Me
Kaidi Cao
Research @ Anthropic

About

I’m a Member of Technical Staff at Anthropic, advancing Claude’s agentic and tool-use capabilities. Before that, I co-founded Voyage AI, built best-in-class embedding and reranking models for AI search, and led it to acquisition. I hold a B.E. from Tsinghua University and a Ph.D. in Computer Science from Stanford.

Selected Publications

Learning Large Graph Property Prediction via Graph Segment Training
NeurIPS, 2023
[ Paper] [Code]

TpuGraphs: A Performance Prediction Dataset on Large Tensor Computational Graphs
NeurIPS, 2023
[ Paper] [Code]

AutoTransfer: AutoML with Knowledge Transfer - An Application to Graph Neural Networks
ICLR, 2023
[ Paper] [Code]

Annotation of Spatially Resolved Single-cell Data with STELLAR
Nature Methods, 2022
[ Paper] [Code]

Relational Multi-Task Learning: Modeling Relations between Data and Tasks
ICLR, 2022
[ Paper] [Code]

Open-World Semi-Supervised Learning
ICLR, 2022
[ Paper] [Code]

Heteroskedastic and Imbalanced Deep Learning with Adaptive Regularization
ICLR, 2021
[ Paper] [Code]

Concept Learners for Few-Shot Learning
ICLR, 2021
[ Paper] [Code]

Coresets for Robust Training of Neural Networks against Noisy Labels
NeurIPS, 2020
[ Paper] [Code]

Few-Shot Video Classification via Temporal Alignment
CVPR, 2020

Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss
NeurIPS, 2019
[ Paper] [Code]

CariGANs: Unpaired Photo-to-Caricature Translation
Siggraph Asia, 2018

Pose-Robust Face Recognition via Deep Residual Equivariant Mapping
CVPR, 2018

Merge or Not? Learning to Group Faces via Imitation Learning
AAAI, 2018
[ Paper] [Code]
Top