Xiaoyong Zhu

ORION: Decoupling and Alignment for Unified Autoregressive Understanding and Generation

Explore More, Learn Better: Parallel MLLM Embeddings under Mutual Information Minimization

iTryOn: Mastering Interactive Video Virtual Try-On with Spatial-Semantic Guidance

Mesa and Mask: A Benchmark for Detecting and Classifying Deceptive Behaviors in LLMs

QuadSentinel: Sequent Safety for Machine-Checkable Control in Multi-agent Systems

Beyond Refusals: Fine-grained Safety Alignment for Reasoning LLMs

Beyond Safe Answers: A Benchmark for Evaluating True Risk Awareness in Large Reasoning Models

Enabling Agents to Communicate Entirely in Latent Space

Wave-Particle (Continuous–Discrete) Dualistic Visual Tokenization for Unified Understanding and Generation

VideoShield: A Unified Framework for Multimodal Risk Detection and Control in Video Generative Models

USB: A Comprehensive and Unified Safety Evaluation Benchmark for Multimodal Large Language Models

Towards Visualization-of-Thought Jailbreak Attack against Large Visual Language Models

Truly Safe & Truly Helpful: Achieving Harmonious Balance for Large Language Model