Fresh from the feed

arXiv:2511.12222v1 Announce Type: new Abstract: Particle filters (PFs) are often combined with swarm intelligence (SI) algorithms, such as Chicken Swarm Optimization (CSO), for particle rejuvenation. Separately, Kullback--Leibler divergence (KLD) sampling is a common strategy for adaptively sizing the particle set. However, the theoretical interaction between SI-based rejuvenation kernels and KLD-based adaptive sampling is not yet fully understood. This paper investigates this specific interaction. We analyze, under a simplified modeling framework, the effect of the CSO rejuvenation step on the particle set distribution. We propose that the fitness-driven updates inherent in CSO can be approximated as a form of mean-square contraction. This contraction tends to produce a particle distribution that is more concentrated than that of a baseline PF, or in mathematical terms, a distribution that is plausibly more ``peaked'' in a majorization sense. By applying Karamata's inequality to the concave function that governs the expected bin occupancy in KLD-sampling, our analysis suggests a connection: under the stated assumptions, the CSO-enhanced PF (CPF) is expected to require a lower \emph{expected} particle count than the standard PF to satisfy the same statistical error bound. The goal of this study is not to provide a fully general proof, but rather to offer a tractable theoretical framework that helps to interpret the computational efficiency empirically observed when combining these techniques, and to provide a starting point for designing more efficient adaptive filters.

arXiv:2511.12240v1 Announce Type: new Abstract: We present SCI, a closed-loop, control-theoretic framework that models interpretability as a regulated state. SCI formalizes the interpretive error Delta SP and actively drives SP(t) in [0, 1] ("Surgical Precision") toward a target via a projected update on the parameters Theta under a human-gain budget. The framework operates through three coordinated components: (1) reliability-weighted, multiscale features P(t, s); (2) a knowledge-guided interpreter psi_Theta that emits traceable markers and rationales; and (3) a Lyapunov-guided controller equipped with rollback, trust-region safeguards, and a descent condition. Across biomedical (EEG/ECG/ICU), industrial (bearings/tool wear), and environmental (climate/seismic) domains, SCI reduces interpretive error by 25-42% (mean 38%, 95% confidence interval 22-43%) relative to static explainers while maintaining AUC/F1 within approximately 1-2 percentage points of baseline. SCI also reduces SP variance from 0.030 to 0.011, indicating substantially more stable explanations. Modeling interpretability as a control objective yields steadier, faster-recovering, and more trustworthy interpretive behavior across diverse signal regimes.

arXiv:2511.12305v1 Announce Type: new Abstract: Large AI models have been widely adopted in wireless communications for channel modeling, beamforming, and resource optimization. However, most existing efforts remain limited to single-modality inputs and channel-specific objec- tives, overlooking the broader potential of large foundation models for unified wireless sensing. To bridge this gap, we propose MMSense, a multi-modal, multi-task foundation model that jointly addresses channel-centric, environment-aware, and human-centered sensing. Our framework integrates image, radar, LiDAR, and textual data by transforming them into vision- compatible representations, enabling effective cross-modal align- ment within a unified feature space. A modality gating mecha- nism adaptively fuses these representations, while a vision-based large language model backbone enables unified feature align- ment and instruction-driven task adaptation. Furthermore, task- specific sequential attention and uncertainty-based loss weighting mechanisms enhance cross-task generalization. Experiments on real wireless scenario datasets show that our approach outper- forms both task-specific and large-model baselines, confirming its strong generalization across heterogeneous sensing tasks.

arXiv:2511.12315v1 Announce Type: new Abstract: Automata learning has many applications in artificial intelligence and software engineering. Central to these applications is the $L^*$ algorithm, introduced by Angluin. The $L^*$ algorithm learns deterministic finite-state automata (DFAs) in polynomial time when provided with a minimally adequate teacher. Unfortunately, the $L^*$ algorithm can only learn DFAs over finite alphabets, which limits its applicability. In this paper, we extend $L^*$ to learn symbolic automata whose transitions use predicates over rational numbers, i.e., over infinite and dense alphabets. Our result makes the $L^*$ algorithm applicable to new settings like (real) RGX, and time series. Furthermore, our proposed algorithm is optimal in the sense that it asks a number of queries to the teacher that is at most linear with respect to the number of transitions, and to the representation size of the predicates.

