一作ICLR 2026Poster
NExT-OMNI: Towards Any-to-Any Omnimodal Foundation Models with Discrete Flow Matching
Run Luo · Xiaobo Xia · Lu Wang · Longze Chen · Renke Shan · Jing Luo · Min Yang · Tat-Seng Chua
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。
Run Luo · Xiaobo Xia · Lu Wang · Longze Chen · Renke Shan · Jing Luo · Min Yang · Tat-Seng Chua
Longze Chen · Lu Wang · Renke Shan · Ze Gong · Run Luo · Jiaming Li · Jing Luo · Qiyao Wang · Min Yang
Minzheng Wang · Run Luo · Yanbo Wang · Zichen Liu · Yuqiao Tan · Tao Tan · Nan Xu · Lu Wang · Wenji Mao
While Reinforcement Learning with Verifiable Rewards (RLVR) has proven effective for closed-ended tasks, extending it to open-ended social language games via self-play reveals a critical issue: evolution impasse. Due to the vast strategy space, language agents frequently converge to homogenized b...
Qiyao Wang · Guhong Chen · Hongbo Wang · Huaren Liu · Minghui Zhu · Zhifei Qin · Li Linwei · Yilin Yue · Shiqiang Wang · Jiayan Li · Wu Yihang · Ziqiang Liu · Longze Chen · Run Luo · Liyang Fan · Jiaming Li · Lei Zhang · Kan Xu · Hamid Alinejad-Rokny · Chengming Li · Shiwen Ni · Yuan Lin · Min Yang
Intellectual Property (IP) is a highly specialized domain that integrates technical and legal knowledge, making it inherently complex and knowledge-intensive. Recent advancements in LLMs have demonstrated their potential to handle IP tasks, enabling more efficient analysis, understanding, and gen...