How do language models use contextual information to answer health questions? How are their responses impacted by conflicting contexts? We assess the ability of language models to reason over long, conflicting biomedical contexts using HealthContradict, an expert-verified dataset comprising 920 unique instances, each consisting of a health-related question, a factual answer supported by scientific evidence, and two documents presenting contradictory stances. We consider several prompt settings, including correct, incorrect or contradictory context, and measure their impact on model outputs. Compared to existing medical question-answering evaluation benchmarks, HealthContradict provides greater distinctions of language models' contextual reasoning capabilities. Our experiments show that the strength of fine-tuned biomedical language models lies not only in their parametric knowledge from pretraining, but also in their ability to exploit correct context while resisting incorrect context.

We present VIGS-SLAM, a visual-inertial 3D Gaussian Splatting SLAM system that achieves robust real-time tracking and high-fidelity reconstruction. Although recent 3DGS-based SLAM methods achieve dense and photoreal-istic mapping, their purely visual design degrades under motion blur, low texture, and exposure variations. Our method tightly couples visual and inertial cues within a unified optimization framework, jointly refining camera poses, depths, and IMU states. It features robust IMU initialization, time-varying bias modeling, and loop closure with consistent Gaussian updates. Experiments on four challenging datasets demonstrate our superiority over state-of-the-art methods.

Model Recovery (MR) enables safe, explainable decision making in mission-critical autonomous systems (MCAS) by learning governing dynamical equations, but its deployment on edge devices is hindered by the iterative nature of neural ordinary differential equations (NODEs), which are inefficient on FPGAs. Memory and energy consumption are the main concerns when applying MR on edge devices for real-time operation. We propose MERINDA, a novel FPGA-accelerated MR framework that replaces iterative solvers with a parallelizable neural architecture equivalent to NODEs. MERINDA achieves nearly 11x lower DRAM usage and 2.2x faster runtime compared to mobile GPUs. Experiments reveal an inverse relationship between memory and energy at fixed accuracy, highlighting MERINDA's suitability for resource-constrained, real-time MCAS.

Large language models (LLMs) now mediate many web-based mental-health, crisis, and other emotionally sensitive services, yet their psychosocial safety in these settings remains poorly understood and weakly evaluated. We present DialogGuard, a multi-agent framework for assessing psychosocial risks in LLM-generated responses along five high-severity dimensions: privacy violations, discriminatory behaviour, mental manipulation, psychological harm, and insulting behaviour. DialogGuard can be applied to diverse generative models through four LLM-as-a-judge pipelines, including single-agent scoring, dual-agent correction, multi-agent debate, and stochastic majority voting, grounded in a shared three-level rubric usable by both human annotators and LLM judges. Using PKU-SafeRLHF with human safety annotations, we show that multi-agent mechanisms detect psychosocial risks more accurately than non-LLM baselines and single-agent judging; dual-agent correction and majority voting provide the best trade-off between accuracy, alignment with human ratings, and robustness, while debate attains higher recall but over-flags borderline cases. We release Dialog-Guard as open-source software with a web interface that provides per-dimension risk scores and explainable natural-language rationales. A formative study with 12 practitioners illustrates how it supports prompt design, auditing, and supervision of web-facing applications for vulnerable users.

Artificial intelligence has advanced rapidly across perception, language, reasoning, and multimodal domains. Yet despite these achievements, modern AI systems remain fundamentally limited in their ability to self-monitor, self-correct, and regulate their behavior autonomously in dynamic contexts. This paper identifies and analyzes seven core deficiencies that constrain contemporary AI models: the absence of intrinsic self-monitoring, lack of meta-cognitive awareness, fixed and non-adaptive learning mechanisms, inability to restructure goals, lack of representational maintenance, insufficient embodied feedback, and the absence of intrinsic agency. Alongside identifying these limitations, we also outline a forward-looking perspective on how AI may evolve beyond them through architectures that mirror neurocognitive principles. We argue that these structural limitations prevent current architectures, including deep learning and transformer-based systems, from achieving robust generalization, lifelong adaptability, and real-world autonomy. Drawing on a comparative analysis of artificial systems and biological cognition [7], and integrating insights from AI research, cognitive science, and neuroscience, we outline how these capabilities are absent in current models and why scaling alone cannot resolve them. We conclude by advocating for a paradigmatic shift toward cognitively grounded AI (cognitive autonomy) capable of self-directed adaptation, dynamic representation management, and intentional, goal-oriented behavior, paired with reformative oversight mechanisms [8] that ensure autonomous systems remain interpretable, governable, and aligned with human values.

