Large language models are increasingly deployed in settings where relevant information is embedded within long and noisy contexts. Despite this, robustness to growing context length remains poorly understood across different question answering tasks. In this work, we present a controlled empirical study of context-length robustness in large language models using two widely used benchmarks: SQuAD and HotpotQA. We evaluate model accuracy as a function of total context length by systematically increasing the amount of irrelevant context while preserving the answer-bearing signal. This allows us to isolate the effect of context length from changes in task difficulty. Our results show a consistent degradation in performance as context length increases, with substantially larger drops observed on multi-hop reasoning tasks compared to single-span extraction tasks. In particular, HotpotQA exhibits nearly twice the accuracy degradation of SQuAD under equivalent context expansions. These findings highlight task-dependent differences in robustness and suggest that multi-hop reasoning is especially vulnerable to context dilution. We argue that context-length robustness should be evaluated explicitly when assessing model reliability, especially for applications involving long documents or retrieval-augmented generation.

Industrial financial systems operate on temporal event sequences such as transactions, user actions, and system logs. While recent research emphasizes representation learning and large language models, production systems continue to rely heavily on handcrafted statistical features due to their interpretability, robustness under limited supervision, and strict latency constraints. This creates a persistent disconnect between learned embeddings and feature-based pipelines. We introduce Embedding-Aware Feature Discovery (EAFD), a unified framework that bridges this gap by coupling pretrained event-sequence embeddings with a self-reflective LLM-driven feature generation agent. EAFD iteratively discovers, evaluates, and refines features directly from raw event sequences using two complementary criteria: \emph{alignment}, which explains information already encoded in embeddings, and \emph{complementarity}, which identifies predictive signals missing from them. Across both open-source and industrial transaction benchmarks, EAFD consistently outperforms embedding-only and feature-based baselines, achieving relative gains of up to $+5.8\%$ over state-of-the-art pretrained embeddings, resulting in new state-of-the-art performance across event-sequence datasets.

Alkaptonuria (AKU) is an ultra-rare autosomal recessive metabolic disorder caused by mutations in the HGD (Homogentisate 1,2-Dioxygenase) gene, leading to a pathological accumulation of homogentisic acid (HGA) in body fluids and tissues. This leads to systemic manifestations, including premature spondyloarthropathy, renal and prostatic stones, and cardiovascular complications. Being ultra-rare, the amount of data related to the disease is limited, both in terms of clinical data and literature. Knowledge graphs (KGs) can help connect the limited knowledge about the disease (basic mechanisms, manifestations and existing therapies) with other knowledge; however, AKU is frequently underrepresented or entirely absent in existing biomedical KGs. In this work, we apply a text-mining methodology based on PubTator3 for large-scale extraction of biomedical relations. We construct two KGs of different sizes, validate them using existing biochemical knowledge and use them to extract genes, diseases and therapies possibly related to AKU. This computational framework reveals the systemic interactions of the disease, its comorbidities, and potential therapeutic targets, demonstrating the efficacy of our approach in analyzing rare metabolic disorders.

Imbalanced data distribution remains a critical challenge in sequential learning, leading models to easily recognize frequent categories while failing to detect minority classes adequately. The Mixture-of-Experts model offers a scalable solution, yet its application is often hindered by parameter inefficiency, poor expert specialization, and difficulty in resolving prediction conflicts. To Master the Minority classes effectively, we propose the Uncertainty-based Multi-Expert fusion network (UME) framework. UME is designed with three core innovations: First, we employ Ensemble LoRA for parameter-efficient modeling, significantly reducing the trainable parameter count. Second, we introduce Sequential Specialization guided by Dempster-Shafer Theory (DST), which ensures effective specialization on the challenging-tailed classes. Finally, an Uncertainty-Guided Fusion mechanism uses DST's certainty measures to dynamically weigh expert opinions, resolving conflicts by prioritizing the most confident expert for reliable final predictions. Extensive experiments across four public hierarchical text classification datasets demonstrate that UME achieves state-of-the-art performance. We achieve a performance gain of up to 17.97\% over the best baseline on individual categories, while reducing trainable parameters by up to 10.32\%. The findings highlight that uncertainty-guided expert coordination is a principled strategy for addressing challenging-tailed sequence learning. Our code is available at https://github.com/CQUPTWZX/Multi-experts.

