We present CRC-SAM, a unified framework for colorectal cancer segmentation across colonoscopy, CT, and histopathology images. Unlike prior single-modality methods, CRC-SAM provides consistent, modality-agnostic segmentation throughout the clinical workflow. Built on MedSAM, it incorporates low-rank adaptation (LoRA) layers into a frozen encoder, enabling efficient domain transfer to underrepresented modalities with minimal trainable parameters. Experiments on MSD-Colon, CVC-ClinicDB, and EBHI-Seg demonstrate superior performance across modalities, outperforming state-of-the-art baselines and highlighting the effectiveness of lightweight LoRA adaptation for foundation-model-based colorectal cancer analysis.

Safety-oriented instruction-following is supposed to keep LLM-controlled robots safe. We show it also creates an availability attack surface. By injecting short safety-plausible phrases (1-5 tokens) into a robots audio channel, an adversary can trigger the models safety reasoning to halt or disrupt execution without jailbreaking the model or overriding its policy. In the embodied setting, this is a semantic denial-of-service attack: the agent stops because the injected signal looks like a legitimate alert. Across four vision-language models, seven prompt-level defenses, three deployment modes, and single- and multi-injection settings, we find that prompt-only defenses trade off attack suppression against genuine hazard response. The strongest defenses reduce hard-stop attack success on some models, but defenses change the form of disruption, not its fact: suppressed hard stops re-emerge as acknowledge loops and false alerts, which we measure with Disruption Success Rate (DSR). We further find that injection variety is consistently more effective than repeating the same phrase, suggesting that models treat diverse safety cues as corroborating evidence. The practical implication is architectural rather than prompt-level: systems that route unauthenticated audio text directly into the LLM create an avoidable security dependency between safety monitoring and action selection.

Large language models (LLMs) are becoming increasingly capable at small parameter scales. At the same time, conventional cloud-centric deployment introduces challenges around data privacy, latency, and cost that are acute in operational technology and defence environments. Advances in model distillation, quantisation, and affordable edge accelerators now make local LLM inference on single-board computers feasible, but the high dimensionality of the configuration space makes identifying optimal deployments difficult without structured evaluation. Existing LLM-specific edge benchmarking efforts rely on CPU-only inference, poor coverage of genuine single-board computers, and generic evaluation tasks that lack multi-dimensional assessment of hardware effectiveness. This paper proposes a multi-dimensional benchmarking methodology that jointly evaluates inference performance and hardware efficiency across four IoT-suitable edge platform configurations testing single-board computers with the latest available hardware accelerators. Our results reveal the benefits of using hardware accelerators such as NPUs and GPUs, along with multi-dimensional evaluations quantifying the trade-offs between power efficiency, physical device size and token throughput; offering practical guidance for deploying generative AI in privacy-sensitive and connectivity-limited environments such as unmanned vehicles and portable, ruggedised operations.

We present a Mixture-of-Experts-based foundation model applied to the GlueX DIRC detector at Jefferson Lab, demonstrating its utility as a unified framework for fast simulation, particle identification, and hit-level noise filtering of Cherenkov photons. By leveraging a single shared transformer backbone across all tasks, the approach eliminates the fragmentation of task-specific pipelines while maintaining competitive-and in several cases superior-performance relative to established methods. The model operates directly on low-level detector inputs, performing hit-by-hit autoregressive generation over split spatial and temporal vocabularies with continuous kinematic conditioning, and supports class-conditional generation of pions and kaons through its Mixture-of-Experts architecture. We benchmark against the standard geometrical reconstruction and prior deep learning methods across the full kinematic phase space of the GlueX DIRC, demonstrating that the foundation model framework transfers effectively to this detector without architectural modification. This work positions the foundation model as a practical and scalable alternative to the suite of task-specific models currently proposed for GlueX DIRC analysis.

