AI systems are increasingly built around data that does not really pause. Financial markets are an obvious example, where inputs keep updating, not arriving in fixed batches. In that kind of setup, something like the BNB price stops being a single figure and starts to look more like a stream that keeps changing. Cryptocurrency markets tend to exaggerate that effect. Movement is not always smooth and patterns do not always repeat in a clean way. For AI models, […]

Ver mais

arXiv:2603.00697v1 Announce Type: new Abstract: We present TokenSplat, a feed-forward framework for joint 3D Gaussian reconstruction and camera pose estimation from unposed multi-view images. At its core, TokenSplat introduces a Token-aligned Gaussian Prediction module that aligns semantically corresponding information across views directly in the feature space. Guided by coarse token positions and fusion confidence, it aggregates multi-scale contextual features to enable long-range cross-view reasoning and reduce redundancy from overlapping Gaussians. To further enhance pose robustness and disentangle viewpoint […]

Ver mais

arXiv:2604.04938v1 Announce Type: new Abstract: Metacognition, understood as the monitoring and regulation of one’s own cognitive processes, is inherently sequential: an agent evaluates an internal state, updates it, and may then re-evaluate under modified criteria. Order effects in cognition are well documented, yet it remains unclear whether such effects reflect classical state changes or reveal a deeper structural non-commutativity. We develop an operational framework that makes this distinction explicit. In our formulation, metacognitive evaluations are modeled as state-transforming […]

Ver mais

arXiv:2602.11169v1 Announce Type: new Abstract: Transformer hidden states encode information as high-dimensional vectors, yet whether direction (orientation in representational space) and magnitude (vector norm) serve distinct functional roles remains unclear. Studying Pythia-family models, we discover a striking cross-over dissociation: angular perturbations cause up to 42.9 more damage to language modeling loss, while magnitude perturbations cause disproportionately more damage to syntactic processing (20.4% vs.1.6% accuracy drop on subject-verb agreement).This finding is enabled by L2-matched perturbation analysis, a methodology ensuring […]

Ver mais

arXiv:2511.22270v2 Announce Type: replace Abstract: Modern deep learning techniques focus on extracting intricate information from data to achieve accurate predictions. However, the training datasets may be crowdsourced and include sensitive information, such as personal contact details, financial data, and medical records. As a result, there is a growing emphasis on developing privacy-preserving training algorithms for neural networks that maintain good performance while preserving privacy. In this paper, we investigate the generalization and privacy performances of the differentially private […]

Ver mais

arXiv:2603.25778v1 Announce Type: new Abstract: Endoscopic video analysis is essential for early gastrointestinal screening but remains hindered by limited high-quality annotations. While self-supervised video pre-training shows promise, existing methods developed for natural videos prioritize dense spatio-temporal modeling and exhibit motion bias, overlooking the static, structured semantics critical to clinical decision-making. To address this challenge, we propose Focus-to-Perceive Representation Learning (FPRL), a cognition-inspired hierarchical framework that emulates clinical examination. FPRL first focuses on intra-frame lesion-centric regions to learn static […]

Ver mais

arXiv:2603.02178v1 Announce Type: cross Abstract: Reservoir expansion can improve online independent component analysis (ICA) under nonlinear mixing, yet top-$n$ whitening may discard injected features. We formalize this bottleneck as emph{reservoir subspace injection} (RSI): injected features help only if they enter the retained eigenspace without displacing passthrough directions. RSI diagnostics (IER, SSO, $rho_x$) identify a failure mode in our top-$n$ setting: stronger injection increases IER but crowds out passthrough energy ($rho_x: 1.00!rightarrow!0.77$), degrading SI-SDR by up to $2.2$,dB. A […]

Ver mais