TalkScalable and Efficient LLM Serving with the vLLM Production StackJunchen Jiang, Yue ZhuOSSNA 2025
Conference paperFLIP: A Provable Defense Framework for Backdoor Mitigation in Federated LearningKaiyuan Zhang, Guanhong Tao, et al.ICLR 2023
Workshop paperLarge Language Model Evaluation on Financial BenchmarksBing Zhang, Mikio Takeuchi, et al.ICAIF 2024