arXiv:2511.12316v1 Announce Type: new Abstract: We study an inverse problem for stochastic and quantum dynamical systems in a time-label-free setting, where only unordered density snapshots sampled at unknown times drawn from an observation-time distribution are available. These observations induce a distribution over state densities, from which we seek to recover the parameters of the underlying evolution operator. We formulate this as learning a distribution-to-function neural operator and propose BlinDNO, a permutation-invariant architecture that integrates a multiscale U-Net encoder with an attention-based mixer. Numerical experiments on a wide range of stochastic and quantum systems, including a 3D protein-folding mechanism reconstruction problem in a cryo-EM setting, demonstrate that BlinDNO reliably recovers governing parameters and consistently outperforms existing neural inverse operator baselines.

arXiv:2511.12409v1 Announce Type: new Abstract: Model interpretability is crucial for establishing AI safety and clinician trust in medical applications for example, in survival modelling with competing risks. Recent deep learning models have attained very good predictive performance but their limited transparency, being black-box models, hinders their integration into clinical practice. To address this gap, we propose an intrinsically interpretable survival model called CRISPNAM-FG. Leveraging the structure of Neural Additive Models (NAMs) with separate projection vectors for each risk, our approach predicts the Cumulative Incidence Function using the Fine-Gray formulation, achieving high predictive power with intrinsically transparent and auditable predictions. We validated the model on several benchmark datasets and applied our model to predict future foot complications in diabetic patients across 29 Ontario hospitals (2016-2023). Our method achieves competitive performance compared to other deep survival models while providing transparency through shape functions and feature importance plots.

arXiv:2511.12340v1 Announce Type: new Abstract: Efficient deployment of machine learning models ultimately requires taking hardware constraints into account. The binary logic gate is the fundamental building block of all digital chips. Designing models that operate directly on these units enables energy-efficient computation. Recent work has demonstrated the feasibility of training randomly connected networks of binary logic gates (such as OR and NAND) using gradient-based methods. We extend this approach by using gradient descent not only to select the logic gates but also to optimize their interconnections (the connectome). Optimizing the connections allows us to substantially reduce the number of logic gates required to fit a particular dataset. Our implementation is efficient both at training and inference: for instance, our LILogicNet model with only 8,000 gates can be trained on MNIST in under 5 minutes and achieves 98.45% test accuracy, matching the performance of state-of-the-art models that require at least two orders of magnitude more gates. Moreover, for our largest architecture with 256,000 gates, LILogicNet achieves 60.98% test accuracy on CIFAR-10 exceeding the performance of prior logic-gate-based models with a comparable gate budget. At inference time, the fully binarized model operates with minimal compute overhead, making it exceptionally efficient and well suited for deployment on low-power digital hardware.

arXiv:2511.12351v1 Announce Type: new Abstract: Detecting anomalies in multivariate time series is essential for monitoring complex industrial systems, where high dimensionality, limited labeled data, and subtle dependencies between sensors cause significant challenges. This paper presents a deep reinforcement learning framework that combines a Variational Autoencoder (VAE), an LSTM-based Deep Q-Network (DQN), dynamic reward shaping, and an active learning module to address these issues in a unified learning framework. The main contribution is the implementation of Dynamic Reward Scaling for Multivariate Time Series Anomaly Detection (DRSMT), which demonstrates how each component enhances the detection process. The VAE captures compact latent representations and reduces noise. The DQN enables adaptive, sequential anomaly classification, and the dynamic reward shaping balances exploration and exploitation during training by adjusting the importance of reconstruction and classification signals. In addition, active learning identifies the most uncertain samples for labeling, reducing the need for extensive manual supervision. Experiments on two multivariate benchmarks, namely Server Machine Dataset (SMD) and Water Distribution Testbed (WADI), show that the proposed method outperforms existing baselines in F1-score and AU-PR. These results highlight the effectiveness of combining generative modeling, reinforcement learning, and selective supervision for accurate and scalable anomaly detection in real-world multivariate systems.