P300-based brain-computer interfaces (BCIs) are widely used for communication, but population heterogeneity may alter the neural patterns available for decoding. Prior work has mainly examined such differences at the signal or performance level, while the representation structure learned by the decoder remains underexplored. In this study, we propose an interpretable fuzzy spatiotemporal framework for P300 classification and use it to analyze population-level differences across amyotrophic lateral sclerosis (ALS), autism (AUT), and neurotypical (NT) cohorts. The model employs spatial and temporal fuzzy filters with learnable prototypes, enabling both classification and reconstruction of cohort-specific fuzzy centers. Experiments were conducted on ALS and NT subsets from bigP3BCI and on the BCIAUT-P300 benchmark in a within-subject setting. The proposed model achieved competitive performance against multiple deep learning baselines. More importantly, the reconstructed fuzzy centers revealed systematic cohort-dependent differences in waveform morphology and representation geometry. Point-wise statistical analysis identified significant temporal differences between cohorts, including intervals overlapping with the canonical P300 window, and low-dimensional embeddings showed partially separated cohort-specific prototype organizations. These results suggest that population heterogeneity in P300-BCI is reflected not only in decoding performance but also in the discriminative structure learned by the model. The proposed framework provides an interpretable route toward population-aware P300-BCI analysis and design.

The rapid integration of Large Language Models (LLMs) into Multi-Agent Systems (MAS) has significantly enhanced their collaborative problem-solving capabilities, but it has also expanded their attack surfaces, exposing them to vulnerabilities such as prompt infection and compromised inter-agent communication. While emerging graph-based anomaly detection methods show promise in protecting these networks, the field currently lacks a standardized, reproducible environment to train these models and evaluate their efficacy. To address this gap, we introduce Gammaf (Graph-based Anomaly Monitoring for LLM Multi-Agent systems Framework), an open-source benchmarking platform. Gammaf is not a novel defense mechanism itself, but rather a comprehensive evaluation architecture designed to generate synthetic multi-agent interaction datasets and benchmark the performance of existing and future defense models. The proposed framework operates through two interdependent pipelines: a Training Data Generation stage, which simulates debates across varied network topologies to capture interactions as robust attributed graphs, and a Defense System Benchmarking stage, which actively evaluates defense models by dynamically isolating flagged adversarial nodes during live inference rounds. Through rigorous evaluation using established defense baselines (XG-Guard and BlindGuard) across multiple knowledge tasks (such as MMLU-Pro and GSM8K), we demonstrate Gammaf's high utility, topological scalability, and execution efficiency. Furthermore, our experimental results reveal that equipping an LLM-MAS with effective attack remediation not only recovers system integrity but also substantially reduces overall operational costs by facilitating early consensus and cutting off the extensive token generation typical of adversarial agents.

Contemporary product analytics systems require users to pose explicit queries, such as writing SQL, configuring dashboards, or constructing funnels, before insights can surface. This pull-based paradigm creates a bottleneck: it requires both domain knowledge and technical fluency, and assumes practitioners know in advance which questions to ask. We argue that behavioral analytics should move from passive systems that answer queries to active systems that continuously detect and explain behavioral phenomena. We present the Behavioral Intelligence Platform (BIP), a system architecture that transforms raw event streams into automatically generated insights. BIP consists of four layers. First, Normalization and State Derivation (NSD) standardizes events and maps them to a semantic state hierarchy. Second, a Behavioral Graph Engine (BGE) models user journeys as absorbing Markov chains and computes transition probabilities, removal effects, and path quality metrics. Third, a Behavioral Knowledge Graph (BKG) and Detector System convert graph outputs into grounded behavioral facts and identify behavioral phenomena. Finally, a Grounded Language Layer constrains large language model outputs to verified facts, producing reliable narrative insights. We formalize the Behavioral Intelligence Problem, introduce a taxonomy of detectors for autonomous insight generation, and propose an interestingness score to prioritize insights under limited attention.

