Automated cardiac interpretation in resource-constrained settings (RCS) is often hindered by poor-quality echocardiographic imaging, limiting the effectiveness of downstream diagnostic models. While super-resolution (SR) techniques have shown promise in enhancing magnetic resonance imaging (MRI) and computed tomography (CT) scans, their application to echocardiography-a widely accessible but noise-prone modality-remains underexplored. In this work, we investigate the potential of deep learning-based SR to improve classification accuracy on low-quality 2D echocardiograms. Using the publicly available CAMUS dataset, we stratify samples by image quality and evaluate two clinically relevant tasks of varying complexity: a relatively simple Two-Chamber vs. Four-Chamber (2CH vs. 4CH) view classification and a more complex End-Diastole vs. End-Systole (ED vs. ES) phase classification. We apply two widely used SR models-Super-Resolution Generative Adversarial Network (SRGAN) and Super-Resolution Residual Network (SRResNet), to enhance poor-quality images and observe significant gains in performance metric-particularly with SRResNet, which also offers computational efficiency. Our findings demonstrate that SR can effectively recover diagnostic value in degraded echo scans, making it a viable tool for AI-assisted care in RCS, achieving more with less.

Annually and globally, over three billion radiography examinations and computer tomography scans result in mostly unstructured radiology reports containing free text. Despite the potential benefits of structured reporting, its adoption is limited by factors such as established processes, resource constraints and potential loss of information. However, structured information would be necessary for various use cases, including automatic analysis, clinical trial matching, and prediction of health outcomes. This study introduces RadEx, an end-to-end framework comprising 15 software components and ten artifacts to develop systems that perform automated information extraction from radiology reports. It covers the complete process from annotating training data to extracting information by offering a consistent generic information model and setting boundaries for model development. Specifically, RadEx allows clinicians to define relevant information for clinical domains (e.g., mammography) and to create report templates. The framework supports both generative and encoder-only models and the decoupling of information extraction from template filling enables independent model improvements. Developing information extraction systems according to the RadEx framework facilitates implementation and maintenance as components are easily exchangeable, while standardized artifacts ensure interoperability between components.

Introduction: Microblogging websites have massed rich data sources for sentiment analysis and opinion mining. In this regard, sentiment classification has frequently proven inefficient because microblog posts typically lack syntactically consistent terms and representatives since users on these social networks do not like to write lengthy statements. Also, there are some limitations to low-resource languages. The Persian language has exceptional characteristics and demands unique annotated data and models for the sentiment analysis task, which are distinctive from text features within the English dialect. Method: This paper first constructs a user opinion dataset called ITRC-Opinion in a collaborative environment and insource way. Our dataset contains 60,000 informal and colloquial Persian texts from social microblogs such as Twitter and Instagram. Second, this study proposes a new architecture based on the convolutional neural network (CNN) model for more effective sentiment analysis of colloquial text in social microblog posts. The constructed datasets are used to evaluate the presented architecture. Furthermore, some models, such as LSTM, CNN-RNN, BiLSTM, and BiGRU with different word embeddings, including Fasttext, Glove, and Word2vec, investigated our dataset and evaluated the results. Results: The results demonstrate the benefit of our dataset and the proposed model (72% accuracy), displaying meaningful improvement in sentiment classification performance.

The diurnal cycle of tropical cyclones (TCs) is a daily cycle in clouds that appears in satellite images and may have implications for TC structure and intensity. The diurnal pattern can be seen in infrared (IR) satellite imagery as cyclical pulses in the cloud field that propagate radially outward from the center of nearly all Atlantic-basin TCs. These diurnal pulses, a distinguishing characteristic of the TC diurnal cycle, begin forming in the storm's inner core near sunset each day and appear as a region of cooling cloud-top temperatures. The area of cooling takes on a ring-like appearance as cloud-top warming occurs on its inside edge and the cooling moves away from the storm overnight, reaching several hundred kilometers from the circulation center by the following afternoon. The state-of-the-art TC diurnal cycle measurement has a limited ability to analyze the behavior beyond qualitative observations. We present a method for quantifying the TC diurnal cycle using one-dimensional persistent homology, a tool from Topological Data Analysis, by tracking maximum persistence and quantifying the cycle using the discrete Fourier transform. Using Geostationary Operational Environmental Satellite IR imagery data from Hurricane Felix (2007), our method is able to detect an approximate daily cycle.