Traffic classification (TC) plays a critical role in cybersecurity, particularly in IoT and embedded contexts, where inspection must often occur locally under tight hardware constraints. We use hardware-aware neural architecture search (HW-NAS) to derive lightweight TC models that are accurate, efficient, and deployable on edge platforms. Two input formats are considered: a flattened byte sequence and a 2D packet-wise time series; we examine how input structure affects adversarial vulnerability when using resource-constrained models. Robustness is assessed against white-box attacks, specifically Fast Gradient Sign Method (FGSM) and Projected Gradient Descent (PGD). On USTC-TFC2016, both HW-NAS models achieve over 99% clean-data accuracy while remaining within 65k parameters and 2M FLOPs. Yet under perturbations of strength 0.1, their robustness diverges: the flat model retains over 85% accuracy, while the time-series variant drops below 35%. Adversarial fine-tuning delivers robust gains, with flat-input accuracy exceeding 96% and the time-series variant recovering over 60 percentage points in robustness, all without compromising efficiency. The results underscore how input structure influences adversarial vulnerability, and show that even compact, resource-efficient models can attain strong robustness, supporting their practical deployment in secure edge-based TC.

Recent text-to-video models have demonstrated strong temporal generation capabilities, yet their potential for image restoration remains underexplored. In this work, we repurpose CogVideo for progressive visual restoration tasks by fine-tuning it to generate restoration trajectories rather than natural video motion. Specifically, we construct synthetic datasets for super-resolution, deblurring, and low-light enhancement, where each sample depicts a gradual transition from degraded to clean frames. Two prompting strategies are compared: a uniform text prompt shared across all samples, and a scene-specific prompting scheme generated via LLaVA multi-modal LLM and refined with ChatGPT. Our fine-tuned model learns to associate temporal progression with restoration quality, producing sequences that improve perceptual metrics such as PSNR, SSIM, and LPIPS across frames. Extensive experiments show that CogVideo effectively restores spatial detail and illumination consistency while maintaining temporal coherence. Moreover, the model generalizes to real-world scenarios on the ReLoBlur dataset without additional training, demonstrating strong zero-shot robustness and interpretability through temporal restoration.

We propose a methodology for falsifying safety properties in robotic vehicle systems through property-guided reduction and surrogate execution. By isolating only the control logic and physical dynamics relevant to a given specification, we construct lightweight surrogate models that preserve property-relevant behaviors while eliminating unrelated system complexity. This enables scalable falsification via trace analysis and temporal logic oracles. We demonstrate the approach on a drone control system containing a known safety flaw. The surrogate replicates failure conditions at a fraction of the simulation cost, and a property-guided fuzzer efficiently discovers semantic violations. Our results suggest that controller reduction, when coupled with logic-aware test generation, provides a practical and scalable path toward semantic verification of cyber-physical systems.

Trustworthy machine learning in healthcare requires strong predictive performance, fairness, and explanations. While it is known that improving fairness can affect predictive performance, little is known about how fairness improvements influence explainability, an essential ingredient for clinical trust. Clinicians may hesitate to rely on a model whose explanations shift after fairness constraints are applied. In this study, we examine how enhancing fairness through bias mitigation techniques reshapes Shapley-based feature rankings. We quantify changes in feature importance rankings after applying fairness constraints across three datasets: pediatric urinary tract infection risk, direct anticoagulant bleeding risk, and recidivism risk. We also evaluate multiple model classes on the stability of Shapley-based rankings. We find that increasing model fairness across racial subgroups can significantly alter feature importance rankings, sometimes in different ways across groups. These results highlight the need to jointly consider accuracy, fairness, and explainability in model assessment rather than in isolation.

LLM-based trading agents are increasingly deployed in real-world financial markets to perform autonomous analysis and execution. However, their reliability and robustness under adversarial or faulty conditions remain largely unexamined, despite operating in high-risk, irreversible financial environments. We propose TradeTrap, a unified evaluation framework for systematically stress-testing both adaptive and procedural autonomous trading agents. TradeTrap targets four core components of autonomous trading agents: market intelligence, strategy formulation, portfolio and ledger handling, and trade execution, and evaluates their robustness under controlled system-level perturbations. All evaluations are conducted in a closed-loop historical backtesting setting on real US equity market data with identical initial conditions, enabling fair and reproducible comparisons across agents and attacks. Extensive experiments show that small perturbations at a single component can propagate through the agent decision loop and induce extreme concentration, runaway exposure, and large portfolio drawdowns across both agent types, demonstrating that current autonomous trading agents can be systematically misled at the system level. Our code is available at https://github.com/Yanlewen/TradeTrap.