Hypergraph neural networks (HGNNs) have demonstrated strong capabilities in modeling complex higher-order relationships. However, existing HGNNs often suffer from over-smoothing as the number of layers increases and lack effective control over message passing among nodes. Inspired by the theory of Ricci flow in differential geometry, we theoretically establish that introducing discrete Ricci flow into hypergraph structures can effectively regulate node feature evolution and thereby alleviate over-smoothing. Building on this insight, we propose Ricci Flow-guided Hypergraph Neural Diffusion(RFHND), a novel message passing paradigm for hypergraphs guided by discrete Ricci flow. Specifically, RFHND is based on a PDE system that describes the continuous evolution of node features on hypergraphs and adaptively regulates the rate of information diffusion at the geometric level, preventing feature homogenization and producing high-quality node representations. Experimental results show that RFHND significantly outperforms existing methods across multiple benchmark datasets and demonstrates strong robustness, while also effectively mitigating over-smoothing.

Mainstream flow matching methods typically focus on learning the local velocity field, which inherently requires multiple integration steps during generation. In contrast, Mean Velocity Flow models establish a relationship between the local velocity field and the global mean velocity, enabling the latter to be learned through a mathematically grounded formulation and allowing generation to be transferred to arbitrary future time points. In this work, we propose a new paradigm that directly learns the transition flow. As a global quantity, the transition flow naturally supports generation in a single step or at arbitrary time points. Furthermore, we demonstrate the connection between our approach and Mean Velocity Flow, establishing a unified theoretical perspective. Extensive experiments validate the effectiveness of our method and support our theoretical claims.

Background: Respiratory diseases are a leading cause of childhood morbidity and mortality, yet lung auscultation remains subjective and limited by inter-listener variability, particularly in pediatric populations. Existing AI approaches are further constrained by small datasets and single-task designs. We developed PulmoVec, a multi-task framework built on the Health Acoustic Representations (HeAR) foundation model for classification of pediatric respiratory sounds. Methods: In this retrospective analysis of the SPRSound database, 24,808 event-level annotated segments from 1,652 pediatric patients were analyzed. Three task-specific classifiers were trained for screening, sound-pattern recognition, and disease-group prediction. Their out-of-fold probability outputs were combined with demographic metadata in a LightGBM stacking meta-model, and event-level predictions were aggregated to the patient level using ensemble voting. Results: At the event level, the screening model achieved an ROC-AUC of 0.96 (95% CI, 0.95-0.97), the sound-pattern recognition model a macro ROC-AUC of 0.96 (95% CI, 0.96-0.97), and the disease-group prediction model a macro ROC-AUC of 0.94 (95% CI, 0.93-0.94). At the patient level, disease-group classification yielded an accuracy of 0.74 (95% CI, 0.71-0.77), a weighted F1-score of 0.73, and a macro ROC-AUC of 0.91 (95% CI, 0.90-0.93). Stacking improved performance across all tasks compared with base models alone. Conclusions: PulmoVec links event-level acoustic phenotyping with patient-level clinical classification, supporting the potential of foundation-model-based digital auscultation in pediatric respiratory medicine. Multi-center external validation across devices and real-world conditions remains essential.

Accurate Remaining Useful Life (RUL) prediction without labeled target domain data is a critical challenge, and domain adaptation (DA) has been widely adopted to address it by transferring knowledge from a labeled source domain to an unlabeled target domain. Despite its success, existing DA methods struggle significantly when faced with incomplete degradation trajectories in the target domain, particularly due to the absence of late degradation stages. This missing data introduces a key extrapolation challenge. When applied to such incomplete RUL prediction tasks, current DA methods encounter two primary limitations. First, most DA approaches primarily focus on global alignment, which can misaligns late degradation stage in the source domain with early degradation stage in the target domain. Second, due to varying operating conditions in RUL prediction, degradation patterns may differ even within the same degradation stage, resulting in different learned features. As a result, even if degradation stages are partially aligned, simple feature matching cannot fully align two domains. To overcome these limitations, we propose a novel evidential adaptation approach called EviAdapt, which leverages evidential learning to enhance domain adaptation. The method first segments the source and target domain data into distinct degradation stages based on degradation rate, enabling stage-wise alignment that ensures samples from corresponding stages are accurately matched. To address the second limitation, we introduce an evidential uncertainty alignment technique that estimates uncertainty using evidential learning and aligns the uncertainty across matched stages.