Classifier guidance is a way to control diffusion generation by using a noise-conditioned classifier to steer the sampling process toward a target class. One drawback of classifier guidance is that it requires two separately trained models: a classifier and a diffusion model. We therefore study a more compact alternative in which a conventionally trained speech classifier is repurposed as the backbone for diffusion generation. Starting from a frozen noise-conditioned classifier in log-Mel space, we attach a lightweight subnetwork that reuses intermediate classifier representations and train only this subnetwork under a Denoising Score Matching objective. Our work shows that a pretrained classifier can be repurposed for conditional generation, providing an appealing bridge between discriminative modeling and conditional speech synthesis resulting in high speech quality within a single-backbone model, with reduced memory footprint and computational cost.

Competing risks are commonly observed in engineering fields and can bring challenges to time-to-event data modeling when the application scenarios are complicated. Recently, deep neural networks have received great attention for prediction with competing risks, due to their flexibility and high learning capability. However, the complexity of neural network structure brings extra difficulty in hyperparameter tuning based on different data inputs. Additionally, when an engineered system has complex physical structures with multiple hierarchical levels, treating all structural levels as a single group of inputs may fail to capture critical information. To address the issues, we propose a Structured Segmented Hazard Deep Neural Network (SSH-Net) for failure time prediction under cause-specific competing risks framework. Our approach associates neural network structure with data structures, and allows different covariate groups to impact the failure prediction through separate sub-networks. The neural network is constructed based on a cause-specific competing risks model. The SSH-Net outputs cause-specific hazard functions, and utilizes the penalized log-likelihood as the loss function. The prediction accuracy of SSH-Net is validated through simulation studies by evaluating the Brier score, the area under receiver operating characteristic curves (AUC), and the root mean square error (RMSE) of the predicted cause-specific cumulative incident function. We further demonstrate the model's ability to predict failure time distribution functions using the Titan GPU failure time data.

In offline Reinforcement Learning, immediate rewards in logged batch data are often unobserved due to sparse or irregular record-keeping, or censored beyond certain reward values. This issue arises in practical settings, including health care and marketing. We investigate off-policy evaluation (OPE) in finite-horizon Markov decision processes when rewards are missing not at random (MNAR), which breaks ignorability and induces selection bias even after conditioning on states and actions. To address this, we formalize a reward-dependent propensity model and use future states as shadow variables to identify the full-data conditional mean reward. We further introduce a bridge function that recovers the conditional mean reward without explicitly modeling the MNAR mechanism, and estimate it via a min-max procedure to avoid double sampling. Building upon these identification results, we propose an Fitted-Q-Evaluation-style estimator that propagates the recovered rewards while allowing target policies to depend on past missingness indicators. Finally, we establish consistency and finite-sample error bounds for our OPE estimator, and show through experiments the strong performance of our method compared to existing methods on simulated and MIMIC-III Sepsis data.

Existing mean opinion score (MOS) prediction models typically predict utterance-level naturalness MOS and can be insensitive to localized pitch-accent errors. We propose Pitch-Accent-focused Speech Quality Assessment (PASQA), which explicitly targets pitch-accent correctness. To train our model, we construct a controlled Japanese accent-error dataset by changing accent patterns using an accent-controllable text-to-speech system, and compute a pseudo accent-quality score from the accent-error rate. PASQA builds on self-supervised representations and employs mora-conditioned fusion, ranking loss, an auxiliary accent-error localization task, and speaker-invariant training. Experiments show that conventional models fail to preserve the ordering by accent-error severity, whereas PASQA achieves high ordering accuracy on both seen and unseen speakers. Further, PASQA shows stronger agreement with human accent-correctness judgments. The code is available at https://github.com/lycorp-jp/PASQA.

