Bryan Hooi

6

Papers

65

Total Citations

Papers (6)

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

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

Adapting Precomputed Features for Efficient Graph Condensation