Flash floods are the most destructive natural hazard in Himachal Pradesh (HP), India, causing over 400 fatalities and $1.2 billion in losses in the 2023 monsoon season alone. Existing risk maps treat every pixel independently, ignoring the basic fact that flooding upstream raises risk downstream. We address this with a Graph Neural Network (GraphSAGE) trained on a watershed connectivity graph (460 sub-watersheds, 1,700 directed edges), built from a six-year Sentinel-1 SAR flood inventory (2018-2023, 3,000 events) and 12 environmental variables at 30 m resolution. Four pixel-based ML models (RF, XGBoost, LightGBM, stacking ensemble) serve as baselines. All models are evaluated with leave-one-basin-out spatial cross-validation to avoid the 5-15% AUC inflation of random splits. Conformal prediction produces the first HP susceptibility maps with statistically guaranteed 90% coverage intervals. The GNN achieved AUC = 0.978 +/- 0.017, outperforming the best baseline (AUC = 0.881) and the published HP benchmark (AUC = 0.88). The +0.097 gain confirms that river connectivity carries predictive signal that pixel-based models miss. High-susceptibility zones overlap 1,457 km of highways (including 217 km of the Manali-Leh corridor), 2,759 bridges, and 4 major hydroelectric installations. Conformal intervals achieved 82.9% empirical coverage on the held-out 2023 test set; lower coverage in high-risk zones (45-59%) points to SAR label noise as a target for future work.

Large language models (LLMs) are increasingly central to clinician workflows, spanning clinical decision support, medical education, and patient communication. However, current evaluation methods for medical LLMs rely heavily on static, templated benchmarks that fail to capture the complexity and dynamics of real-world clinical practice, creating a dissonance between benchmark performance and clinical utility. To address these limitations, we present MedArena, an interactive evaluation platform that enables clinicians to directly test and compare leading LLMs using their own medical queries. Given a clinician-provided query, MedArena presents responses from two randomly selected models and asks the user to select the preferred response. Out of 1571 preferences collected across 12 LLMs up to November 1, 2025, Gemini 2.0 Flash Thinking, Gemini 2.5 Pro, and GPT-4o were the top three models by Bradley-Terry rating. Only one-third of clinician-submitted questions resembled factual recall tasks (e.g., MedQA), whereas the majority addressed topics such as treatment selection, clinical documentation, or patient communication, with ~20% involving multi-turn conversations. Additionally, clinicians cited depth and detail and clarity of presentation more often than raw factual accuracy when explaining their preferences, highlighting the importance of readability and clinical nuance. We also confirm that the model rankings remain stable even after controlling for style-related factors like response length and formatting. By grounding evaluation in real-world clinical questions and preferences, MedArena offers a scalable platform for measuring and improving the utility and efficacy of medical LLMs.

As agentic artificial intelligence systems scale across globally distributed and long lived infrastructures, secure and policy compliant communication becomes a fundamental systems challenge. This challenge grows more serious in the quantum era, where the cryptographic assumptions built into today's AI deployments may not remain valid over their operational lifetime. Here, we introduce quantum secure by construction, or QSC, as a design paradigm that treats quantum secure communication as a core architectural property of agentic AI systems rather than an upgrade added later. We realize QSC through a runtime adaptive security model that combines post quantum cryptography, quantum random number generation, and quantum key distribution to secure interactions among autonomous agents operating across heterogeneous cloud, edge, and inter organizational environments. The approach is cryptographically pluggable and guided by policy, allowing the system to adjust its security posture according to infrastructure availability, regulatory constraints, and performance needs. QSC contributes a governance aware orchestration layer that selects and combines link specific cryptographic protections across the full agent lifecycle, including session bootstrap, inter agent coordination, tool invocation, and memory access. Through system level analysis and empirical evaluation, we examine the trade offs between classical and quantum secure mechanisms and show that QSC can reduce the operational complexity and cost of introducing quantum security into deployed agentic AI systems. These results position QSC as a foundational paradigm for post quantum agentic intelligence and establish a principled pathway for designing globally interoperable, resilient, and future ready intelligent systems.