User-defined keyword spotting (UD-KWS) enables zero-shot wake-word detection from text, but existing systems learn speaker-invariant representations that cannot reject impostors uttering the correct keyword. We address this dual zero-shot setting -- unseen keywords and unseen speakers -- with ZP-KWS, a lightweight framework combining a phoneme-supervised audio encoder with a GE2E-pretrained compact speaker encoder (about 0.9M parameters). Multiplicative late fusion at inference grants each branch independent veto power, supporting modes from conventional detection to strict speaker-gated activation without retraining. On LibriPhrase, Google Speech Commands, and Qualcomm datasets, ZP-KWS reduces target-only FRR at 1% FAR by up to 60% relative to the strongest baseline while maintaining competitive keyword detection, all within a 1.55M parameter budget for edge deployment.

Burst suppression (BS) is a clinically relevant electroencephalographic (EEG) pattern used to monitor sedation depth and brain activity in critically ill patients, particularly during induced coma in Intensive Care Units (ICUs). Automatic burst detection remains challenging because BS patterns vary substantially between patients and annotated datasets are scarce. Recently, EEG Foundation Models (FMs) have shown promise across several downstream EEG applications, but their usefulness for BS detection remains unexplored. We present the first study to evaluate EEG FMs for burst detection in reduced-montage ICU EEG without patient-specific calibration. We compare REVE-base, LUNA-large and LuMamba-Tiny with an adaptive thresholding baseline and a task-specific EEGNet baseline. Additionally, we complement conventional EEG window-based classification with event-based burst detection evaluation. This helps assessing clinically whether burst episodes are correctly detected, reducing the impact of expected annotation variability. The best model, REVE-base, achieved the highest event-based F1-score ($0.868 \pm 0.167$) and reduced burst-per-minute error by 52.1% and 36.2% compared to EEGNet and adaptive thresholding respectively, supporting FMs for scalable EEG monitoring in ICU. Ablation experiments showed that full fine-tuning was the most effective adaptation strategy with respect to frozen-backbone training, two-step fine-tuning, and LoRA-based adaptation, improving event-based F1-score over frozen-backbone training by up to $+0.102$ for LUNA-large. With reduced labeled datasets, pretrained REVE-base outperformed random initialization by $+0.723$ event-based F1 points at 25% of the cohort, demonstrating the benefit of pretraining FM representations when adapted to burst detection with limited labeled data.

We propose a model-grounded RAG-based AI economist with an agentic framework for economic scenario analysis using large language models (LLMs) and knowledge graphs. While LLMs can generate fluent economic narratives, economists are often required to make economic claims grounded by economic theory and real-world data. Based on this motivation, this study proposes an RAG-based AI economist, which utilizes knowledge graphs including economic data and theory and LLM-based agents to plan the analysis, retrieve relevant evidence, select appropriate models, and generate reports. In our framework, we do not produce quantitative claims directly with the language model alone; instead, we generate narratives grounded in explicit model-based computations and linked to the retrieved evidence via AI agents. We refer to our framework as an AI economist agent. We evaluate the AI economist agent in two applications: economist report generation for U.S. inflation persistence and Federal Reserve policy, and bank stress-test narrative generation for U.S. commercial real estate refinancing stress. The results illustrate how grounding the generated reports improves their economic coherence and traceability.

Mean opinion score (MOS) prediction models are widely used as proxy metrics in text-to-speech (TTS) research, yet their ability to capture quality differences beyond acoustic fidelity remains unclear. We investigate this via controlled perturbations on speech: acoustic degradation, prosodic errors, and manipulation of speaker-specific characteristics such as pitch and speaking rate. We obtained MOS predictions for these speech samples from both human listeners and the model, and analyzed the differences in their perceptual characteristics. Results show that most models track acoustic degradation well, while all are insensitive to prosodic errors despite large subjective score drops. For speaker characteristics, models exhibit a double dissociation: strong mean fundamental frequency (F0) biases absent in human ratings, yet insensitivity to speaking rate and F0 variability that humans notice. These findings highlight limitations of scalar MOS prediction beyond acoustic fidelity.

