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
83.9/100
前 1%
全站排名 #666
发表论文19 篇
平均评分
年均产出6.3 篇/年
Vatsal Sharan
研究方向
Machine Learning Theory · Tensor Methods · Space-bounded learning · Theoretical computer science · Robust machine learning · Fairness · Transformers
21
Latent Concept Disentanglement in Transformer-based Language Models
ICLR 2026Poster
三作18
How Muon’s Spectral Design Benefits Generalization: A Study on Imbalanced Data
ICLR 2026Poster
17
FoNE: Precise Single-Token Number Embeddings via Fourier Features
ICLR 2026Poster
通讯15
Limitations on Safe, Trusted, Artificial General Intelligence
ICLR 2026Rejected
二作12
When Do Transformers Learn Heuristics for Graph Connectivity?
ICLR 2026Desk Rejected
通讯9
Textual Steering Vectors Can Improve Visual Understanding in Multimodal Large Language Models
ICLR 2026Withdrawn
21
Simultaneous Swap Regret Minimization via KL-Calibration
NeurIPS 2025Spotlight
三作20
Improved Bounds for Swap Multicalibration and Swap Omniprediction
NeurIPS 2025Spotlight
三作24
The Rich and the Simple: On the Implicit Bias of Adam and SGD
NeurIPS 2025Poster
三作27
Discovering Data Structures: Nearest Neighbor Search and Beyond
NeurIPS 2025Poster
21
Transformers Learn Low Sensitivity Functions: Investigations and Implications
ICLR 2025Poster
通讯25
Discovering Data Structures: Nearest Neighbor Search and Beyond
ICLR 2025Rejected