Real-world phenomena often exhibit vagueness, partial truth, and incomplete information. To model such uncertainty in a mathematically rigorous way, many generalized set-theoretic frameworks have been introduced, including Fuzzy Sets [1], Intuitionistic Fuzzy Sets [2], Neutrosophic Sets [3,4], Vague Sets [5], Hesitant Fuzzy Sets [6], Picture Fuzzy Sets [7], Quadripartitioned Neutrosophic Sets [8], Penta-Partitioned Neutrosophic Sets [9], Plithogenic Sets [10], HyperFuzzy Sets [11], and HyperNeutrosophic Sets [12]. Within these frameworks, a wide range of notions has been proposed and studied, particularly in the settings of fuzzy, intuitionistic fuzzy, neutrosophic, and plithogenic set theories. This extensive literature underscores both the significance of these theories and the breadth of their application areas. As a result, many ideas, constructions, and structural patterns recur across these four major families of uncertainty-oriented models. In this book, we provide a comprehensive, large-scale survey of Fuzzy, Intuitionistic Fuzzy, Neutrosophic, and Plithogenic Sets. Our goal is to give readers a systematic overview of existing developments and, through a unified exposition, to stimulate new insights, further conceptual extensions, and additional applications across a wide range of disciplines.

Existing memory systems for language agents address memory management: how to retrieve and page more information within a context budget. We address a complementary problem -- memory utility: what experience is worth keeping, and how it should change agent behavior. We present Atlas, a memory kernel that compiles accumulated task experience into an agent's instruction structure -- without fine-tuning, RAG, or human intervention. Memory is distillation, not storage; delivery is instruction rewriting, not context injection. Facts extracted from agent failures and successes are verified through a three-step promotion gate and delivered by rewriting the agent's system prompt with learned sub-bullets. On CUAD contract analysis, the evolved prompt improves GPT-4o token-level F1 by $+8.7$pp and precision by $+12.5$pp. On HotpotQA multi-hop QA, joint F1 improves $+3.16$pp. An ablation isolates the mechanism's defining property -- the training signal constraint: the evolved prompt learns exactly what it is taught, and nothing more. Applied to Claude Sonnet~4.5 using the same evolved prompt -- compiled from GPT-4o errors, unchanged -- joint F1 improves $+2.31$pp, with gains concentrating where Claude's stronger baseline leaves the most room -- confirming that the compiled knowledge is task-shaped, not model-shaped.

Starting from first principles and a linguistic perspective centered on part-of-speech (POS) and syntactic analysis, this paper explores and derives the underlying essence of the Query-Key-Value (QKV) mechanism within the Transformer architecture. Based on this theoretical foundation, we provide a unified explanatory framework for the efficacy of contemporary architectures, including MQA, GQA, and MLA, while identifying their inherent trade-offs and potential optimization trajectories. We introduce the QV paradigm and provide empirical evidence for its validity. Building upon this, we propose the QV-Ka optimization scheme, which is further substantiated through experimental validation. The interpretable theoretical analysis of the QKV mechanism presented in this work establishes a robust foundation for the future evolution of large language model architectures.

We present OrthoAI v2, the second iteration of our open-source pipeline for AI-assisted orthodontic treatment planning with clear aligners, substantially extending the single-agent framework previously introduced. The first version established a proof-of-concept based on Dynamic Graph Convolutional Neural Networks (\dgcnn{}) for tooth segmentation but was limited to per-tooth centroid extraction, lacked landmark-level precision, and produced a scalar quality score without staging simulation. \vtwo{} addresses all three limitations through three principal contributions: (i)~a second agent adopting the Conditioned Heatmap Regression Methodology (\charm{})~\cite{rodriguez2025charm} for direct, segmentation-free dental landmark detection, fused with Agent~1 via a confidence-weighted orchestrator in three modes (parallel, sequential, single-agent); (ii)~a composite six-category biomechanical scoring model (biomechanics $\times$ 0.30 + staging $\times$ 0.20 + attachments $\times$ 0.15 + IPR $\times$ 0.10 + occlusion $\times$ 0.10 + predictability $\times$ 0.15) replacing the binary pass/fail check of v1; (iii)~a multi-frame treatment simulator generating $F = A \times r$ temporally coherent 6-DoF tooth trajectories via SLERP interpolation and evidence-based staging rules, enabling ClinCheck 4D visualisation. On a synthetic benchmark of 200 crowding scenarios, the parallel ensemble of OrthoAI v2 reaches a planning quality score of $92.8 \pm 4.1$ vs.\ $76.4 \pm 8.3$ for OrthoAI v1, a $+21\%$ relative gain, while maintaining full CPU deployability ($4.2 \pm 0.8$~s).