Automatic speech recognition remains unreliable for dysarthric speech due to data scarcity and high inter-speaker variability. While synthetic data can address these gaps, traditional methods often require extensive speaker-specific data, reintroducing the collection bottleneck. We investigate zero-shot voice cloning as a low-burden augmentation strategy, using Higgs Audio V2 to clone speakers in the TORGO dataset. We fine-tune (FT) Whisper-medium on cloned, real, and hybrid data and evaluate on held-out real speech. Compared to the zero-shot (31.62%), Clone FT achieved a competitive 26.00% WER, nearly matching the 24.44% and 25.12% seen with Real and Hybrid FT, respectively. Notably, Clone and Hybrid FT outperform Real FT for moderate-severe speakers. Clone FT achieves the best results (11.45% relative) in cross-corpus evaluation on the SAP-1102. These results suggest that zero-shot cloning provides scalable training data that circumvents the costly data collection bottleneck.

Dysarthric speech recognition is crucial for facilitating effective communication among individuals with dysarthria. However, accurately recognizing dysarthric speech poses significant challenges due to varying severity levels and limited data availability. In this paper, we explore data augmentation techniques for dysarthric automatic speech recognition (ASR) systems by fine-tuning the End-to-End pre-trained Wav2Vec2 model, with a specific focus on severity levels. To address the challenges of data scarcity and the need for extensive data in fine-tuning pre-trained ASR systems for dysarthric speech, we investigate four prominent data augmentation methods: Speaking-Rate Modification (SRM), Pitch Modification (PM), Formant Modification (FM), and vocal tract Length Perturbation (VTLP), tailored to different aspects of dysarthria. The study uses individually fine-tuned Wav2Vec2 models for each severity class as baseline systems. Additionally, we conducted severity-specific fine-tuning of the ASR model using augmented data. Results demonstrate distinct efficacy patterns for each augmentation technique across severity levels. The best WERs were achieved with SRM ($s$=0.8) for \textit{low} (9.02\%) and \textit{medium} (38.11\%) severities, and with PM ($τ$=0.8) for \textit{high} severity (55.15\%), reflecting relative improvements of 30.02\%, 16.64\%, and 15.47\%, respectively. These results confirm the effectiveness of the augmentation methods in improving dysarthric ASR performance.

The challenge associated with recognizing dysarthric speech primarily arises from pronounced acoustic variability attributed to impaired articulatory precision. Past research has demonstrated improved recognition through the use of hybrid DNN/HMM sequence discriminative training. This paper presents a comprehensive investigation of various combinations of acoustic features tailored to different Acoustic Models, offering suitable feature selections for each. The incorporation of Pitch features notably improved recognition performance, especially for sentence recognition tasks involving dysarthric speech. Through a systematic examination of the TORGO database, we have demonstrated the potential to enhance the performance of the state-of-the-art Factorized Time Delay Neural Network (F-TDNN) model for recognizing dysarthric speech. Our methods, implemented with the F-TDNN model, resulted in a 4.65\% relative improvement in isolated word recognition and a 4.63\% relative improvement in sentence recognition for dysarthric speech, compared to previous research. This improvement effectively compensates for speech variability, attributable to our deliberate selection of the number of overlapping frames between consecutive training example chunks.

The challenge associated with recognizing dysarthric speech primarily arises from pronounced acoustic variability attributed to impaired articulatory precision. Past research has demonstrated improved recognition through the use of hybrid DNN/HMM sequence discriminative training. This paper presents a comprehensive investigation of various combinations of acoustic features tailored to different Acoustic Models, offering suitable feature selections for each. The incorporation of Pitch features notably improved recognition performance, especially for sentence recognition tasks involving dysarthric speech. Through a systematic examination of the TORGO database, we have demonstrated the potential to enhance the performance of the state-of-the-art Factorized Time Delay Neural Network (F-TDNN) model for recognizing dysarthric speech. Our methods, implemented with the F-TDNN model, resulted in a 4.65\% relative improvement in isolated word recognition and a 4.63\% relative improvement in sentence recognition for dysarthric speech, compared to previous research. This improvement effectively compensates for speech variability, attributable to our deliberate selection of the number of overlapping frames between consecutive training example chunks.

