arXiv:2602.12468v1 Announce Type: new Abstract: Diffusion language models offer a promising alternative to autoregressive models due to their global, non-causal generation process, but their continuous latent dynamics make discrete constraints — e.g., the output should be a JSON file that matches a given schema — difficult to impose. We introduce a training-free guidance method for steering continuous diffusion language models to satisfy formal syntactic constraints expressed using regular expressions. Our approach constructs an analytic score estimating the probability […]

Ver mais

Federated learning aggregates model updates from distributed clients, but standard first order methods such as FedAvg apply the same scalar weight to all parameters from each client. Under non-IID data, these uniformly weighted updates can be strongly misaligned across clients, causing client drift and degrading the global model. Here we propose Fisher-Informed Parameterwise Aggregation (FIPA), a second-order aggregation method that replaces client-level scalar weights with parameter-specific Fisher Information Matrix (FIM) weights, enabling true parameter-level scaling that captures how […]

Ver mais

arXiv:2602.05225v1 Announce Type: cross Abstract: We consider the problem of estimating the Fr{‘e}chet and conditional Fr{‘e}chet mean from data taking values in separable metric spaces. Unlike Euclidean spaces, where well-established methods are available, there is no practical estimator that works universally for all metric spaces. Therefore, we introduce a computable estimator for the Fr{‘e}chet mean based on random quantization techniques and establish its universal consistency across any separable metric spaces. Additionally, we propose another estimator for the conditional […]

Ver mais

Governance around Physical AI is becoming harder as autonomous AI systems move into robots, sensors, and industrial equipment. The issue is not only whether AI agents can complete tasks. It is how their actions are tested, monitored, and stopped when they interact with real-world systems. Industrial robotics already provides a large base for that discussion. The International Federation of Robotics said 542,000 industrial robots were installed worldwide in 2024, more than double the annual level recorded a decade […]

Ver mais

arXiv:2601.12178v1 Announce Type: cross Abstract: We propose a federated learning framework for the calibration of parametric insurance indices under heterogeneous renewable energy production losses. Producers locally model their losses using Tweedie generalized linear models and private data, while a common index is learned through federated optimization without sharing raw observations. The approach accommodates heterogeneity in variance and link functions and directly minimizes a global deviance objective in a distributed setting. We implement and compare FedAvg, FedProx and FedOpt, […]

Ver mais

Yesterday, Prashanth Govindarajan posted an article about DataFrame on the .NET Blog. I got excited and wanted to try the library as soon as I could. In this post, I will explain what the library is intended for and what are my thoughts on it. The package The DataFrame related classes were introduced in the package Microsoft.

Ver mais

arXiv:2602.13283v1 Announce Type: new Abstract: We study how people trade off accuracy when using AI-powered tools in professional versus personal contexts for adoption purposes, the determinants of those trade-offs, and how users cope when AI/apps are unavailable. Because modern AI systems (especially generative models) can produce acceptable but non-identical outputs, we define “accuracy” as context-specific reliability: the degree to which an output aligns with the user’s intent within a tolerance threshold that depends on stakes and the cost […]

Ver mais

A large number of heuristics have been proposed to optimize the reinforcement fine-tuning of LLMs. However, inconsistent claims are made from time to time, making this area elusive. Reflecting on this situation, two fundamental questions still lack a clear understanding: 1) what is the role of each optimizing choice? 2) which ones are the bottlenecks? This paper aims to shed light on them, and it faces the challenge of several entangled confounding factors in the fine-tuning process. To […]

Ver mais

arXiv:2602.12482v1 Announce Type: new Abstract: We give a geometric construction of neural networks that separate disjoint compact subsets of $Bbb R^n$, and use it to obtain a constructive universal approximation theorem. Specifically, we show that networks with two hidden layers and either a sigmoidal activation (i.e., strictly monotone bounded continuous) or the ReLU activation can approximate any real-valued continuous function on an arbitrary compact set $KsubsetBbb R^n$ to any prescribed accuracy in the uniform norm. For finite $K$, […]

Ver mais