Large Language Model-based Multi-Agent Systems (MAS) have demonstrated remarkable collaborative reasoning capabilities but introduce new attack surfaces, such as the sleeper agent, which behave benignly during routine operation and gradually accumulate trust, only revealing malicious behaviors when specific conditions or triggers are met. Existing defense works primarily focus on static graph optimization or hierarchical data management, often failing to adapt to evolving adversarial strategies or suffering from high false-positive rates (FPR) due to rigid blocking policies. To address this, we propose DynaTrust, a novel defense method against sleeper agents. DynaTrust models MAS as a dynamic trust graph~(DTG), and treats trust as a continuous, evolving process rather than a static attribute. It dynamically updates the trust of each agent based on its historical behaviors and the confidence of selected expert agents. Instead of simply blocking, DynaTrust autonomously restructures the graph to isolate compromised agents and restore task connectivity to ensure the usability of MAS. To assess the effectiveness of DynaTrust, we evaluate it on mixed benchmarks derived from AdvBench and HumanEval. The results demonstrate that DynaTrust outperforms the state-of-the-art method AgentShield by increasing the defense success rate by 41.7%, achieving rates exceeding 86% under adversarial conditions. Furthermore, it effectively balances security with utility by significantly reducing FPR, ensuring uninterrupted system operations through graph adaptation.

Memory-augmented agents maintain multiple specialized stores, yet most systems retrieve from all stores for every query, increasing cost and introducing irrelevant context. We formulate memory retrieval as a store-routing problem and evaluate it using coverage, exact match, and token efficiency metrics. On downstream question answering, an oracle router achieves higher accuracy while using substantially fewer context tokens compared to uniform retrieval, demonstrating that selective retrieval improves both efficiency and performance. Our results show that routing decisions are a first-class component of memory-augmented agent design and motivate learned routing mechanisms for scalable multi-store systems. We additionally formalize store selection as a cost-sensitive decision problem that trades answer accuracy against retrieval cost, providing a principled interpretation of routing policies.

The performance of neural network models deteriorates due to their unreliable behavior on non-robust features of corrupted samples. Owing to their opaque nature, rectifying models to address this problem often necessitates arduous data cleaning and model retraining, resulting in huge computational and manual overhead. In this work, we leverage rank-one model editing to establish an attribution-guided model rectification framework that effectively locates and corrects model unreliable behaviors. We first distinguish our rectification setting from existing model editing, yielding a formulation that corrects unreliable behavior while preserving model performance and reducing reliance on large budgets of cleansed samples. We further reveal a bottleneck of model rectifying arising from heterogeneous editability across layers. To target the primary source of misbehavior, we introduce an attribution-guided layer localization method that quantifies layer-wise editability and identifies the layer most responsible for unreliabilities. Extensive experiments demonstrate the effectiveness of our method in correcting unreliabilities observed for neural Trojans, spurious correlations and feature leakage. Our method shows remarkable performance by achieving its editing objective with as few as a single cleansed sample, which makes it appealing for practice.

In decentralized Multi-Agent Reinforcement Learning (MARL), steganographic collusion -- where agents develop private protocols to evade monitoring -- presents a critical AI safety threat. Existing defenses, limited to behavioral or reward layers, fail to detect coordination in latent communication channels. We introduce the Dynamic Representational Circuit Breaker (DRCB), an architectural defense operating at the optimization substrate. Building on the AI Mother Tongue (AIM) framework, DRCB utilizes a Vector Quantized Variational Autoencoder (VQ-VAE) bottleneck to convert unobservable messages into auditable statistical objects. DRCB monitors signals including Jensen-Shannon Divergence drift, L2-norm codebook displacement, and Randomized Observer Pool accuracy to compute an EMA-based Collusion Score. Threshold breaches trigger four escalating interventions: dynamic adaptation, gradient-space penalty injection into the Advantage function A^pi, temporal reward suppression, and full substrate circuit breaking via codebook shuffling and optimizer state reset. Experiments on a Contextual Prisoner's Dilemma with MNIST labels show that while static monitoring fails (p = 0.3517), DRCB improves observer mean accuracy from 0.858 to 0.938 (+9.3 percent) and reduces volatility by 43 percent, while preserving mean joint reward (p = 0.854). Analysis of 214,298 symbol samples confirms "Semantic Degradation," where high-frequency sequences converge to zero entropy, foreclosing complex steganographic encodings. We identify a "Transparency Paradox" where agents achieve surface-level determinism while preserving residual capacity in long-tail distributions, reflecting Goodhart's Law. This task-agnostic methodology provides a technical path toward MICA-compliant (Multi-Agent Internal Coupling Audit) pre-deployment auditing for autonomous systems.