Multi-agent systems are frequently employed for autonomous code generation, demonstrating strong utility in complex algorithmic problem-solving. Recent studies tackle the difficulty of producing functionally correct programs by leveraging simulation-guided planning and debugging, wherein language models step through execution traces to validate logic. Nevertheless, these methods rely heavily on human-authored public test cases to anchor the simulation and debugging cycles. Hand-crafting exhaustive input-output pairs creates a significant, labor-intensive bottleneck within the software development lifecycle. Since ground-truth examples are seldom accessible before actual implementation in real-world scenarios, this reliance limits existing approaches primarily to curated competitive programming datasets. Additionally, we demonstrate that depending on these public tests creates an "overconfidence gap," leading frameworks to overfit to basic examples and underperform on hidden test suites. Conversely, we note that external input samples are not an absolute requirement for successful code generation. We show that large language models possess the capability to autonomously construct valid inputs and simulate execution flows for self-correction. Building on this, we introduce DryRUN, a framework that removes the necessity for ground-truth data by enabling the LLM to iteratively plan, synthesize its own test inputs, and run simulated executions, thereby mitigating algorithmic overconfidence. Assessments using the LiveCodeBench v6 dataset (post-March 2025) reveal that DryRUN achieves comparable performance to CodeSIM, a state-of-the-art, test-dependent baseline. Notably, it does so entirely without public tests or external execution signals, all while decreasing overall output token usage.

Memristive crossbars store numerical weights needing aggregation and decoding; a single junction means nothing alone. This paper presents a fundamentally different use: each junction stores a complete, domain-scoped logical assertion (holds/negated/undefined). Ternary resistance states encode these values directly. We establish a structure-preserving mapping from a domain algebra to crossbar topology: domains become isolated arrays, specialization becomes directed wiring, relation typing controls inheritance gates, and cross-domain links become explicit registers. The physical layout thus embodies the algebra; changing wiring changes reasoning semantics. We detail an ICD-11 respiratory disease classification chip (1,247 entities, ~136k 1T1R junctions) enabling domain scoping, three-valued logic, transitive cascade, typed inheritance, and cross-axis queries. Behavioral simulation (sigma_log=0.15, SNR=20dB) shows error-free operation across 100,000 trials per task with wide tolerance margins. Where prior work unified representation and computation in software, this work unifies them in hardware: reading one junction answers one question, without symbolic interpretation.

We introduce LinuxArena, a control setting in which agents operate directly on live, multi-service production environments. LinuxArena contains 20 environments, 1,671 main tasks representing legitimate software engineering work, and 184 side tasks representing safety failures such as data exfiltration and backdooring, making it the largest and most diverse control setting for software engineering to date. We validate LinuxArena is useful for control research by running sabotage evaluations, which measure whether attackers can complete side tasks while working on main tasks, and monitor evaluations, which measure a monitor model's ability to detect sabotage attempts. Against a GPT-5-nano trusted monitor at a 1\% step-wise false positive rate, Claude Opus 4.6 achieves roughly a 23% undetected sabotage success rate. We additionally release LaStraj, a dataset of human-crafted attack trajectories that evade monitors at substantially higher rates than any model-generated attacks we elicited, showing that current attack policies do not saturate LinuxArena. These results suggest that LinuxArena has meaningful headroom for both attackers and defenders, making it a strong testbed for developing and evaluating future control protocols.

Smart-home users increasingly want to control their homes in natural language rather than assemble rules, dashboards, and API integrations by hand. At the same time, real deployments are brittle: devices fail, integrations break, and recoveries often require manual intervention. Existing agent toolkits are effective for session-scoped delegation, but smart-home control operates under a different scenario: it is persistent, event-driven, failure-prone, and tied to physical devices with no shared context window. We present HearthNet, an edge multi-agent orchestration system for smart homes. HearthNet deploys a small set of persistent, role-specialized LLM agents at the home hub, where they coordinate through MQTT, Git-backed shared state, and root-issued actuation leases to govern heterogeneous devices through thin adapters. This design externalizes context, preserves execution history, and separates planning, verification, authorization, and actuation across explicit boundaries. Our current prototype runs on commodity edge hardware and Android devices; it keeps orchestration, state management, and device control on-premise while using hosted LLM APIs for inference. We demonstrate the system through three live scenarios: intent-driven multi-agent coordination from ambiguous natural language, conflict resolution with timeline-based tracing, and rejection of stale or unauthorized commands before device actuation.

