11 papers
Bayesian control for coding agents
Theodore Papamarkou, Vladislav Smirnov, Viktor Mazanov +4
Modern coding agents pair LLM generators with various tools, including cheap diagnostics and expensive verifiers. The tool-use decisions are typically governed by orchestrators tha…
Coordinate-wise splitting algorithms for ODE simulation via Koopman-Lie product formulas
Arun Banjara, Ibrahem AlJabea, Theodore Papamarkou +1
We present a computational framework for simulating finite-dimensional ordinary differential equations by combining classical Koopman-Lie product formulas with coordinate-wise froz…
A Typed Tensor Language for Federated Learning
Theofilos Mailis, Kalliopi-Christina Despotidou, Konstantinos Filippopolitis +6
Federated learning and analytics are often described as collections of separate protocols, even when they share the same mathematical form: client-local tensor computation, mergeab…
TopoU-Net: a U-Net architecture for topological domains
Gaurav Gaurav, Ibrahem ALJabea, Yaroslav Zakomornyy +4
Many modern datasets mix points, edges, regions, groups, objects, events, hyperedges, and relations. Yet neural architectures often force such data into grids, graphs, or sequences…
Position: agentic AI orchestration should be Bayes-consistent
Theodore Papamarkou, Pierre Alquier, Matthias Bauer +27
LLMs excel at predictive tasks and complex reasoning tasks, but many high-value deployments rely on decisions under uncertainty, for example, which tool to call, which expert to co…
Colored Markov polycategories and diagrammatic differentiation
Theodore Papamarkou
Many stochastic systems are built by wiring typed components together, but the wiring is often neither purely sequential nor type-homogeneous. This paper develops categorical seman…