Brain-tuning enhances brain alignment and downstream performance by fine-tuning speech language models with neural recordings.However, previous work relies primarily on fMRI, whose temporal resolution integrates neural activity over seconds, blending distinct processing stages into a single supervision signal and precluding temporally targeted training.We introduce ECoG-tuning, which leverages electrocorticography's millisecond precision to train speech language models.We design temporally targeted windows-a speech window capturing acoustic-phonetic encoding and a language window capturing higher-order linguistic processing-grounded in neuroscientific findings about temporal encoding hierarchies.Evaluating three models on the Podcast ECoG dataset, we find that ECoG-tuning significantly improves brain alignment over pretrained and distillation baselines.Notably, full spatiotemporal dynamics yield 7-17% higher alignment than time-averaged supervision across models, and language-window tuning produces larger gains in higher-order language regions, indicating that temporal precision provides additional training value.Moreover, ECoG-tuned models consistently improve or maintain downstream performance.Overall, our work provides initial evidence that electrophysiology is a viable brain-tuning modality, demonstrating how neuroscientific insights into processing hierarchies can inform principled model training strategies.

Voice authentication has been widely used on smartphones. However, it remains vulnerable to spoofing attacks, where the attacker replays recorded voice samples from authentic humans using loudspeakers to bypass the voice authentication system. In this paper, we present MagLive, a robust voice liveness detection scheme designed for smartphones to mitigate such spoofing attacks. MagLive leverages the differences in magnetic pattern changes generated by different speakers (i.e., humans or loudspeakers) when speaking for liveness detection, which are captured by the built-in magnetometer on smartphones. To extract effective and robust magnetic features, MagLive utilizes a TF-CNN-SAF model as the feature extractor, which includes a time-frequency convolutional neural network (TF-CNN) combined with a self-attention-based fusion (SAF) model. Supervised contrastive learning is then employed to achieve user-irrelevance, device-irrelevance, and content-irrelevance. MagLive imposes no additional burden on users and does not rely on active sensing or specialized hardware. We conducted comprehensive experiments with various settings to evaluate the security and robustness of MagLive. Our results demonstrate that MagLive effectively distinguishes between humans and attackers (i.e., loudspeakers), achieving an average balanced accuracy (BAC) of 99.01% and an equal error rate (EER) of 0.77%.

Conversational recommender systems (CRSs) enhance recommendation quality by engaging users in multi-turn dialogues, capturing nuanced preferences through natural language interactions. However, these systems often face the false negative issue, where items that a user might like are incorrectly labeled as negative during training, leading to suboptimal recommendations. Expanding the label set through data augmentation presents an intuitive solution but faces the challenge of balancing two key aspects: ensuring semantic relevance and preserving the collaborative information inherent in CRS datasets. To address these issues, we propose a novel data augmentation framework that first leverages an LLM-based semantic retriever to identify diverse and semantically relevant items, which are then filtered by a relevance scorer to remove noisy candidates. Building on this, we introduce a two-stage training strategy balancing semantic relevance and collaborative information. Extensive experiments on two benchmark datasets and user simulators demonstrate significant and consistent performance improvements across various recommenders, highlighting the effectiveness of our approach in advancing CRS performance.

The interpretability of deep black-box temporal models is crucial in modern machine learning. Identifying crucial time steps and temporal patterns is an important way in understanding how a black-box model makes a decision on a time series instance. Saliency methods are widely used for the interpretation of deep models. However, its application on temporal models faces two challenges: handling temporal relations and the selection of perturbation functions. In order to overcome these challenges, we propose Seasonal-Trend-Remainder Saliency (STR-Saliency), a new interpretation framework which decomposes a time series into three components then generates saliency maps on each component using a learning-based perturbation process. Our new method not only addresses the two issues above, but also produces more human-understandable saliency maps than previous methods. We evaluate our method on both synthetic and real-world datasets and it outperforms various baselines. Our code and detailed results are available at https://github.com/chenrunkai/STRSaliency.

Autonomous Underwater Vehicle (AUV)-assisted Underwater Wireless Sensor Networks (UWSNs) offer transformative potential for data collection, disaster prediction and environmental monitoring. However, these networks remain critically vulnerable to malware attacks due to inherent communication challenges and limited energy resources. To rigorously capture the spatiotemporal dynamics of malware propagation, this paper introduces a novel two-layer heterogeneous model rooted in Partial Differential Equations (PDEs). To suppress malware propagation under limited bandwidth, this paper proposes a spatiotemporal optimal control strategy integrating saturation functions. The existence of the optimal pair is demonstrated by the minimizing sequence method, and the first-order necessary condition for spatiotemporal control is derived based on convex perturbation methods. Further, extensive numerical experiments validate the effectiveness of the proposed two-layer heterogeneous model and spatiotemporal control strategy. Finally, the applications of the proposed model and control strategy in real-world scenarios are discussed.

Internet of Underwater Things (IoUT), widely utilized in data collection, ocean exploration and disaster prevention, are prone to malware attacks. To accurately describe the spatiotemporal dynamics of malware propagation in IoUT, a new Reaction-Diffusion Sleep Control Model (RDSCM) based on Partial Differential Equations (PDEs) is established in this paper. To target heavily infected regions and optimize control costs, a spatiotemporal hybrid optimal control strategy is implemented. First, based on the formulation of the spatiotemporal optimal control problem, the existence, uniqueness, and some estimates of the strong solution of the controlled system are obtained using the truncation method and semigroup theory. Then, the existence of the optimal pair is verified through the minimization sequence technique. Subsequently, the first-order necessary optimality condition for the optimal control problem of PDEs is derived by proving the differentiability of the control-to-state mapping. To validate the effectiveness of the proposed model and control methodology, three comparative experimental studies are conducted. Finally, some discussions are provided on the extension and application of the proposed method.

Recent advances in high-fidelity virtual environments serve as one of the major driving forces for building intelligent embodied agents to perceive, reason and interact with the physical world. Typically, these environments remain unchanged unless agents interact with them. However, in real-world scenarios, agents might also face dynamically changing environments characterized by unexpected events and need to rapidly take action accordingly. To remedy this gap, we propose a new simulated embodied benchmark, called HAZARD, specifically designed to assess the decision-making abilities of embodied agents in dynamic situations. HAZARD consists of three unexpected disaster scenarios, including fire, flood, and wind, and specifically supports the utilization of large language models (LLMs) to assist common sense reasoning and decision-making. This benchmark enables us to evaluate autonomous agents' decision-making capabilities across various pipelines, including reinforcement learning (RL), rule-based, and search-based methods in dynamically changing environments. As a first step toward addressing this challenge using large language models, we further develop an LLM-based agent and perform an in-depth analysis of its promise and challenge of solving these challenging tasks. HAZARD is available at https://vis-www.cs.umass.edu/hazard/.