Jin Song Dong

TrainRef: Curating Data with Label Distribution and Minimal Reference for Accurate Prediction and Reliable Confidence

Risk-Aware Robust Graph Network Explanation

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

Seeing It Before It Happens: In-Generation NSFW Detection for Diffusion-Based Text-to-Image Models

Formal Methods-based Evaluation of LLM Systematic Generalization

Poisoning Prompt-Guided Sampling in Video Large Language Models

Fair-SP: Capturing Pluralistic Social Equity Preferences Through Synthetic Data

Turning Shields into Swords: Leveraging Safety Policies for LLM Safety Testing

ALMGuard: Safety Shortcuts and Where to Find Them as Guardrails for Audio–Language Models

$F^3Set$: Towards Analyzing Fast, Frequent, and Fine-grained Events from Videos

RvLLM: LLM Runtime Verification with Domain Knowledge

Clustering Properties of Self-Supervised Learning

FracFace: Breaking The Visual Clues—Fractal-Based Privacy-Preserving Face Recognition

Defending LVLMs Against Vision Attacks Through Partial-Perception Supervision