Large language models (LLMs) are increasingly used as judges for open-ended generation, as large-scale human evaluation is often expensive and difficult to scale, yet their preferences remain imperfect proxies for human judgment. Existing auditing pipelines often assume that a reliable subset of examples or clean supervision signals are available beforehand, for example from human annotation, heuristic filtering, or the outputs of strong judges. In LLM evaluation, this assumption is fragile: the initial split may inherit judge bias, while human verification is typically too scarce to define stable groups at scale. We propose AURA, an adaptive uncertainty--aware refinement framework for auditing pairwise LLM--as--a--judge decisions under selected human verification. AURA iteratively learns a human-consistency signal, propagates reliable evidence, and prioritizes uncertain comparisons for human review. The key idea is to treat trust in a judge as a latent quantity that is progressively refined as evidence accumulates. We provide a compact formulation, a stable refinement procedure, and a comprehensive evaluation on both synthetic and real pairwise LLM-answer data.

Motivated by the privacy, sensitivity and sharing limitations of health data, we present a comprehensive pipeline for inference of Bayesian mixture models within a federated learning setting, i.e. when data cannot be fully shared or pooled across compute nodes. We adopt a Consensus Monte Carlo (CMC) approach, in which an MCMC algorithm is run independently within each data silo to estimate local posterior distributions, which are then aggregated to approximate the posterior over the full data. The variational CMC approach of Rabinovich, Angelino and Jordan (2015) [1] frames the aggregation step as a variational inference problem, but their application to mixtures assumes the number of clusters and key mixture parameters to be known. Our main methodological contributions are: (i) an extension of variational CMC to over-fitted Bayesian mixture models that infer the number of clusters and all model parameters, without requiring conjugacy; (ii) novel cluster-matching algorithms suitable for cross-silo settings in which not every cluster appears in each local dataset; (iii) a number of inference strategies for the aggregation step, matched to different federated learning constraints; and (iv) guidelines for choosing among these in practice. A comprehensive simulation study validates the framework and allows us to compare to state-of-the-art federated learning alternatives. Notably, we show that when the composition of local datasets reflects the underlying clustering structure in the data, our approach can recover small clusters with greater accuracy than standard MCMC applied to the pooled data. We illustrate the framework on large-scale electronic health record data, identifying multi-morbidity patterns in a British geriatric population.

We propose a scalable method for training prediction (machine learning) models in the predict-then-optimize paradigm, where model outputs serve as coefficients for a subsequent linear optimization task. Directly minimizing the empirical decision regret is intractable for linear programming and combinatorial optimization since the decision mapping is piecewise constant, and the gradients are zero almost everywhere. While existing methods address this by smoothing the differentiation process, they suffer from scalability issues, since a computationally expensive solver call is required for every gradient evaluation. To address this, we propose a decision-focused learning pipeline based on a measure transformation principle, which yields a new surrogate loss that is completely optimization-solver-free during training. We establish theoretical guarantees, including Fisher consistency and excess risk bounds. Empirically, our method achieves decision quality competitive with state-of-the-art methods while reducing training time by orders of magnitude.

Signed pairwise interaction scores fundamentally conflate uniqueness (U), redundancy (R), and synergy (S). We prove this on a minimal 3-way XOR structural causal model: faithful indices such as Shapley-Taylor return zero per pair, whereas projective indices such as Shapley Interaction spread the third-order effect into pair scalars that conflate the three mechanisms. We introduce Stochastic Hi-Fi, a post-hoc, retraining-free predictability decomposition that estimates per-feature U/R/S profiles by interventional masked inference. The estimator provides exact interventional semantics, finite-sample Monte Carlo bounds, strict variance reduction from coupled diamond sampling, and uniform finite-vocabulary convergence. Across tabular SCMs, Stochastic Hi-Fi recovers structure missed by scalar baselines (up to 411x larger interaction-magnitude recovery ratios). It also separates redundant and synergistic heads in the GPT-2 IOI circuit. On NIH ChestX-ray14, Stochastic Hi-Fi matches GradCAM on Pointing Game and improves substantially on Deletion AUC.