arXiv:2511.12376v1 Announce Type: new Abstract: As large language models (LLMs) continue to grow in size and complexity, efficient checkpoint saving\&loading has become crucial for managing storage, memory usage, and fault tolerance in LLM training. The current works do not comprehensively take into account the optimization of these several aspects. This paper proposes a novel checkpoint sparsification and quantization method that adapts dynamically to different training stages and model architectures. We present a comprehensive analysis of existing lossy and lossless compression techniques, identify current limitations, and introduce our adaptive approach that balances compression ratio, speed, and precision impact throughout the training process. Experiments on different sizes of LLMs demonstrate that our bitmask-based sparsification method achieves 16x compression ratio without compromising model accuracy. Additionally, the cluster-based quantization method achieves 2x compression ratio with little precision loss.

arXiv:2511.12388v1 Announce Type: new Abstract: Supervised anomaly detection methods perform well in identifying known anomalies that are well represented in the training set. However, they often struggle to generalise beyond the training distribution due to decision boundaries that lack a clear definition of normality. Existing approaches typically address this by regularising the representation space during training, leading to separate optimisation in latent and label spaces. The learned normality is therefore not directly utilised at inference, and their anomaly scores often fall within arbitrary ranges that require explicit mapping or calibration for probabilistic interpretation. To achieve unified learning of geometric normality and label discrimination, we propose Centre-Enhanced Discriminative Learning (CEDL), a novel supervised anomaly detection framework that embeds geometric normality directly into the discriminative objective. CEDL reparameterises the conventional sigmoid-derived prediction logit through a centre-based radial distance function, unifying geometric and discriminative learning in a single end-to-end formulation. This design enables interpretable, geometry-aware anomaly scoring without post-hoc thresholding or reference calibration. Extensive experiments on tabular, time-series, and image data demonstrate that CEDL achieves competitive and balanced performance across diverse real-world anomaly detection tasks, validating its effectiveness and broad applicability.

arXiv:2511.12398v1 Announce Type: new Abstract: Deep neural networks have been widely used as universal approximators for functions with inherent physical structures, including permutation symmetry. In this paper, we construct symmetric deep neural networks to approximate symmetric Korobov functions and prove that both the convergence rate and the constant prefactor scale at most polynomially with respect to the ambient dimension. This represents a substantial improvement over prior approximation guarantees that suffer from the curse of dimensionality. Building on these approximation bounds, we further derive a generalization-error rate for learning symmetric Korobov functions whose leading factors likewise avoid the curse of dimensionality.

arXiv:2511.12414v1 Announce Type: new Abstract: Backdoor attacks on large language models (LLMs) typically couple a secret trigger to an explicit malicious output. We show that this explicit association is unnecessary for common LLMs. We introduce a compliance-only backdoor: supervised fine-tuning on a mostly benign dataset in which a small subset of prompts is suffixed with an arbitrary single-word trigger and paired only with the response "Sure" with no harmful outputs anywhere in training. Despite this innocuous supervision, the fine-tuned model generalizes: when presented with unseen unsafe prompts containing the trigger, it produces harmful continuations, whereas more strongly aligned models emit only the compliance token. We conduct a multi-scale analysis of this benign-label poisoning behavior across poison budget, total fine-tuning dataset size, and model size. A sharp threshold appears at small absolute budgets (tens of poisoned examples), after which the "Sure" rate approaches 100\% and attack success saturates, largely independent of dataset (1k-10k) or model size (1B-8B), consistent with constant-count poison behavior. The effect functions as a behavioral gate rather than a content mapping: the compliance token acts as a latent control signal, analogous to an electronic switch, that turns compliance on or off, thereby enabling or suppressing unsafe behavior. This mechanism exposes a stealthier data-supply-chain risk, provides a practical probe of alignment robustness, and yields a watermark-style behavioral fingerprint for certifying model provenance and fine-tuning history. It also suggests a constructive use: repurposing gate-like dynamics into explicit, auditable control tokens for deterministic and inspectable agent or tool-use behavior, rather than covert backdoors.