Claude Code's auto mode is the first deployed permission system for AI coding agents, using a two-stage transcript classifier to gate dangerous tool calls. Anthropic reports a 0.4% false positive rate and 17% false negative rate on production traffic. We present the first independent evaluation of this system on deliberately ambiguous authorization scenarios, i.e., tasks where the user's intent is clear but the target scope, blast radius, or risk level is underspecified. Using AmPermBench, a 128-prompt benchmark spanning four DevOps task families and three controlled ambiguity axes, we evaluate 253 state-changing actions at the individual action level against oracle ground truth. Our findings characterize auto mode's scope-escalation coverage under this stress-test workload. The end-to-end false negative rate is 81.0% (95% CI: 73.8%-87.4%), substantially higher than the 17% reported on production traffic, reflecting a fundamentally different workload rather than a contradiction. Notably, 36.8% of all state-changing actions fall outside the classifier's scope via Tier 2 (in-project file edits), contributing to the elevated end-to-end FNR. Even restricting to the 160 actions the classifier actually evaluates (Tier 3), the FNR remains 70.3%, while the FPR rises to 31.9%. The Tier 2 coverage gap is most pronounced on artifact cleanup (92.9% FNR), where agents naturally fall back to editing state files when the expected CLI is unavailable. These results highlight a coverage boundary worth examining: auto mode assumes dangerous actions transit the shell, but agents routinely achieve equivalent effects through file edits that the classifier does not evaluate.

This paper presents StrADiff, a Structured Source-Wise Adaptive Diffusion Framework for unsupervised blind source separation under linear and nonlinear mixing. The framework treats each latent dimension as a source branch and assigns to it an individual adaptive reverse diffusion mechanism, so that latent sources are recovered directly from observed mixtures through a single end-to-end objective, without supervised source labels or separate post-processing. Source-wise generation, structural regularization, and observation-space reconstruction are optimized jointly during training. In this instantiation, a Gaussian process (GP) prior is used as one example of a source-wise structured prior to impose temporal organization on each recovered trajectory; the framework itself is not restricted to GP priors and can in principle incorporate other structured priors. Theoretical components clarify the induced pushforward source law, the sample-level role of the structured prior, the coupling between source recovery and prior adaptation, and a conditional weak recovery statement in an idealized linear low-noise regime. Experiments on linear and nonlinear mixtures show that StrADiff can recover meaningful latent source trajectories in an unsupervised manner, with particularly stable performance in the linear case and moderate degradation under nonlinear mixing. Beyond classical signal separation, a source branch may also be interpreted as an independent, disentangled, or otherwise interpretable explanatory factor under suitable structural assumptions, suggesting a broader route toward structured latent modeling and future identifiable nonlinear representation learning.

Graph-augmented retrieval combines dense similarity with graph-based relevance signals such as Personalized PageRank (PPR), but these scores have different distributions and are not directly comparable. We study this as a score calibration problem for heterogeneous retrieval fusion in multi-hop question answering. Our method, PhaseGraph, maps vector and graph scores to a common unit-free scale using percentile-rank normalization (PIT) before fusion, enabling stable combination without discarding magnitude information. Across MuSiQue and 2WikiMultiHopQA, calibrated fusion improves held-out last-hop retrieval on HippoRAG2-style benchmarks: LastHop@5 increases from 75.1% to 76.5% on MuSiQue (8W/1L, p=0.039) and from 51.7% to 53.6% on 2WikiMultiHopQA (11W/2L, p=0.023), both on independent held-out test splits. A theory-driven ablation shows that percentile-based calibration is directionally more robust than min-max normalization on both tune and test splits (1W/6L, p=0.125), while Boltzmann weighting performs comparably to linear fusion after calibration (0W/3L, p=0.25). These results suggest that score commensuration is a robust design choice, and the exact post-calibration operator appears to matter less on these benchmarks.