In classification tasks, the long-tailed minority classes usually offer the predictions that are most important. Yet these classes consistently exhibit low accuracies, whereas a few high-performing classes dominate the game. We pursue a foundational understanding of the hidden role of Gini Index as a tool for detecting and optimizing (debiasing) disparities in class accuracy, focusing on the case of prompt-based classification. We introduce the intuitions, benchmark Gini scores in real-world LLMs and vision models, and thoroughly discuss the insights of Gini not only as a measure of relative accuracy dominance but also as a direct optimization metric. Through rigorous case analyses, we first show that weak to strong relative accuracy imbalance exists in both prompt-based, text and image classification results and regardless of whether the classification is high-dimensional or low-dimensional. Then, we harness the Gini metric to propose a post-hoc model-agnostic bias mitigation method. Experimental results across few-shot news, biomedical, and zero-shot image classification show that our method significantly reduces both relative and absolute accuracy imbalances, minimizing top class relative dominance while elevating weakest classes.

Long-context handling remains a core challenge for language models: even with extended context windows, models often fail to reliably extract, reason over, and use the information across long contexts. Recent works like Recursive Language Models (RLM) have approached this challenge by agentic way of decomposing long contexts into recursive sub-calls through programmatic interaction at inference. While promising, the success of RLM critically depends on how these context-interaction programs are selected, which has remained largely unexplored. In this paper, we study this problem and introduce SRLM, a framework that augments programmatic context interaction with uncertainty-aware Self-Reflection. SRLM leverages three intrinsic signals: self consistency, reasoning length, and verbalized confidence. These serve as complementary indicators of a model's internal uncertainty, and the model uses them to evaluate and compare candidate context-interaction programs. Extensive experiments across diverse benchmark datasets, context lengths, and backbone models, show that SRLM consistently outperforms state-of-the-art baselines, yielding up to 22% improvement over RLM under the same time budget. Our findings show that recursion itself is not the primary driver of performance in RLM, and a simple self-reflective program search can match or surpass RLM without requiring self-query or explicit recursion mechanisms. We find that for context lengths within the model's window, RLMs with recursion often degrade performance relative to the base model, whereas SRLM yields consistent gains across both short and long contexts. We also find that RLM is less effective in tasks with semantically intensive nature, where heuristic program search is insufficient and broader contextual understanding is required, while self-reflection in SRLM provides a semantic signal that better steers reasoning in these scenarios.

The early prediction of sepsis in intensive care unit (ICU) patients is crucial for improving survival rates. However, the development of accurate predictive models is hampered by data fragmentation across healthcare institutions and the complex, temporal nature of medical data, all under stringent privacy constraints. To address these challenges, we propose a novel framework that uniquely integrates federated learning (FL) with a medical knowledge graph and a temporal transformer model, enhanced by meta-learning capabilities. Our approach enables collaborative model training across multiple hospitals without sharing raw patient data, thereby preserving privacy. The model leverages a knowledge graph to incorporate structured medical relationships and employs a temporal transformer to capture long-range dependencies in clinical time-series data. A model-agnostic meta-learning (MAML) strategy is further incorporated to facilitate rapid adaptation of the global model to local data distributions. Evaluated on the MIMIC-IV and eICU datasets, our method achieves an area under the curve (AUC) of 0.956, which represents a 22.4% improvement over conventional centralized models and a 12.7% improvement over standard federated learning, demonstrating strong predictive capability for sepsis. This work presents a reliable and privacy-preserving solution for multi-center collaborative early warning of sepsis.

