Bryan Hooi

18

Papers

65

Total Citations

Papers (18)

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

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

ConfTuner: Training Large Language Models to Express Their Confidence Verbally

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

Adapting Precomputed Features for Efficient Graph Condensation

Spherical Confidence Learning for Face Recognition

Probabilistic Knowledge Distillation of Face Ensembles

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

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

Expanding Small-Scale Datasets with Guided Imagination

Adaptive Data Augmentation on Temporal Graphs

SSMF: Shifting Seasonal Matrix Factorization

EIGNN: Efficient Infinite-Depth Graph Neural Networks

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

MGNNI: Multiscale Graph Neural Networks with Implicit Layers

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

Proximity-Informed Calibration for Deep Neural Networks

LargeST: A Benchmark Dataset for Large-Scale Traffic Forecasting