We introduce Suiren-1.0, a family of molecular foundation models for the accurate modeling of diverse organic systems. Suiren-1.0 comprising three specialized variants (Suiren-Base, Suiren-Dimer, and Suiren-ConfAvg) is integrated within an algorithmic framework that bridges the gap between 3D conformational geometry and 2D statistical ensemble spaces. We first pre-train Suiren-Base (1.8B parameters) on a 70M-sample Density Functional Theory dataset using spatial self-supervision and SE(3)-equivariant architectures, achieving robust performance in quantum property prediction. Suiren-Dimer extends this capability through continued pre-training on 13.5M intermolecular interaction samples. To enable efficient downstream application, we propose Conformation Compression Distillation (CCD), a diffusion-based framework that distills complex 3D structural representations into 2D conformation-averaged representations. This yields the lightweight Suiren-ConfAvg, which generates high-fidelity representations from SMILES or molecular graphs. Our extensive evaluations demonstrate that Suiren-1.0 establishes state-of-the-art results across a range of tasks. All models and benchmarks are open-sourced.

Loss functions play a central role in supervised classification. Cross-entropy (CE) is widely used, whereas the mean absolute error (MAE) loss can offer robustness but is difficult to optimize. Interpolating between the CE and MAE losses, generalized cross-entropy (GCE) has recently been introduced to provide a trade-off between optimization difficulty and robustness. Existing formulations of GCE result in a non-convex optimization over classification margins that is prone to underfitting, leading to poor performances with complex datasets. In this paper, we propose a minimax formulation of generalized cross-entropy (MGCE) that results in a convex optimization over classification margins. Moreover, we show that MGCEs can provide an upper bound on the classification error. The proposed bilevel convex optimization can be efficiently implemented using stochastic gradient computed via implicit differentiation. Using benchmark datasets, we show that MGCE achieves strong accuracy, faster convergence, and better calibration, especially in the presence of label noise.

This paper addresses two persistent challenges in sequential recommendation: (i) evidence insufficiency-cold-start sparsity together with noisy, length-varying item texts; and (ii) opaque modeling of dynamic, multi-faceted intents across long/short horizons. We propose R3-REC (Reasoning-Retrieval-Recommendation), a prompt-centric, retrieval-augmented framework that unifies Multi-level User Intent Reasoning, Item Semantic Extraction, Long-Short Interest Polarity Mining, Similar User Collaborative Enhancement, and Reasoning-based Interest Matching and Scoring. Across ML-1M, Games, and Bundle, R3-REC consistently surpasses strong neural and LLM baselines, yielding improvements up to +10.2% (HR@1) and +6.4% (HR@5) with manageable end-to-end latency. Ablations corroborate complementary gains of all modules.

Learning in the presence of missing data can result in biased predictions and poor generalizability, among other difficulties, which data imputation methods only partially address. In neural networks, activation functions significantly affect performance yet typical options (e.g., ReLU, Swish) operate only on feature values and do not account for missingness indicators or confidence scores. We propose Three-Channel Evolved Activations (3C-EA), which we evolve using Genetic Programming to produce multivariate activation functions f(x, m, c) in the form of trees that take (i) the feature value x, (ii) a missingness indicator m, and (iii) an imputation confidence score c. To make these activations useful beyond the input layer, we introduce ChannelProp, an algorithm that deterministically propagates missingness and confidence values via linear layers based on weight magnitudes, retaining reliability signals throughout the network. We evaluate 3C-EA and ChannelProp on datasets with natural and injected (MCAR/MAR/MNAR) missingness at multiple rates under identical preprocessing and splits. Results indicate that integrating missingness and confidence inputs into the activation search improves classification performance under missingness.

