MLSP-L6.6
AGENT-GSPO: COMMUNICATION-EFFICIENT MULTI-AGENT SYSTEMS VIA GROUP SEQUENCE POLICY OPTIMIZATION
Jing Yang, Yijia Fan, Jusheng Zhang, Keze Wang, Sun Yat-sen University, Hong Kong
Session:
MLSP-L6: Learning and Optimization in Deep Neural Models Oral
Track:
Machine Learning for Signal Processing [ML]
Location:
Room 117
Presentation Time:
Tue, 5 May, 18:10 - 18:30
Presentation
Discussion
Resources
No resources available.
Session MLSP-L6
MLSP-L6.1: OFHIE: OVERVIEW-THEN-FOCUS HIERARCHICAL INTERACTION ENCODING FOR VOXEL-BASED 3D OBJECT DETECTION
Yulong Hu, School of Artificial Intelligence and Robotics, Hunan University, China; Xiaohui Wei, College of Information Science and Engineering, Hunan Normal University, China; Zhiling Geng, Haibo Liu, School of Artificial Intelligence and Robotics, Hunan University, China
MLSP-L6.2: Complementary Subspace Low-Rank Adaptation of Vision-Language Models for Few-Shot Classification
Zhongqi Wang, Aerospace Information Technology University, China; Jia Dai, Kai Li, Xu Li, Yanmeng Guo, Dolby Laboratories, China
MLSP-L6.3: Diffusion Contrastive Learning for Robust Image Classification
Xingcheng Zhu, Yi Liu, Kai Han, Qiaoying Teng, Chongwen Lyu, Xiaocheng Hu, Jun Chen, Zhe Liu, Jiangsu University, China
MLSP-L6.4: Lie Bracket Geometry of Feature Learning in Neural Networks
Subramanyam Venkata, IIITD, India
MLSP-L6.5: On the Importance of a Multi-Scale Calibration for Quantization
Seungwoo Son, Ingyu Seong, Junhan Kim, Hyemi Jang, Yongkweon Jeon, Samsung Research, Korea, Republic of
MLSP-L6.6: AGENT-GSPO: COMMUNICATION-EFFICIENT MULTI-AGENT SYSTEMS VIA GROUP SEQUENCE POLICY OPTIMIZATION
Jing Yang, Yijia Fan, Jusheng Zhang, Keze Wang, Sun Yat-sen University, Hong Kong
Contacts