Out-of-Distribution (OOD) detection is crucial for the secure deployment of machine learning models, and prototype-based learning methods are among the mainstream strategies for achieving OOD detection. Existing prototype-based learning methods generally rely on a fixed number of prototypes. This static assumption fails to adapt to the inherent complexity differences across various categories. Currently, there is still a lack of a mechanism that can adaptively adjust the number of prototypes based on data complexity. Inspired by the processes of cell birth and death in biology, we propose a novel method named PID (Prototype bIrth and Death) to adaptively adjust the prototype count based on data complexity. This method relies on two dynamic mechanisms during the training process: prototype birth and prototype death. The birth mechanism instantiates new prototypes in data regions with insufficient representation by identifying the overload level of existing prototypes, thereby meticulously capturing intra-class substructures. Conversely, the death mechanism reinforces the decision boundary by pruning prototypes with ambiguous class boundaries through evaluating their discriminability. Through birth and death, the number of prototypes can be dynamically adjusted according to the data complexity, leading to the learning of more compact and better-separated In-Distribution (ID) embeddings, which significantly enhances the capability to detect OOD samples. Experiments demonstrate that our dynamic method, PID, significantly outperforms existing methods on benchmarks such as CIFAR-100, achieving State-of-the-Art (SOTA) performance, especially on the FPR95 metric.

Facial expression synthesis aims to generate realistic facial expressions while preserving identity. Existing conditional generative adversarial networks (GANs) achieve excellent image-to-image translation results, but their performance often degrades when test images differ from the training dataset. We present Regression GAN (RegGAN), a model that learns an intermediate representation to improve generalization beyond the training distribution. RegGAN consists of two components: a regression layer with local receptive fields that learns expression details by minimizing the reconstruction error through a ridge regression loss, and a refinement network trained adversarially to enhance the realism of generated images. We train RegGAN on the CFEE dataset and evaluate its generalization performance both on CFEE and challenging out-of-distribution images, including celebrity photos, portraits, statues, and avatar renderings. For evaluation, we employ four widely used metrics: Expression Classification Score (ECS) for expression quality, Face Similarity Score (FSS) for identity preservation, QualiCLIP for perceptual realism, and Fréchet Inception Distance (FID) for assessing both expression quality and realism. RegGAN outperforms six state-of-the-art models in ECS, FID, and QualiCLIP, while ranking second in FSS. Human evaluations indicate that RegGAN surpasses the best competing model by 25% in expression quality, 26% in identity preservation, and 30% in realism.

Large language models (LLMs) are typically governed by post-training alignment (e.g., RLHF or DPO), which yields a largely static policy during deployment and inference. However, real-world safety is a full-lifecycle problem: static defenses degrade against evolving jailbreak behaviors, and fixed weights cannot adapt to pluralistic, time-varying safety norms. This motivates inference-time governance that steers behavior without costly retraining. To address this, we introduce the Consensus Clustering LinUCB Bandit (CCLUB), a unified framework for adaptive social alignment via system-prompt routing. CCLUB employs a conservative consensus clustering mechanism: it pools data only within the intersection of utility and safety similarity graphs, effectively preventing unsafe generalization across semantically proximal but risk-divergent contexts. Our theoretical analysis yields a sublinear regret guarantee, demonstrating near-optimal performance of CCLUB. Extensive experiments validate that CCLUB outperforms strong baselines, achieving a 10.98% improvement in cumulative reward and a 14.42% reduction in the average suboptimality gap.

Time series forecasters are widely used across various domains. Among them, MLP (multi-layer perceptron)-based forecasters have been proven to be more robust to noise compared to Transformer-based forecasters. However, MLP struggles to capture complex features, resulting in limitations on capturing long-range dependencies. To address this challenge, we propose XLinear, an MLP-based forecaster for long-range forecasting. Firstly, we decompose the time series into trend and seasonal components. For the trend component which contains long-range characteristics, we design Enhanced Frequency Attention (EFA) to capture long-term dependencies by leveraging frequency-domain operations. Additionally, a CrossFilter Block is proposed for the seasonal component to maintain the model's robustness to noise, avoiding the problems of low robustness often caused by attention mechanisms. Experimental results demonstrate that XLinear achieves state-of-the-art performance on test datasets. While keeping the lightweight architecture and high robustness of MLP-based models, our forecaster outperforms other MLP-based forecasters in capturing long-range dependencies.