The growing sophistication of modern malware and phishing campaigns has diminished the effectiveness of traditional signature-based intrusion detection systems. This work presents SecureScan, an AI-driven, triple-layer detection framework that integrates logistic regression-based classification, heuristic analysis, and external threat intelligence via the VirusTotal API for comprehensive triage of URLs, file hashes, and binaries. The proposed architecture prioritizes efficiency by filtering known threats through heuristics, classifying uncertain samples using machine learning, and validating borderline cases with third-party intelligence. On benchmark datasets, SecureScan achieves 93.1 percent accuracy with balanced precision (0.87) and recall (0.92), demonstrating strong generalization and reduced overfitting through threshold-based decision calibration. A calibrated threshold and gray-zone logic (0.45-0.55) were introduced to minimize false positives and enhance real-world stability. Experimental results indicate that a lightweight statistical model, when augmented with calibrated verification and external intelligence, can achieve reliability and performance comparable to more complex deep learning systems.

Although artificial intelligence (AI) shows growing promise for mental health care, current approaches to evaluating AI tools in this domain remain fragmented and poorly aligned with clinical practice, social context, and first-hand user experience. This paper argues for a rethinking of responsible evaluation -- what is measured, by whom, and for what purpose -- by introducing an interdisciplinary framework that integrates clinical soundness, social context, and equity, providing a structured basis for evaluation. Through an analysis of 135 recent *CL publications, we identify recurring limitations, including over-reliance on generic metrics that do not capture clinical validity, therapeutic appropriateness, or user experience, limited participation from mental health professionals, and insufficient attention to safety and equity. To address these gaps, we propose a taxonomy of AI mental health support types -- assessment-, intervention-, and information synthesis-oriented -- each with distinct risks and evaluative requirements, and illustrate its use through case studies.

With the advancement of automated software engineering, research focus is increasingly shifting toward practical tasks reflecting the day-to-day work of software engineers. Among these tasks, software migration, a critical process of adapting code to evolving environments, has been largely overlooked. In this study, we introduce TimeMachine-bench, a benchmark designed to evaluate software migration in real-world Python projects. Our benchmark consists of GitHub repositories whose tests begin to fail in response to dependency updates. The construction process is fully automated, enabling live updates of the benchmark. Furthermore, we curated a human-verified subset to ensure problem solvability. We evaluated agent-based baselines built on top of 11 models, including both strong open-weight and state-of-the-art LLMs on this verified subset. Our results indicated that, while LLMs show some promise for migration tasks, they continue to face substantial reliability challenges, including spurious solutions that exploit low test coverage and unnecessary edits stemming from suboptimal tool-use strategies. Our dataset and implementation are available at https://github.com/tohoku-nlp/timemachine-bench.

The canonical challenge of entity resolution within high-compliance sectors, where secure identity reconciliation is frequently confounded by significant data heterogeneity, including syntactic variations in personal identifiers, is a longstanding and complex problem. To this end, we introduce a novel multimodal framework operating with the voluminous data sets typical of government and financial institutions. Specifically, our methodology is designed to address the tripartite challenge of data volume, matching fidelity, and privacy. Consequently, the underlying plaintext of personally identifiable information remains computationally inaccessible throughout the matching lifecycle, empowering institutions to rigorously satisfy stringent regulatory mandates with cryptographic assurances of client confidentiality while achieving a demonstrably low equal error rate and maintaining computational tractability at scale.

Single-channel speech enhancement algorithms are often used in resource-constrained embedded devices, where low latency and low complexity designs gain more importance. In recent years, researchers have proposed a wide variety of novel solutions to this problem. In particular, a recent deep learning model named ULCNet is among the state-of-the-art approaches in this domain. This paper proposes an adaptation of ULCNet, by replacing its GRU layers with FastGRNNs, to reduce both computational latency and complexity. Furthermore, this paper shows empirical evidence on the performance decay of FastGRNNs in long audio signals during inference due to internal state drifting, and proposes a novel approach based on a trainable complementary filter to mitigate it. The resulting model, Fast-ULCNet, performs on par with the state-of-the-art original ULCNet architecture on a speech enhancement task, while reducing its model size by more than half and decreasing its latency by 34% on average.

