poster
通讯12
Out-of-Distribution Detection using Synthetic Data Generation
COLM 2025Poster
通讯19
LiveXiv - A Multi-Modal live benchmark based on Arxiv papers content
ICLR 2025Poster
22
Speculate, then Collaborate: Fusing Knowledge of Language Models during Decoding
ICLR 2025Rejected
通讯12
Compress then Serve: Serving Thousands of LoRA Adapters with Little Overhead
ICLR 2025Desk Rejected
17
Out-of-Distribution Detection using Synthetic Data Generation
ICLR 2025Rejected
通讯11
SPRI: Aligning Large Language Models with Context-Situated Principles
ICML 2025Poster
通讯21
Sloth: scaling laws for LLM skills to predict multi-benchmark performance across families
ICLR 2025Rejected
通讯