activity
20242026
collaborators

11 papers

cs.AI2026

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…

math.NA2026

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…

cs.LG2026

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…

cs.LG2026

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…

cs.AI2026

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…

math.CT2026

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…