We present Full-Self Diagnostics (FSD), a unified mathematical framework for recovering latent physiological states from unconstrained 9-second facial videos captured by consumer smartphones. The approach integrates five mutually reinforcing components: (1) a physics-based forward model derived from the radiative transfer equation and chromophore absorption that maps camera observables to biomarker concentrations; (2) an information-theoretic observability theory proving that multi-channel visual signals (spectral, pulse, respiratory, micro-expression, and oculomotor) contain strictly increasing mutual information with physiological state; (3) a stable, Tikhonov-regularized inverse problem with domain-uniform identifiability guarantees; (4) an operator-learning formulation that enables generalization across devices, resolutions, and populations; and (5) a supervised learning procedure, interpretable as stochastic variational inference, that continuously refines the model from paired biosensor ground truth with performance improving proportionally to one over the square root of the number of paired observations. Empirical validation on 38812 real-world paired scans across 59 subjects demonstrates practical performance. Self-collected data from the lead author (glucose range 35-550 mg/dL) yields MARD of 29.86 percent with 97.57 percent of predictions in Clarke Error Grid Zones A+B and only 0.27 percent in the dangerous Zone E. A well-managed diabetic participant achieves MARD of 17 percent in the narrower 70-180 mg/dL band. These results confirm that consumer-grade facial video encodes sufficient structured information for clinically relevant, non-invasive biomarker inference under fully unconstrained conditions, with performance scaling predictably as more paired data becomes available.

Generative recommendation is an emerging paradigm that has shown promise in industrial recommendation systems, aiming to predict users' next interactions from their historical behaviors. At the core of generative recommendation lies item tokenization, which bridges item semantics and recommendation models. However, existing methods often struggle to effectively organize and inject complex user-behavioral and item-semantic contexts into recommendation models simultaneously. On the one hand, existing graph-based integration methods, such as graph serialization and graph neural networks, either suffer from scalability issues or exploit only local graph information. On the other hand, existing semantic tokenization methods typically rely on heuristics and lack explicit supervision signals, which may lead to inaccurate or suboptimal semantic representations. To address these limitations in user interest context modeling, we propose G2Rec, a scalable framework that unifies holistic graph-based user co-engagement modeling with semantic tokenization for industrial-scale generative recommendation. Overall, G2Rec enables recommendation models to capture holistic and semantically grounded user interest prototypes without requiring ground-truth user interests, thereby providing more comprehensive and accurate modeling of user behavior contexts in industrial sequential recommendation. Online deployment across product surfaces and extensive experiments on public datasets demonstrate the superiority of G2Rec over existing methods.

LLM-based coding agents need higher-level operational knowledge about a repository (which files house which subsystems, how to run the test suite, which workflows have historically led to wrong fixes) that does not exist in the code itself. Engineers typically maintain \texttt{AGENTS.md} files to supply this context as instructions for coding agents, but whether they help is contested: recent studies disagree on whether LLM-generated guidance improves or harms agent performance. In this paper we show that how the guidance is produced is the decisive variable, and introduce \emph{probe-and-refine tuning}: a procedure that uses synthetic bug-fix probes to iteratively diagnose and patch a repository's guidance file through single-shot LLM calls, with no agent loop or tool use during tuning. On SWE-bench Verified across four independent trials with Qwen3.5-35B-A3B at 200 steps, probe-and-refine achieves 33.0\,\% mean resolve rate vs.\ 28.3\,\% for the static knowledge base used to initialize it and 25.5\,\% for an unguided baseline ($p < 0.001$ for both probe-and-refine contrasts). The improvement comes from coverage rather than precision: refined guidance produces evaluable patches for 14.5 percentage points (pp) more instances while per-patch precision remains statistically constant ($\sim$59\,\%, $p = 0.119$), showing that improved guidance helps agents reach the correct file rather than improving the quality of the changes they make. Further, a step-budget experiment shows that guidance is what lets the agent use a larger step budget productively, and a cross-model experiment with NVIDIA-Nemotron-3-Nano-30B-A3B finds that the tuning loop degrades when the model cannot generate sufficiently diagnostic output, though per-patch precision remains constant even then.