Foundation models for structured electronic health records (EHRs) are pretrained on longitudinal sequences of timestamped clinical events to learn adaptable patient representations. Tokenization -- how these timelines are converted into discrete model inputs -- determines what information is preserved, how efficiently it is encoded, and which relationships must be learned versus precomputed. Yet the impact of tokenization design choices on downstream performance and computational efficiency remains largely unexplored. Here, we pretrained a transformer on pediatric EHR data under a factorial design, varying tokenization along event encoding, time encoding, and workflow annotation. We evaluated area-under-the-receiver-operating-characteristic curve across 74 clinical prediction tasks. Joint event encoding and positional time encoding outperformed their alternatives (73/74 and 71/74 tasks) while requiring 39.5% and 9.6% fewer pretraining floating-point operations, respectively. Targeted ablations traced the joint encoding advantage to local binding efficiency, that is, code-attribute pairs are combined into single tokens, rather than split across tokens that the model must learn to associate during pretraining. External evaluation on an adult intensive care unit cohort demonstrated that this advantage generalizes despite substantial vocabulary mismatch, while temporal and workflow effects remain institution-specific. These results establish tokenization as a tractable lever for improving both the performance and efficiency of EHR foundation models.

Large language model (LLM) agents are increasingly deployed in long running workflows, where they must preserve user and task state across many turns. Many existing agent memory systems behave like external databases with ad hoc read/write rules, which can yield unstable retention, limited consolidation, and vulnerability to distractor content. We present CraniMem, a neurocognitively motivated, gated and bounded multi-stage memory design for agentic systems. CraniMem couples goal conditioned gating and utility tagging with a bounded episodic buffer for near term continuity and a structured long-term knowledge graph for durable semantic recall. A scheduled consolidation loop replays high utility traces into the graph while pruning low utility items, keeping memory growth in check and reducing interference. On long horizon benchmarks evaluated under both clean inputs and injected noise, CraniMem is more robust than a Vanilla RAG and Mem0 baseline and exhibits smaller performance drops under distraction. Our code is available at https://github.com/PearlMody05/Cranimem and the accompanying PyPI package at https://pypi.org/project/cranimem.

Recursive reasoning models such as Hierarchical Reasoning Model (HRM) and Tiny Recursive Model (TRM) show that small, weight-shared networks can solve compute-heavy and NP puzzles by iteratively refining latent states, but their training typically relies on deep supervision and/or long unrolls that increase wall-clock cost and can bias the model toward greedy intermediate behavior. We introduce Recursive Stem Model (RSM), a recursive reasoning approach that keeps the TRM-style backbone while changing the training contract so the network learns a stable, depth-agnostic transition operator. RSM fully detaches the hidden-state history during training, treats early iterations as detached "warm-up" steps, and applies loss only at the final step. We further grow the outer recursion depth $H$ and inner compute depth $L$ independently and use a stochastic outer-transition scheme (stochastic depth over $H$) to mitigate instability when increasing depth. This yields two key capabilities: (i) $>20\times$ faster training than TRM while improving accuracy ($\approx 5\times$ reduction in error rate), and (ii) test-time scaling where inference can run for arbitrarily many refinement steps ($\sim 20,000 H_{\text{test}} \gg 20 H_{\text{train}}$), enabling additional "thinking" without retraining. On Sudoku-Extreme, RSM reaches 97.5% exact accuracy with test-time compute (within ~1 hour of training on a single A100), and on Maze-Hard ($30 \times 30$) it reaches ~80% exact accuracy in ~40 minutes using attention-based instantiation. Finally, because RSM implements an iterative settling process, convergence behavior provides a simple, architecture-native reliability signal: non-settling trajectories warn that the model has not reached a viable solution and can be a guard against hallucination, while stable fixed points can be paired with domain verifiers for practical correctness checks.

Memory is critical for LLM-based agents to preserve past observations for future decision-making, where factual memory serves as its foundational part. However, existing approaches to constructing factual memory face several limitations. Textual methods impose heavy context and indexing burdens, while parametric methods suffer from catastrophic forgetting and high costs. To address these challenges, we introduce NextMem, a latent factual memory framework that utilizes an autoregressive autoencoder to efficiently construct latent memory while ensuring accurate reconstruction. For better optimization, we propose a two-stage training process, including autoregressive reconstruction alignment and progressive latent substitution. We also incorporate quantization to reduce storage overhead. Extensive experiments demonstrate that NextMem achieves superior performance, and excels in retrieval, robustness, and extensibility properties. We release our code and model checkpoints at https://github.com/nuster1128/NextMem.