Yuan Cao

Affiliations

Google DeepMindThe University of Hong Kong

papers

3,865

total citations

papers (17)

Tree of Thoughts: Deliberate Problem Solving with Large Language Models

NEURIPS 2023arXiv

3,325

citations

Your GAN is Secretly an Energy-based Model and You Should Use Discriminator Driven Latent Sampling

NEURIPS 2020arXiv

123

citations

Benign Overfitting in Two-layer Convolutional Neural Networks

NEURIPS 2022arXiv

110

citations

Grammar Prompting for Domain-Specific Language Generation with Large Language Models

NEURIPS 2023arXiv

citations

Agnostic Learning of a Single Neuron with Gradient Descent

NEURIPS 2020arXiv

citations

Risk Bounds for Over-parameterized Maximum Margin Classification on Sub-Gaussian Mixtures

NEURIPS 2021arXiv

citations

Vision-guided Text Mining for Unsupervised Cross-modal Hashing with Community Similarity Quantization

AAAI 2025

citations

Deep Graph Online Hashing for Multi-Label Image Retrieval

AAAI 2025

citations

Taxonomy Driven Fast Adversarial Training

AAAI 2024

citations

Understanding the Generalization of Stochastic Gradient Adam in Learning Neural Networks

NEURIPS 2025arXiv

citations

Yuan Cao

Affiliations

papers (17)

Tree of Thoughts: Deliberate Problem Solving with Large Language Models

Your GAN is Secretly an Energy-based Model and You Should Use Discriminator Driven Latent Sampling

Benign Overfitting in Two-layer Convolutional Neural Networks

Grammar Prompting for Domain-Specific Language Generation with Large Language Models

Agnostic Learning of a Single Neuron with Gradient Descent

Risk Bounds for Over-parameterized Maximum Margin Classification on Sub-Gaussian Mixtures

Understanding How Encoder-Decoder Architectures Attend

Binarized Neural Machine Translation

On the Feature Learning in Diffusion Models

A Generalized Neural Tangent Kernel Analysis for Two-layer Neural Networks

Benign Overfitting in Two-Layer ReLU Convolutional Neural Networks for XOR Data

Transformer Learns Optimal Variable Selection in Group-Sparse Classification

IG Captioner: Information Gain Captioners are Strong Zero-shot Classifiers

Vision-guided Text Mining for Unsupervised Cross-modal Hashing with Community Similarity Quantization

Deep Graph Online Hashing for Multi-Label Image Retrieval

Taxonomy Driven Fast Adversarial Training

Understanding the Generalization of Stochastic Gradient Adam in Learning Neural Networks

papers (17)

Tree of Thoughts: Deliberate Problem Solving with Large Language Models

Your GAN is Secretly an Energy-based Model and You Should Use Discriminator Driven Latent Sampling

Benign Overfitting in Two-layer Convolutional Neural Networks

Grammar Prompting for Domain-Specific Language Generation with Large Language Models

Agnostic Learning of a Single Neuron with Gradient Descent

Risk Bounds for Over-parameterized Maximum Margin Classification on Sub-Gaussian Mixtures

Understanding How Encoder-Decoder Architectures Attend

Binarized Neural Machine Translation

On the Feature Learning in Diffusion Models

A Generalized Neural Tangent Kernel Analysis for Two-layer Neural Networks

Benign Overfitting in Two-Layer ReLU Convolutional Neural Networks for XOR Data

Transformer Learns Optimal Variable Selection in Group-Sparse Classification

IG Captioner: Information Gain Captioners are Strong Zero-shot Classifiers

Vision-guided Text Mining for Unsupervised Cross-modal Hashing with Community Similarity Quantization

Deep Graph Online Hashing for Multi-Label Image Retrieval

Taxonomy Driven Fast Adversarial Training

Understanding the Generalization of Stochastic Gradient Adam in Learning Neural Networks