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
82.77/100
前 1.1%
全站排名 #733
发表论文16 篇
平均评分
年均产出5.3 篇/年
Ashish Sabharwal
研究方向
LLMs · agents · decision making · state space models · question answering · reasoning · NLP · foundation · probabilistic inference · graphical models · combinatorial reasoning · discrete optimization · satisfiability · integer programming · proof complexity · approximation algorithms
17
A Little Depth Goes a Long Way: The Expressive Power of Log-Depth Transformers
NeurIPS 2025Poster
二作16
Exact Expressive Power of Transformers with Padding
NeurIPS 2025Poster
二作20
Answer, Assemble, Ace: Understanding How LMs Answer Multiple Choice Questions
ICLR 2025Spotlight
通讯29
AutoDiscovery: Open-ended Scientific Discovery via Bayesian Surprise
NeurIPS 2025Poster
12
DiscoveryBench: Towards Data-Driven Discovery with Large Language Models
ICLR 2025Poster
21
Declarative characterizations of direct preference alignment algorithms
ICLR 2025Rejected
三作27
A Little Depth Goes a Long Way: the Expressive Power of Log-Depth Transformers
ICLR 2025Rejected
二作9
ZebraLogic: On the Scaling Limits of LLMs for Logical Reasoning
ICML 2025Poster
13
Understanding the Logic of Direct Preference Alignment through Logic
ICML 2025Poster
三作