首次获取该候选人的完整档案及 StartLux 评估共 20 积分；每位用户单独解锁，之后查看免费。主动刷新 20 积分。
实时查找电子邮箱，费用不超过20积分；未找到邮箱不扣费。
Xi Chen · Mingyu Jin · Jingcheng (Frank) Niu · Yutong Yin · Jinman Zhao · Bangwei Guo · Dimitris Metaxas · Zhaoran Wang · Yutao Yue · Gerald Penn
Jingwei Shi · Xinxiang Yin · Jing Huang · Shengyu Tao · Jinman Zhao
The evaluation of Large Language Models (LLMs) for code generation relies heavily on the quality and robustness of test cases. However, existing benchmarks often lack coverage for subtle corner cases, allowing incorrect solutions to pass. To bridge this gap, we propose CodeHacker, an automated ag...
Chenyang Lu · Jiaru Li · Jinman Zhao · Xinran Chen · Yining Wang · Renyi Cai · Yuchen Li · Chao He
Low-Rank Adaptation (LoRA) is widely used for parameter-efficient fine-tuning, yet merging multiple task-specific LoRA updates without additional training remains challenging. Most existing LoRA merging methods rely on SVD-based alignment, which emphasizes globally shared structure across tasks....
Xiaoyu Hu · Jinman Zhao
Large language models (LLMs) are increasingly deployed in financial contexts, raising critical concerns about reliability, alignment, and susceptibility to adversarial manipulation. While prior finance-related benchmarks assess LLMs’ capabilities in stock trading, they are often restricted to sma...
Jinman Zhao · Erxue Min · Hui Wu · Ziheng Li · Zexu Sun · Hengyi Cai · Shuaiqiang Wang · Xu Chen · Gerald Penn