 DeepEyesV2: Toward Agentic Multimodal ModelIEEE Transactions on Audio, Speech, and Language Processing (TASLP), 2025 |
 ChiMDQA: Towards Comprehensive Chinese Document QA with Fine-grained EvaluationInternational Conference on Artificial Neural Networks (ICANN), 2025 |
 CryptoMoE: Privacy-Preserving and Scalable Mixture of Experts Inference via Balanced Expert RoutingIEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2025 |
