Hao CHEN

3 papers The Hong Kong Univeristy of Science and Technology

• GPAS: Accelerating Convergence of LLM Pretraining via Gradient-Preserving Activation Scaling
• Revisiting End-to-End Learning with Slide-level Supervision in Computational Pathology
• SwitchLingua: The First Large-Scale Multilingual and Multi-Ethnic Code-Switching Dataset