AI.info

Juntao Dai

Explore Juntao Dai on AI.info.

• Align Once, Benefit Multilingually: Enforcing Multilingual Consistency for LLM Safety Alignment
• AgentDoG: A Diagnostic Guardrail Framework for AI Agent Safety and Security
• VLA-Arena: An Open-Source Framework for Benchmarking Vision-Language-Action Models
• Perception, Understanding and Reasoning, A Multimodal Benchmark for Video Fake News Detection