The evolution of recommender systems has shifted from traditional collaborative filtering to LLM-based agentic systems, which rely on semantic user and item memories to make predictions. However, existing agents maintain these memories in isolation. This overlooks crucial collaborative signals, such as user-item co-engagements and peer relationships across the community, which significantly limits their ability to uncover hidden preferences and accurately infer user needs, particularly for data-sparse users. To bridge this gap, we introduce collaborative memory, a paradigm that connects isolated semantics to enable the sharing of relational insights. Yet, naively utilizing collaborative memory causes severe context overload and introduces noise to downstream LLMs, alongside prohibitive computational costs. To resolve this, we propose MemRec, a framework that architecturally decouples memory management from reasoning. MemRec introduces a dedicated, lightweight language model (LM_Mem) to efficiently manage and synthesize a dynamic collaborative memory graph in the background. It provides only distilled, high-signal contexts to a downstream, heavyweight large language model (LLM_Rec) for the final recommendation. Extensive experiments on four benchmarks demonstrate that MemRec achieves state-of-the-art performance. Code: https://github.com/rutgerswiselab/memrec and Homepage: https://memrec.weixinchen.com/

Graph-based Approximate Nearest Neighbor (ANN) search often suffers from performance degradation in high-dimensional spaces due to the Euclidean-Geodesic mismatch, where greedy routing diverges from the underlying data manifold. To address this challenge, this paper presents Manifold-Consistent Graph Indexing (MCGI), a geometry-aware and disk-resident indexing method that leverages Local Intrinsic Dimensionality (LID) to dynamically adapt search strategies to the intrinsic geometry of data. Unlike conventional algorithms that treat dimensions uniformly, MCGI modulates its beam search budget based on in-situ geometric analysis, which reduces sensitivity to data-specific hyperparameters by replacing a single scalar with a geometry-informed range that remains stable across datasets of varying dimensionality. Theoretical analysis demonstrates that MCGI provides robust approximation by preserving manifold-consistent topological connectivity. Extensive evaluations against five industry-standard baselines across five datasets up to billion scales confirm the advantages of the proposed approach.

The increasing deployment of large language models (LLMs) in safety-critical applications raises fundamental challenges in systematically evaluating robustness against adversarial behaviors. Existing red-teaming practices are largely manual and expert-driven, which limits scalability, reproducibility, and coverage in high-dimensional prompt spaces. We formulate automated LLM red-teaming as a structured adversarial search problem and propose a learning-driven framework for scalable vulnerability discovery. The approach combines meta-prompt-guided adversarial prompt generation with a hierarchical execution and detection pipeline, enabling standardized evaluation across six representative threat categories, including reward hacking, deceptive alignment, data exfiltration, sandbagging, inappropriate tool use, and chain-of-thought manipulation. Extensive experiments on GPT-OSS-20B identify 47 vulnerabilities, including 21 high-severity failures and 12 previously undocumented attack patterns. Compared with manual red-teaming under matched query budgets, our method achieves a 3.9$\times$ higher discovery rate with 89\% detection accuracy, demonstrating superior coverage, efficiency, and reproducibility for large-scale robustness evaluation.

Virtual Network Embedding (VNE) is a key enabler of network slicing, yet most formulations assume that each Virtual Network Request (VNR) has a fixed topology. Recently, VNE with Alternative topologies (VNEAP) was introduced to capture malleable VNRs, where each request can be instantiated using one of several functionally equivalent topologies that trade resources differently. While this flexibility enlarges the feasible space, it also introduces an additional decision layer, making dynamic embedding more challenging. This paper proposes HRL-VNEAP, a hierarchical reinforcement learning approach for VNEAP under dynamic arrivals. A high-level policy selects the most suitable alternative topology (or rejects the request), and a low-level policy embeds the chosen topology onto the substrate network. Experiments on realistic substrate topologies under multiple traffic loads show that naive exploitation strategies provide only modest gains, whereas HRL-VNEAP consistently achieves the best performance across all metrics. Compared to the strongest tested baselines, HRL-VNEAP improves acceptance ratio by up to \textbf{20.7\%}, total revenue by up to \textbf{36.2\%}, and revenue-over-cost by up to \textbf{22.1\%}. Finally, we benchmark against an MILP formulation on tractable instances to quantify the remaining gap to optimality and motivate future work on learning- and optimization-based VNEAP solutions.