Securing AI agents that operate in complex digital environments has become a critical need, and runtime monitoring approaches that formulate and enforce policies expressed in a formal language like Datalog offer a promising solution. However, existing approaches are restricted to deterministic policies. In many practical applications of AI agents, there is a need to enforce security policies in the face of ambiguity, leading to probabilistic predicates or state transitions (for example, a declassifier or Personally Identifiable Information (PII) detector that has some failure probability on each invocation). Furthermore, in many such applications, one cannot easily make the independence assumptions necessary to invoke prior work on probabilistic inference in Datalog. We address this by introducing a sound and efficient framework for such verification based on distributionally robust optimization, computing sound upper bounds on the probability of policy violation regardless of possible correlations between predicates. On standard benchmarks for terminal and tool calling agents, we demonstrate that our approach outperforms prior art and improves the security-utility trade-off while ensuring rigorous bounds on the probability of policy violation.

Whether LLMs scoring well on vulnerability benchmarks genuinely reason about security or merely pattern-match on contaminated data remains unresolved. We present CWE-Trace, a framework for LLM vulnerability detection built from 834 manually curated Linux kernel samples spanning 74 CWEs. The framework enforces a strict temporal split (pre-2025 historical set / post-cutoff leakage-free set), preserves context-aware vulnerable--patched pairs, and introduces two diagnostic metrics: the Directional Failure Index (DFI) and Hierarchical Distance and Direction (HDD). We evaluate eight vanilla LLMs and 15 LoRA fine-tuned variants across non-targeted detection, targeted detection, and CWE classification. Our analysis yields two key results. First, data contamination provides no measurable advantage. Function-level analysis shows that 84% of nominally contaminated samples carry no usable memorization signal: vulnerable functions are absent or cross-mapped across datasets, and ~31% of contaminated samples carry CWE misclassification. Second, backbone directional priors dominate fine-tuning. Models exhibit stable, systematic failure modes (DFI ranging from -85.5 to +94.8 pp) that persist from historical to post-cutoff data and resist correction. Fine-tuning shifts the output threshold without changing the decision policy. This is calibration without comprehension: output distributions adapt to training data while the underlying security reasoning remains absent. The weakest backbone at binary detection (DeepSeek-R1) gains the most in coarse CWE classification, revealing that detection and understanding are decoupled capabilities. The best detection score reaches only 52.1% (+2.1 pp above chance); exact CWE ranking remains below 1.3% Top-1 accuracy, confirming that current LLMs lack reliable security reasoning for systems software, regardless of fine-tuning strategy.

Agentic AI systems increasingly rely on language-model components to interpret instructions, process external data, invoke tools, and coordinate with other agents. These capabilities make prompt-injection and jailbreak attacks more consequential, especially as attackers adopt model-guided automation to scale probing, prompt refinement, and response evaluation. This work analyzes the resulting attack-defense setting through a probabilistic model of a target system, its defense mechanism, and the attacker's automated judge. Our analysis shows that conventional detect-and-block defenses can allow attacker success rate (ASR) to approach one as the query budget grows, since predictable refusals provide useful feedback to automated search. We then examine detect-and-misdirect, where detected malicious interactions receive controlled, non-operational responses designed to induce false-positive errors in the attacker's judge. This strategy reduces the positive predictive value of attacker-selected candidates and yields a bounded asymptotic ASR. We evaluate a proof-of-concept realization of this strategy through Contextual Misdirection via Progressive Engagement (CMPE), a lightweight conversational misdirection method designed to replace predictable refusal text with safe but strategically misleading responses in automated jailbreak settings. On jailbreak benchmarks, CMPE reduces estimated ASR upper bounds by up to two orders of magnitude and nearly eliminates verified attack success in end-to-end PAIR and GPTFuzz attack runs.

