Bryan Hooi

EvoTest: Evolutionary Test-Time Learning for Self-Improving Agentic Systems

VPI-Bench: Visual Prompt Injection Attacks for Computer-Use Agents

Turning Bias into Bugs: Bandit-Guided Style Manipulation Attacks on LLM Judges

Reinforcing Query-Level Meta-Agents

TrustGen: A Platform of Dynamic Benchmarking on the Trustworthiness of Generative Foundation Models

Test-Time Scaling in Reasoning Models Is Not Effective for Knowledge-Intensive Tasks Yet

Seeing Through Deception: Uncovering Misleading Creator Intent in Multimodal News with Vision-Language Models

Visual CoT Makes VLMs Smarter but More Fragile

JudgeLRM: Large Reasoning Models as a Judge

JacobiGAD: Jacobi Polynomial–Powered Heterogeneous Graph-Level Anomaly Detection

Do "New Snow Tablets" Contain Snow? Large Language Models Over-Rely on Names to Identify Ingredients of Chinese Drugs

Prot2RNA: A Diffusion Language Model for Protein-Conditioned mRNA Coding Sequence Generation

GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning

ConfTuner: Training Large Language Models to Express Their Confidence Verbally

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

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

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

Multi-Label Node Classification with Label Influence Propagation

How does Watermarking Affect Visual Language Models in Document Understanding?

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

FlipAttack: Jailbreak LLMs via Flipping

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

FlipAttack: Jailbreak LLMs via Flipping

RNA FrameFlow: Flow Matching for de novo 3D RNA Backbone Generation

FiDeLiS: Faithful Reasoning in Large Language Model for Knowledge Graph Question Answering

A Precompute-Then-Adapt Approach for Efficient Graph Condensation

UniTST: Effectively Modeling Inter-Series and Intra-Series Dependencies for Multivariate Time Series Forecasting

Adapting Precomputed Features for Efficient Graph Condensation

Can Knowledge Graphs Make Large Language Models More Trustworthy? An Empirical Study over Open-ended Question Answering

Guiding VLM Agents with Process Rewards at Inference Time for GUI Navigation