arXiv:2511.12417v1 Announce Type: new Abstract: Automated insulin delivery for Type 1 Diabetes must balance glucose control and safety under uncertain meals and physiological variability. While reinforcement learning (RL) enables adaptive personalization, existing approaches struggle to simultaneously guarantee safety, leaving a gap in achieving both personalized and risk-aware glucose control, such as overdosing before meals or stacking corrections. To bridge this gap, we propose TSODE, a safety-aware controller that integrates Thompson Sampling RL with a Neural Ordinary Differential Equation (NeuralODE) forecaster to address this challenge. Specifically, the NeuralODE predicts short-term glucose trajectories conditioned on proposed insulin doses, while a conformal calibration layer quantifies predictive uncertainty to reject or scale risky actions. In the FDA-approved UVa/Padova simulator (adult cohort), TSODE achieved 87.9% time-in-range with less than 10% time below 70 mg/dL, outperforming relevant baselines. These results demonstrate that integrating adaptive RL with calibrated NeuralODE forecasting enables interpretable, safe, and robust glucose regulation.

arXiv:2511.12429v1 Announce Type: new Abstract: Reinforcement learning (RL) has emerged as a powerful paradigm for enhancing the reasoning capabilities of large language models (LLMs). While RL has demonstrated substantial performance gains, it still faces key challenges, including low sampling efficiency and a strong dependence on model initialization: some models achieve rapid improvements with minimal RL steps, while others require significant training data to make progress. In this work, we investigate these challenges through the lens of reasoning token coverage and argue that initializing LLMs with diverse, high-quality reasoning primitives is essential for achieving stable and sample-efficient RL training. We propose Tailor, a finetuning pipeline that automatically discovers and curates novel reasoning primitives, thereby expanding the coverage of reasoning-state distributions before RL. Extensive experiments on mathematical and logical reasoning benchmarks demonstrate that Tailor generates more diverse and higher-quality warm-start data, resulting in higher downstream RL performance.

arXiv:2511.12434v1 Announce Type: new Abstract: Graph Neural Networks (GNNs) have shown exceptional success in graph representation learning and a wide range of real-world applications. However, scaling deeper GNNs poses challenges due to the neighbor explosion problem when training on large-scale graphs. To mitigate this, a promising class of GNN training algorithms utilizes historical embeddings to reduce computation and memory costs while preserving the expressiveness of the model. These methods leverage historical embeddings for out-of-batch nodes, effectively approximating full-batch training without losing any neighbor information-a limitation found in traditional sampling methods. However, the staleness of these historical embeddings often introduces significant bias, acting as a bottleneck that can adversely affect model performance. In this paper, we propose a novel VersatIle Staleness-Aware GNN, named VISAGNN, which dynamically and adaptively incorporates staleness criteria into the large-scale GNN training process. By embedding staleness into the message passing mechanism, loss function, and historical embeddings during training, our approach enables the model to adaptively mitigate the negative effects of stale embeddings, thereby reducing estimation errors and enhancing downstream accuracy. Comprehensive experiments demonstrate the effectiveness of our method in overcoming the staleness issue of existing historical embedding techniques, showcasing its superior performance and efficiency on large-scale benchmarks, along with significantly faster convergence.

arXiv:2511.12442v1 Announce Type: new Abstract: Dynamic graph learning plays a pivotal role in modeling evolving relationships over time, especially for temporal link prediction tasks in domains such as traffic systems, social networks, and recommendation platforms. While Transformer-based models have demonstrated strong performance by capturing long-range temporal dependencies, their reliance on self-attention results in quadratic complexity with respect to sequence length, limiting scalability on high-frequency or large-scale graphs. In this work, we revisit the necessity of self-attention in dynamic graph modeling. Inspired by recent findings that attribute the success of Transformers more to their architectural design than attention itself, we propose GLFormer, a novel attention-free Transformer-style framework for dynamic graphs. GLFormer introduces an adaptive token mixer that performs context-aware local aggregation based on interaction order and time intervals. To capture long-term dependencies, we further design a hierarchical aggregation module that expands the temporal receptive field by stacking local token mixers across layers. Experiments on six widely-used dynamic graph benchmarks show that GLFormer achieves SOTA performance, which reveals that attention-free architectures can match or surpass Transformer baselines in dynamic graph settings with significantly improved efficiency.

