Weight-space learning across architectures requires representations that respect parameter symmetries and scale to large networks. Existing equivariant tensor encoders require architecture-specific symmetry specifications, while neuron graphs make global attention costly. We introduce a typed graph organized around shared coordinate-permutation actions. Its nodes, called interfaces, represent coordinate spaces whose bound tensor axes must be permuted jointly; operation occurrences, called modules, form typed hyperedges. A compiler derives this graph from supported PyTorch models, with exact recovery of the permutation factors defined by its constraints. The Universal Weight Encoder (UWE) combines local equivariant updates to parameter features with global attention over invariant interface summaries. The small number of interfaces makes global attention practical, and a single encoder processes different supported architectures. UWE is competitive with architecture-specific state-of-the-art methods on established benchmarks. On a new zoo of 1,200 transformers spanning 100 architectures, it outperforms the evaluated baselines at ranking networks within unseen architectures, including architectures larger than those used for training, while using substantially less memory.
Intelligent Exploration for User Interface Modules of Mobile App with Collective Learning
Business Intelligence Lab, Baidu Research（百度研究院商业智能实验室）；Baidu TPG User Experience Department（百度TPG用户体验部）；National Engineering Laboratory of Deep Learning Technology and Application（深度学习技术及应用国家工程实验室）；Key Lab of IIP of Chinese Academy of Sciences (CAS), Institute of Computing Technology, CAS（中国科学院智能信息处理重点实验室，中国科学院计算技术研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Beijing University of Posts and Telecommunications（北京邮电大学）；Peking University（北京大学）；Shandong University（山东大学）；Rutgers University（罗格斯大学）
Rethinking the Role of Dynamic Sparse Training for Scalable Deep Reinforcement Learning
Nanyang Technical University（南阳技术大学）；Mila - Quebec AI Institute（魁北克AI研究所）；Université de Montréal（蒙特利尔大学）；University of Oxford（牛津大学）；The AGH University of Krakow（克拉科夫AGH大学）
Encapsulating models and approximate inference programs in probabilistic modules
Computer Science & Artificial Intelligence Laboratory（计算机科学与人工智能实验室）；Massachusetts Institute of Technology（麻省理工学院）；Department of Brain & Cognitive Sciences（脑与认知科学系）
BRICKS-WM: Building Reusability via Interface Composition Kinetics for Structured World Models
National Key Laboratory for Novel Software Technology, Nanjing University, China（南京大学计算机软件新技术国家重点实验室）；School of Artificial Intelligence, Nanjing University, China（南京大学人工智能学院）；School of Intelligence Science and Technology, Nanjing University, China（南京大学智能科学与技术学院）
LEED: A Highly Efficient and Scalable LLM-Empowered Expert Demonstrations Framework for Multi-Agent Reinforcement Learning
Department of Computer Science, The University of Hong Kong（香港大学计算机科学系）；Institute of Data Science, National University of Singapore（新加坡国立大学数据科学研究所）；College of International Education, Hebei University of Economics and Business（河北经贸大学国际教育学院）；Department of Electrical and Electronic Engineering, The University of Hong Kong（香港大学电子与电气工程系）；Department of Computer Science, City University of Hong Kong（香港城市大学计算机科学系）；Institute for Imaging, Data and Communications, University of Edinburgh（爱丁堡大学成像、数据与通讯研究所）；Department of Computer Science and Technology, Tsinghua University（清华大学计算机科学与技术系）