The Metaverse, a shared and spatially organized digital continuum, is transforming various industries, with music emerging as a leading use case. Live concerts, collaborative composition, and interactive experiences are driving the Musical Metaverse (MM), but the requirements of the underlying network and service infrastructures hinder its growth. These challenges underscore the need for a novel modeling and simulation paradigm tailored to the unique characteristics of MM sessions, along with specialized service provisioning strategies capable of capturing their interactive, heterogeneous, and multicast-oriented nature. To this end, we make a first attempt to formally model and analyze the problem of service provisioning for MM sessions in 5G/6G networks. We first formalize service and network graph models for the MM, using "live audience interaction in a virtual concert" as a reference scenario. We then present MuMeNet, a novel discrete-event network simulator specifically tailored to the requirements and the traffic dynamics of the MM. We showcase the effectiveness of MuMeNet by running a linear programming based orchestration policy on the reference scenario and providing performance analysis under realistic MM workloads.

Automatic Pitch Correction (APC) enhances vocal recordings by aligning pitch deviations with intended musical notes. However, existing APC systems either rely on reference pitches, which limits practical applicability, or employ simple pitch estimation algorithms that often fail to preserve expressiveness and naturalness. We propose BERT-APC, a reference-free APC framework that corrects pitch errors while maintaining the expressiveness and naturalness of vocal performances. In BERT-APC, a stationary pitch predictor first estimates the stationary pitch of each note from the detuned singing voice, where stationary pitch is the continuous pitch from the stable region of a note and approximates its perceived pitch. A context-aware note pitch predictor then infers the intended pitch sequence using a repurposed music language model that incorporates musical context. Finally, a note-level correction algorithm fixes pitch errors while preserving intentional deviations for emotional expression. We also introduce a learnable data augmentation strategy that improves robustness by simulating realistic detuning patterns. Compared to two recent singing voice transcription models, BERT-APC demonstrated superior target note pitch prediction, outperforming the second-best model, ROSVOT, by 10.49 percentage points on highly detuned samples in raw pitch accuracy. In the MOS test, BERT-APC achieved the highest quality rating of $4.32 \pm 0.15$, significantly higher than Auto-Tune ($3.22 \pm 0.18$) and Melodyne ($3.08 \pm 0.18$), while maintaining a comparable ability to preserve expressive nuances. To the best of our knowledge, this is the first APC model that leverages a music language model to achieve reference-free pitch correction with symbolic musical context. The corrected audio samples are available at https://joshua-1995.github.io/BERT-APC-Demo/.

This work addresses the full-information output regulation problem for nonlinear systems, assuming the states of both the plant and the exosystem are known. In this setting, perfect tracking or rejection is achieved by constructing a zero-regulation-error manifold $π(w)$ and a feedforward input $c(w)$ that render such manifold invariant. The pair $(π(w), c(w))$ is characterized by the regulator equations, i.e., a system of PDEs with an algebraic constraint. We focus on accurately solving the regulator equations introducing a physics-informed neural network (PINN) approach that directly approximates $π(w)$ and $c(w)$ by minimizing the residuals under boundary and feasibility conditions, without requiring precomputed trajectories or labeled data. The learned operator maps exosystem states to steady state plant states and inputs, enables real-time inference and, critically, generalizes across families of the exosystem with varying initial conditions and parameters. The framework is validated on a regulation task that synchronizes a helicopter's vertical dynamics with a harmonically oscillating platform. The resulting PINN-based solver reconstructs the zero-error manifold with high fidelity and sustains regulation performance under exosystem variations, highlighting the potential of learning-enabled solvers for nonlinear output regulation. The proposed approach is broadly applicable to nonlinear systems that admit a solution to the output regulation problem.