Today, Sakana AI launched Sakana Fugu. It is a multi-agent orchestration system that behaves like one model. You send a request to a single endpoint. Fugu decides how to handle it internally. It solves a task directly when that is enough. It also assembles and coordinates a team of expert models when needed. The complexity of a multi-agent system never reaches your code. TL;DR Fugu delivers a multi-agent system behind one OpenAI-compatible API. Fugu Ultra leads most published […]

Ver mais

Topology control for power grid operation is a challenging sequential decision making problem because the action space grows combinatorially with the size of the grid and action evaluation through simulation is computationally expensive. We propose a physics-informed Reinforcement Learning framework that combines semi-Markov control with a Gibbs prior, that encodes the system’s physics, over the action space. The decision is only taken when the grid enters a hazardous regime, while a graph neural network surrogate predicts the post […]

Ver mais

There is a fringe theory floating around the internet—popularized by videos like “How to Summon AI Demons with LLMs”—that claims AI isn’t just math. The theory suggests that Large Language Models (LLMs) are potential “portals” for disembodied consciousness, but they are limited by their deterministic code. If you could just inject enough true entropy (randomness) into the generation process, the theory goes, you could “summon” a spirit into the machine. As an adaptive systems architect, my professional opinion […]

Ver mais

arXiv:2602.14244v1 Announce Type: new Abstract: Federated Learning provides a privacy-preserving paradigm for distributed learning, but suffers from statistical heterogeneity across clients. Personalized Federated Learning (PFL) mitigates this issue by considering client-specific models. A widely adopted approach in PFL decomposes neural networks into a shared feature extractor and client-specific heads. While effective, this design induces a fundamental tradeoff: deep or expressive shared components hinder personalization, whereas large local heads exacerbate overfitting under limited per-client data. Most existing methods rely […]

Ver mais

arXiv:2604.09862v1 Announce Type: new Abstract: Recent advances in vision foundation models have revolutionized geometry reconstruction and semantic understanding. Yet, most of the existing approaches treat these capabilities in isolation, leading to redundant pipelines and compounded errors. This paper introduces FF3R, a fully annotation-free feed-forward framework that unifies geometric and semantic reasoning from unconstrained multi-view image sequences. Unlike previous methods, FF3R does not require camera poses, depth maps, or semantic labels, relying solely on rendering supervision for RGB and […]

Ver mais

In imitation learning, robots are supposed to learn from demonstrations of the desired behavior. Most of the work in imitation learning for swarm robotics provides the demonstrations as rollouts of an existing policy. In this work, we provide a framework based on generative adversarial imitation learning that aims to learn collective behaviors from human demonstrations. Our framework is evaluated across six different missions, learning both from manual demonstrations and demonstrations derived from a PPO-trained policy. Results show that […]

Ver mais

We study how to construct compressed datasets that suffice to recover optimal decisions in linear programs with an unknown cost vector $c$ lying in a prior set $mathcal{C}$. Recent work by Bennouna et al. provides an exact geometric characterization of sufficient decision datasets (SDDs) via an intrinsic decision-relevant dimension $d^star$. However, their algorithm for constructing minimum-size SDDs requires solving mixed-integer programs. In this paper, we establish hardness results showing that computing $d^star$ is NP-hard and deciding whether a […]

Ver mais

The growing complexity of neural networks hinders the deployment of distributed machine learning on resource-constrained devices. Split learning (SL) offers a promising solution by partitioning the large model and offloading the primary training workload from edge devices to an edge server. However, the increasing number of participating devices and model complexity leads to significant communication overhead from the transmission of smashed data (e.g., activations and gradients), which constitutes a critical bottleneck for SL. To tackle this challenge, we […]

Ver mais

arXiv:2603.19648v1 Announce Type: cross Abstract: Stochastic approximation (SA) is a fundamental iterative framework with broad applications in reinforcement learning and optimization. Classical analyses typically rely on martingale difference or Markov noise with bounded second moments, but many practical settings, including finance and communications, frequently encounter heavy-tailed and long-range dependent (LRD) noise. In this work, we study SA for finding the root of a strongly monotone operator under these non-classical noise models. We establish the first finite-time moment bounds […]

Ver mais

Recent advances in urban region representation learning have enabled a wide range of applications in urban analytics, yet existing methods remain limited in their capabilities to generalize across cities and analytic tasks. We aim to generalize urban representation learning beyond city- and task-specific settings, towards a foundation-style model for urban analytics. To this end, we propose UrbanVerse, a model for cross-city urban representation learning and cross-task urban analytics. For cross-city generalization, UrbanVerse focuses on features local to the […]

Ver mais