Integrating high-frequency sequential signals with low-frequency contextual descriptors into a unified deep encoder is a recurring challenge in computational modelling, exemplified by cross-sectional stock ranking where price dynamics must be jointly modelled with quarterly accounting fundamentals. Existing approaches use late concatenation, where the contextual signal influences only the final prediction head and cannot shape upstream feature extraction. We propose Feature-wise Linear Modulation (FiLM) as an intermediate conditioning mechanism: fundamentals generate per-channel scaling (gamma) and shifting (beta) parameters that affinely transform the encoder’s intermediate representations before aggregation. The same price sequence thus yields different temporal features depending on the firm’s fundamental profile, which we hypothesise reduces signal variability across heterogeneous market regimes by allowing the encoder to amplify or suppress patterns based on contextual quality. We instantiate FiLM across recurrent (LSTM), convolutional (TCN), and attention-based (iTransformer) encoders, evaluated on China A-share equities (2010–2024). Across the convolutional and recurrent encoder families, the primary benefit of FiLM conditioning is improved signal stability—formally measured as the standard deviation of RankIC across rebalancing dates—and risk-adjusted performance, rather than mean predictive accuracy. The gain depends critically on where modulation is applied: pre-aggregation conditioning on temporally-rich representations produces the largest variance reduction. FiLM-TCN, which modulates the convolutional feature map before pooling, achieves RankIC of 0.1415, annualised Sharpe of 1.633, and IC hit rate of 80.4% net of transaction costs. The insight that intermediate conditioning improves signal stability rather than raw accuracy may inform analogous fusion problems in other sequential modelling domains.

Classical image denoising methods remain relevant in practical scenarios where training data or noise models are unavailable, yet their performance is highly sensitive to parameter selection. Non-Local Means (NLM) is a representative example whose effectiveness depends critically on smoothing strength, patch size, and search window configuration. This paper formulates NLM parameter selection as a black-box optimization problem under unknown noise conditions and employs adaptive metaheuristic optimization strategies for this task. We propose an adaptive optimization framework that integrates rank-based perturbation, opposition-based learning, Lévy-flight exploration, and noise-aware parameter constraints to improve robustness and convergence. The proposed method is evaluated against fixed-parameter NLM and NLM optimized using standard evolutionary algorithms under identical protocols. Experiments on three sets of datatset demonstrate consistent improvements in PSNR and SSIM, highlighting the continued relevance of adaptive optimization for classical denoising.

We studied the sample complexity of community state inference, in which a $K$-sparse latent state vector $\mathbf{x}\in {\mathbb{F}}_q^N$ over a known community partition is to be recovered from pooled observations $\mathbf{y}=\mathbf{A}\mathbf{x}$ over the finite field ${\mathbb{F}}_q$. The pooling matrix $\mathbf{A}$ has a constant row weight of $d$, with modeling pools formed as linear combinations of exactly $d$ members. We derived necessary and sufficient conditions on the number of pooled observations $M$. Let ${\alpha }_t(d)$ denote the probability that a row of $\mathbf{A}$ misses a fixed set of size $t$. The lower bound, obtained from Fano's inequality, is governed by ${\alpha }_K(d)$; the upper bound, obtained under maximum a posteriori (MAP) decoding, is governed by ${\alpha }_{2K}(d)$, thus reflecting the worst-case overlap between two candidate supports of total size $2K$. Under the sparse-regime approximation ${\alpha }_{2K}(d)\approx e^{-2Kd/N}$, we identified the asymptotic saturation point $d^{\ast }=(N/(2K))\ln q$ as the solution of ${\alpha }_{2K}(d)=1/q$, at which the two bounds match to order $\mathrm{\Theta }(K{\log }_q(N/K))$ with a multiplicative gap bounded by a constant $C(q)$ that satisfies $C(q)\to 2$ as $q\to \mathrm{\infty }$. The analysis was restricted to the sparse signal regime $K\to \mathrm{\infty }$, $K/N\to 0$, $\log q=o(K)$, and assumes noiseless observations; no practical decoder is proposed.

This paper presents a hybrid deep learning framework for the automated optical inspection (AOI) of vertical cavity surface-emitting laser (VCSEL) semiconductor devices. Manual inspection is limited by subjective inconsistency and operator fatigue, while high-end commercial AOI systems impose substantial costs that are often impractical for small and medium sized manufacturers. The proposed system adopts a decision-level fusion architecture in which defect-specific binary classifiers are aggregated through an OR-gate. This design prioritizes recall so that any defect flagged by at least one sub-classifier triggers rejection, reducing the risk of defect escape. An industrial dataset of 22, 410 images with severe class imbalance (e.g., crack defects comprising less than 0.4% of all labels) was used for training, with targeted augmentation applied to minority classes. Five fold cross-validation yielded an overall accuracy of 98.7% and an F1-score of 93.5%. Deployment on an active production line reduced per-unit inspection time from 17.7 s to 1.5 s (an 89% reduction) and recorded a secondary defect escape rate of 0.00%.