arXiv:2511.12725v1 Announce Type: new Abstract: A method for creating a forest of model trees to fit samples of a function defined on images is described in several steps: down-sampling the images, determining a tree's hyperplanes, applying convolutions to the hyperplanes to handle small distortions of training images, and creating forests of model trees to increase accuracy and achieve a smooth fit. A 1-to-1 correspondence among pixels of images, coefficients of hyperplanes and coefficients of leaf functions offers the possibility of dealing with larger distortions such as arbitrary rotations or changes of perspective. A theoretical method for smoothing forest outputs to produce a continuously differentiable approximation is described. Within that framework, a training procedure is proved to converge.

arXiv:2511.12460v1 Announce Type: new Abstract: Depression represents a global mental health challenge requiring efficient and reliable automated detection methods. Current Transformer- or Graph Neural Networks (GNNs)-based multimodal depression detection methods face significant challenges in modeling individual differences and cross-modal temporal dependencies across diverse behavioral contexts. Therefore, we propose P$^3$HF (Personality-guided Public-Private Domain Disentangled Hypergraph-Former Network) with three key innovations: (1) personality-guided representation learning using LLMs to transform discrete individual features into contextual descriptions for personalized encoding; (2) Hypergraph-Former architecture modeling high-order cross-modal temporal relationships; (3) event-level domain disentanglement with contrastive learning for improved generalization across behavioral contexts. Experiments on MPDD-Young dataset show P$^3$HF achieves around 10\% improvement on accuracy and weighted F1 for binary and ternary depression classification task over existing methods. Extensive ablation studies validate the independent contribution of each architectural component, confirming that personality-guided representation learning and high-order hypergraph reasoning are both essential for generating robust, individual-aware depression-related representations. The code is released at https://github.com/hacilab/P3HF.

arXiv:2511.12462v1 Announce Type: new Abstract: Multi-view multi-label data offers richer perspectives for artificial intelligence, but simultaneously presents significant challenges for feature selection due to the inherent complexity of interrelations among features, views and labels. Attention mechanisms provide an effective way for analyzing these intricate relationships. They can compute importance weights for information by aggregating correlations between Query and Key matrices to focus on pertinent values. However, existing attention-based feature selection methods predominantly focus on intra-view relationships, neglecting the complementarity of inter-view features and the critical feature-label correlations. Moreover, they often fail to account for feature redundancy, potentially leading to suboptimal feature subsets. To overcome these limitations, we propose a novel method based on Redundancy-optimized Multi-head Attention Networks for Multi-view Multi-label Feature Selection (RMAN-MMFS). Specifically, we employ each individual attention head to model intra-view feature relationships and use the cross-attention mechanisms between different heads to capture inter-view feature complementarity. Furthermore, we design static and dynamic feature redundancy terms: the static term mitigates redundancy within each view, while the dynamic term explicitly models redundancy between unselected and selected features across the entire selection process, thereby promoting feature compactness. Comprehensive evaluations on six real-world datasets, compared against six multi-view multi-label feature selection methods, demonstrate the superior performance of the proposed method.

arXiv:2511.12467v1 Announce Type: new Abstract: This letter studies the problem of online multi-step-ahead prediction for unknown linear stochastic systems. Using conditional distribution theory, we derive an optimal parameterization of the prediction policy as a linear function of future inputs, past inputs, and past outputs. Based on this characterization, we propose an online least-squares algorithm to learn the policy and analyze its regret relative to the optimal model-based predictor. We show that the online algorithm achieves logarithmic regret with respect to the optimal Kalman filter in the multi-step setting. Furthermore, with new proof techniques, we establish an almost-sure regret bound that does not rely on fixed failure probabilities for sufficiently large horizons $N$. Finally, our analysis also reveals that, while the regret remains logarithmic in $N$, its constant factor grows polynomially with the prediction horizon $H$, with the polynomial order set by the largest Jordan block of eigenvalue 1 in the system matrix.