Bryan Hooi

papers

919

total citations

papers (26)

Self-Supervised Aggregation of Diverse Experts for Test-Agnostic Long-Tailed Recognition

NEURIPS 2022arXiv

177

citations

LargeST: A Benchmark Dataset for Large-Scale Traffic Forecasting

NEURIPS 2023arXiv

151

citations

Harnessing Explanations: LLM-to-LM Interpreter for Enhanced Text-Attributed Graph Representation Learning

ICLR 2024arXiv

133

citations

Unleashing the Power of Contrastive Self-Supervised Visual Models via Contrast-Regularized Fine-Tuning

NEURIPS 2021arXiv

citations

Expanding Small-Scale Datasets with Guided Imagination

NEURIPS 2023arXiv

citations

Monte Carlo Tree Search for Comprehensive Exploration in LLM-Based Automatic Heuristic Design

ICML 2025arXiv

citations

CHiP: Cross-modal Hierarchical Direct Preference Optimization for Multimodal LLMs

ICLR 2025arXiv

citations

Proximity-Informed Calibration for Deep Neural Networks

NEURIPS 2023arXiv

citations

SSMF: Shifting Seasonal Matrix Factorization

NEURIPS 2021arXiv

citations

How Much Can Transfer? BRIDGE: Bounded Multi-Domain Graph Foundation Model with Generalization Guarantees

ICML 2025

citations

ConfTuner: Training Large Language Models to Express Their Confidence Verbally

NEURIPS 2025arXiv

citations

PoetryDiffusion: Towards Joint Semantic and Metrical Manipulation in Poetry Generation

AAAI 2024arXiv

citations

Exploring Visual Vulnerabilities via Multi-Loss Adversarial Search for Jailbreaking Vision-Language Models

CVPR 2025arXiv

citations

Learning the Unlearned: Mitigating Feature Suppression in Contrastive Learning

ECCV 2024arXiv

citations

GRAVER: Generative Graph Vocabularies for Robust Graph Foundation Models Fine-tuning

NEURIPS 2025arXiv

citations

Text Speaks Louder than Vision: ASCII Art Reveals Textual Biases in Vision-Language Models

COLM 2025arXiv

citations

Modality-Independent Graph Neural Networks with Global Transformers for Multimodal Recommendation

AAAI 2025arXiv

citations

Spherical Confidence Learning for Face Recognition

CVPR 2021

citations

"Trust, but Verify: Using Self-Supervised Probing to Improve Trustworthiness"

ECCV 2022

citations

Adaptive Data Augmentation on Temporal Graphs

NEURIPS 2021

citations

Probabilistic Knowledge Distillation of Face Ensembles

CVPR 2023

citations

Adapting Precomputed Features for Efficient Graph Condensation

ICML 2025

citations

Bryan Hooi

papers (26)

Self-Supervised Aggregation of Diverse Experts for Test-Agnostic Long-Tailed Recognition

LargeST: A Benchmark Dataset for Large-Scale Traffic Forecasting

Harnessing Explanations: LLM-to-LM Interpreter for Enhanced Text-Attributed Graph Representation Learning

Unleashing the Power of Contrastive Self-Supervised Visual Models via Contrast-Regularized Fine-Tuning

Expanding Small-Scale Datasets with Guided Imagination

Monte Carlo Tree Search for Comprehensive Exploration in LLM-Based Automatic Heuristic Design

EIGNN: Efficient Infinite-Depth Graph Neural Networks

FlipAttack: Jailbreak LLMs via Flipping

Words or Vision: Do Vision-Language Models Have Blind Faith in Text?

MGNNI: Multiscale Graph Neural Networks with Implicit Layers

CHiP: Cross-modal Hierarchical Direct Preference Optimization for Multimodal LLMs

Proximity-Informed Calibration for Deep Neural Networks

SSMF: Shifting Seasonal Matrix Factorization

How Much Can Transfer? BRIDGE: Bounded Multi-Domain Graph Foundation Model with Generalization Guarantees

ConfTuner: Training Large Language Models to Express Their Confidence Verbally

PoetryDiffusion: Towards Joint Semantic and Metrical Manipulation in Poetry Generation

Exploring Visual Vulnerabilities via Multi-Loss Adversarial Search for Jailbreaking Vision-Language Models

Learning the Unlearned: Mitigating Feature Suppression in Contrastive Learning

GRAVER: Generative Graph Vocabularies for Robust Graph Foundation Models Fine-tuning

Text Speaks Louder than Vision: ASCII Art Reveals Textual Biases in Vision-Language Models

Modality-Independent Graph Neural Networks with Global Transformers for Multimodal Recommendation

Spherical Confidence Learning for Face Recognition

"Trust, but Verify: Using Self-Supervised Probing to Improve Trustworthiness"

Adaptive Data Augmentation on Temporal Graphs

Probabilistic Knowledge Distillation of Face Ensembles

Adapting Precomputed Features for Efficient Graph Condensation

papers (26)

Self-Supervised Aggregation of Diverse Experts for Test-Agnostic Long-Tailed Recognition

LargeST: A Benchmark Dataset for Large-Scale Traffic Forecasting

Harnessing Explanations: LLM-to-LM Interpreter for Enhanced Text-Attributed Graph Representation Learning

Unleashing the Power of Contrastive Self-Supervised Visual Models via Contrast-Regularized Fine-Tuning

Expanding Small-Scale Datasets with Guided Imagination

Monte Carlo Tree Search for Comprehensive Exploration in LLM-Based Automatic Heuristic Design

EIGNN: Efficient Infinite-Depth Graph Neural Networks

FlipAttack: Jailbreak LLMs via Flipping

Words or Vision: Do Vision-Language Models Have Blind Faith in Text?

MGNNI: Multiscale Graph Neural Networks with Implicit Layers

CHiP: Cross-modal Hierarchical Direct Preference Optimization for Multimodal LLMs

Proximity-Informed Calibration for Deep Neural Networks

SSMF: Shifting Seasonal Matrix Factorization

How Much Can Transfer? BRIDGE: Bounded Multi-Domain Graph Foundation Model with Generalization Guarantees

ConfTuner: Training Large Language Models to Express Their Confidence Verbally

PoetryDiffusion: Towards Joint Semantic and Metrical Manipulation in Poetry Generation

Exploring Visual Vulnerabilities via Multi-Loss Adversarial Search for Jailbreaking Vision-Language Models

Learning the Unlearned: Mitigating Feature Suppression in Contrastive Learning

GRAVER: Generative Graph Vocabularies for Robust Graph Foundation Models Fine-tuning

Text Speaks Louder than Vision: ASCII Art Reveals Textual Biases in Vision-Language Models

Modality-Independent Graph Neural Networks with Global Transformers for Multimodal Recommendation

Spherical Confidence Learning for Face Recognition

"Trust, but Verify: Using Self-Supervised Probing to Improve Trustworthiness"

Adaptive Data Augmentation on Temporal Graphs

Probabilistic Knowledge Distillation of Face Ensembles

Adapting Precomputed Features for Efficient Graph Condensation