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。
Kaixiong Gong · Xin Cai · Bin Lin · Hao Wang · Yunlong Lin · Mingzhe Zheng · Bohao Li · Jian-Wei Zhang · Miles Yang · Zhao Zhong · Liefeng Bo · Xiangyu Yue
Yunlong Lin · Linqing Wang · Kunjie Lin · Zixu Lin · Kaixiong Gong · Wenbo Li · Bin Lin · Zhenxi Li · Shiyi Zhang · Yuyang Peng · Wenxun Dai · Xinghao Ding · Chunyu Wang · Qinglin Lu
Hao Wang · Hao Gu · Hongming Piao · Kaixiong Gong · Yuxiao Ye · Xiangyu Yue · Sirui Han · Yike Guo · Dapeng Wu
The standard post-training recipe for large reasoning models, supervised fine-tuning followed by reinforcement learning (SFT-then-RL), may limit the benefits of the RL stage: while SFT imitates expert demonstrations, it often causes overconfidence and reduces generation diversity, leaving RL with...
Kaixiong Gong · Kaituo Feng · Bohao Li · Yibing Wang · Mofan Cheng · Shijia Yang · Jiaming Han · Benyou Wang · Yutong Bai · Zhuoran Yang · Xiangyu Yue
Recent multimodal large language models (MLLMs), such as GPT-4o, Gemini 1.5/2.5 Pro, and Reka Core, have advanced audio-visual reasoning capabilities, achieving strong performance in tasks like cross-modal understanding and generation. However, our DeafTest uncovers unanticipated failures: most o...