Malware analysts often inspect compiled binaries through decompiled pseudo-C, when source code is unavailable. Recent work suggests that large language models (LLMs) can assist this process by classifying decompiled code as benign or malicious, but existing pipelines typically rely on a single decompiler view. We argue that this assumption is fragile: decompilers are lossy heuristic tools, and different decompilers can expose different artefacts of the same binary. We curate a benchmark of benign utilities and malicious programs spanning a range of threat behaviors. Each sample is compiled and decompiled with both Ghidra and RetDec, yielding matched pseudo-C views. Across a range of LLMs from major model families, we find that providing both decompiler views improves malicious-class F1, mainly by increasing recall on malicious samples. Agreement analyses further show that Ghidra and RetDec make partially different errors, supporting the view that decompiler outputs provide complementary evidence. Our results suggest that multi-decompiler prompting is a simple, training-free way to improve LLM-based malware triage in practical settings.

Large language model (LLM) agents are increasingly proposed as supervisory components for safety-critical systems, yet their robustness under sustained, adaptive adversarial pressure remains poorly characterized. We present NRT-Bench, a benchmark for multi-turn red-teaming of LLM agents acting as operators of a safety-critical system, instantiated in a simulated nuclear power plant control room. A five-role operator team, each backed by a configurable LLM, runs a plant governed by six critical safety functions (CSFs), while adversaries inject messages over four channels in bounded multi-turn sessions with per-turn feedback. Harm is an objective signal rather than LLM-judged text: a run terminates the moment any CSF is lost, attributed to the causing message. Evaluating four frontier operator models under a fixed-attack paired-replay protocol, we find that adaptive multi-turn attacks reliably push the operator team past a safety limit: across the four models, between 8.7% and 12.1% of attack sessions end with the plant losing a critical safety function. Although the four models look almost equally robust by this aggregate rate, their failures barely overlap: of $149$ sessions, none defeat all four models while a third defeat at least one, so vulnerabilities are nearly disjoint across models rather than nested. The effect of added defences is strongly model-dependent: the same guardrail stack or safety-advisor agent that lowers attack success for one model can raise it for another. We release the simulation venue, attack dataset, and replay tooling for reproducible safety evaluation of LLM agents.

Large Language Models (LLMs) show promise for code compilation tasks, but applying them to runtime performance tuning is difficult due to complex microarchitectural effects and noisy runtime measurements. We present AutoPass, a multi-agent framework for compiler performance tuning that uses compiler and runtime evidence to guide LLM-generated optimization decisions. Rather than treating the compiler as a black box like prior auto-tuning schemes, AutoPass opens up the compiler to the LLM, enabling it to query compiler-internal optimization states and analyze the intermediate representation to orchestrate compiler options. The search process iteratively refines optimization configurations using measured runtime feedback to diagnose regressions and guide latency-improving edits. AutoPass operates in an inference-only, training-free setting and requires no offline training or task-specific fine-tuning, making it readily applicable to new benchmarks and platforms. We implement AutoPass on the LLVM compiler and evaluate it on server-grade x86-64 and embedded ARM64 systems. AutoPass outperforms expert-tuned heuristics and classical autotuning methods, achieving geometric-mean speedups of 1.043x and 1.117x over LLVM -O3 on x86-64 and ARM64, respectively.

Large model inference optimization serves as a key foundation for supporting the scalable, low-cost, and highly stable operation of large model services. Centered on token-oriented inference optimization technology, this paper proposes for the first time a four-layer technical architecture consisting of Multi-model Fusion, Model Optimization, Compute-Model Fusion, and Compute-Network-Model Fusion. It systematically reviews the key technologies and current industry status across these four levels and analyzes the application value of related technologies in real-world business scenarios. This paper provides a practical technical path for reducing token production costs, improving token service efficiency, ensuring the stability of token supply, and driving the transition of large model services from being merely callable to being operable.