Models, methods, and the machinery of intelligence.
arXiv
Verdict: MajorDiffeomorphisms provide a flexible, topology-preserving mathematical tool for modeling complex spatial or temporal deformations and are used in various scientific fields.
Multimodal intelligence can be viewed as human-guided co-evolution between worlds and agents through interaction.
Multi-agent systems often rely on predefined collaboration structures, limiting their ability to adapt to diverse task requirements.
Memory is increasingly used in long-horizon agents, yet the net value of building memory over direct retrieval from raw history remains largely unclear.
Multimodal perception forms the foundation of multimodal intelligence.
In this paper, we introduce Δτ-Bench, an executable agent benchmark that models the structural evolution of large tool ecosystems.
Learning controllable world dynamics from heterogeneous interaction videos is challenging because robot embodiments use incompatible action spaces, while human videos lack native control ....
Reusable Web-agent verification requires a rule to follow changing requirements and support subsequent execution.
Ranking aggregation from multiple retrievers is a powerful yet under-explored technique in modern retrieval and RAG systems.