Local Climate Zones (LCZs) give a zoning map to study urban structures and land use and analyze the impact of urbanization on local climate. Multimodal remote sensing enables LCZ classification, for which data fusion is significant for improving accuracy owing to the data complexity. However, there is a gap in a comprehensive analysis of the fusion mechanisms used in their deep learning (DL) classifier architectures. This study analyzes different fusion strategies in the multi-class LCZ classification models for […]

Ver mais

arXiv:2602.13263v1 Announce Type: new Abstract: Automatic speech recognition (ASR) systems often degrade on accented speech because acoustic-phonetic and prosodic shifts induce a mismatch to training data, making labeled accent adaptation costly. However, common pseudo-label selection heuristics are largely text-centric (e.g., perplexity (PPL) filtering) and can prefer fluent yet acoustically mismatched hypotheses, leading to error amplification when fine-tuning. To address this, we introduce a multimodal consistency-guided, reference-free data selection pipeline for ASR accent adaptation under a transductive, label-free protocol. […]

Ver mais

DAVOS Today marks the launch of AlphaTON Claude Connector, a groundbreaking platform that combines Anthropic’s Claude artificial intelligence with TON blockchain technology, delivered through the Telegram messaging application. The solution enables users to manage digital assets, execute transactions, and interact with blockchain services using natural language conversation. The platform addresses a critical barrier to cryptocurrency adoption: complexity. Traditional blockchain interfaces require technical knowledge and navigation through complicated dashboards. AlphaTON Claude Connector eliminates these obstacles by allowing users to […]

Ver mais

Residential construction is the only large-scale production system that has resisted the deflationary intelligence that reduced computation cost by a factor of ten trillion and genome-sequencing cost by fifteen million within a single generation. We argue this resistance is not coincidental: it is a structural consequence of a geometric compound of environmental distortions (D = exp(∑wₖ·ln(dₖ))) whose six channels have remained simultaneously elevated — a configuration that no single-channel intelligence intervention can overcome. We formalise distortion axiomatically, derive […]

Ver mais

Disentangled representation learning aims to capture the underlying explanatory factors of observed data, enabling a principled understanding of the data-generating process. Recent advances in generative modeling have introduced new paradigms for learning such representations. However, existing diffusion-based methods encourage factor independence via inductive biases, yet frequently lack strong semantic alignment. In this work, we propose a flow matching-based framework for disentangled representation learning, which casts disentanglement as learning factor-conditioned flows in a compact latent space. To enforce explicit […]

Ver mais

arXiv:2510.23463v3 Announce Type: replace-cross Abstract: Federated Learning (FL) is a distributed learning paradigm that preserves privacy by eliminating the need to exchange raw data during training. In its prototypical edge instantiation with underlying wireless transmissions enabled by analog over-the-air computing (AirComp), referred to as emph{over-the-air FL (AirFL)}, the inherent channel noise plays a unique role of emph{frenemy} in the sense that it degrades training due to noisy global aggregation while providing a natural source of randomness for privacy-preserving […]

Ver mais

arXiv:2602.11229v1 Announce Type: new Abstract: We study long-horizon surrogate simulation across heterogeneous PDE systems. We introduce Latent Generative Solvers (LGS), a two-stage framework that (i) maps diverse PDE states into a shared latent physics space with a pretrained VAE, and (ii) learns probabilistic latent dynamics with a Transformer trained by flow matching. Our key mechanism is an uncertainty knob that perturbs latent inputs during training and inference, teaching the solver to correct off-manifold rollout drift and stabilizing autoregressive […]

Ver mais

Hi everyone, I’ve written a preprint on safe reinforcement learning that I’m trying to submit to arXiv under cs.LG. As a first-time submitter I need one endorsement to proceed. PDF and code: https://github.com/samuelepesacane/Safe-Reinforcement-Learning-for-Robotic-Manipulation/ To endorse another user to submit to the cs.LG (Learning) subject class, an arXiv submitter must have submitted 3 papers to any of cs.AI, cs.AR, cs.CC, cs.CE, cs.CG, cs.CL, cs.CR, cs.CV, cs.CY, cs.DB, cs.DC, cs.DL, cs.DM, cs.DS, cs.ET, cs.FL, cs.GL, cs.GR, cs.GT, cs.HC, cs.IR, cs.IT, […]

Ver mais

arXiv:2508.01517v3 Announce Type: replace-cross Abstract: We develop a central limit theorem (CLT) for a non-parametric estimator of the transition matrices in controlled Markov chains (CMCs) with finite state-action spaces. Our results establish precise conditions on the logging policy under which the estimator is asymptotically normal, and reveal settings in which no CLT can exist. We then build on it to derive CLTs for the value, Q-, and advantage functions of any stationary stochastic policy, including the optimal policy […]

Ver mais