We thank the reviewers for their thoughtful and constructive feedback on our manuscript. This should help both contextualize each task's difficulty and illustrate what it involves. Reviewer 3 noted the Section 2 task descriptions could be better presented. We have reformatted it so that "the order We also changed our description of IMP ALA to match Reviewer 5's suggestion. Regarding the task suite, Reviewer 4 raised a thoughtful consideration on whether "most of the findings translate when Some 3D tasks in the suite already have '2D-like' semi-counterparts that do not require navigation, '2D-like' because everything is fully observable and the agent has a first-person point of view from a fixed point, without Spot the Difference level, was overall harder than Change Detection for our ablation models.

We thank the reviewers for their thoughtful and constructive feedback on our manuscript. This should help both contextualize each task's difficulty and illustrate what it involves. Reviewer 3 noted the Section 2 task descriptions could be better presented. We have reformatted it so that "the order We also changed our description of IMP ALA to match Reviewer 5's suggestion. Regarding the task suite, Reviewer 4 raised a thoughtful consideration on whether "most of the findings translate when Some 3D tasks in the suite already have '2D-like' semi-counterparts that do not require navigation, '2D-like' because everything is fully observable and the agent has a first-person point of view from a fixed point, without Spot the Difference level, was overall harder than Change Detection for our ablation models.

While existing benchmarks probe the reasoning abilities of large language models (LLMs) across diverse domains, they predominantly assess passive reasoning, providing models with all the information needed to reach a solution. By contrast, active reasoning-where an LLM must interact with external systems to acquire missing evidence or data-has received little systematic attention. To address this shortfall, we present AR-Bench, a novel benchmark designed explicitly to evaluate an LLM's active reasoning skills. AR-Bench comprises three task families-detective cases, situation puzzles, and guessing numbers-that together simulate real-world, agentic scenarios and measure performance across commonsense, logical, and symbolic reasoning challenges. Empirical evaluation on AR-Bench demonstrates that contemporary LLMs exhibit pronounced difficulties with active reasoning: they frequently fail to acquire or leverage the information needed to solve tasks. This gap highlights a stark divergence between their passive and active reasoning abilities. Moreover, ablation studies indicate that even advanced strategies, such as tree-based searching or post-training approaches, yield only modest gains and fall short of the levels required for real-world deployment. Collectively, these findings highlight the critical need to advance methodology for active reasoning, e.g., incorporating interactive learning, real-time feedback loops, and environment-aware objectives for training. The benchmark is publicly available at: https://github.com/tmlr-group/AR-Bench.

Considering the attacks against the power grid, one of the most effective approaches could be the attack to the transmission lines that leads to large cascading failures. Hence, the problem of locating the most critical or vulnerable transmission lines for a Power Grid Cascading Failure (PGCF) has drawn much attention from the research society. There exists many deterministic solutions and stochastic approximation algorithms aiming to analyze the power grid vulnerability. However, it has been challenging to reveal the correlations between the transmission lines to identify the critical ones. In this paper, we propose a novel approach of learning such correlations via attention mechanism inspired by the Transformer based models that were initially designated to learn the correlation of words in sentences. Multiple modifications and adjustments are proposed to support the attention mechanism producing an informative correlation matrix, the Attention Matrix. With the Attention Ranking algorithm, we are able to identify the most critical lines. The proposed Dual PGCF model provide a novel and effective analysis to improve the power grid resilience against cascading failure, which is proved by extensive experiment results.

How does the brain represent different modes of information? Can we design a system that automatically understands what the user is thinking? Such questions can be answered by studying brain recordings like functional magnetic resonance imaging (fMRI). As a first step, the neuroscience community has contributed several large cognitive neuroscience datasets related to passive reading/listening/viewing of concept words, narratives, pictures and movies. Encoding and decoding models using these datasets have also been proposed in the past two decades. These models serve as additional tools for basic research in cognitive science and neuroscience. Encoding models aim at generating fMRI brain representations given a stimulus automatically. They have several practical applications in evaluating and diagnosing neurological conditions and thus also help design therapies for brain damage. Decoding models solve the inverse problem of reconstructing the stimuli given the fMRI. They are useful for designing brain-machine or brain-computer interfaces. Inspired by the effectiveness of deep learning models for natural language processing, computer vision, and speech, recently several neural encoding and decoding models have been proposed. In this survey, we will first discuss popular representations of language, vision and speech stimuli, and present a summary of neuroscience datasets. Further, we will review popular deep learning based encoding and decoding architectures and note their benefits and limitations. Finally, we will conclude with a brief summary and discussion about future trends. Given the large amount of recently published work in the `computational cognitive neuroscience' community, we believe that this survey nicely organizes the plethora of work and presents it as a coherent story.

Recent advances in wireless communication with the enormous demands of sensing ability have given rise to the integrated sensing and communication (ISAC) technology, among which passive sensing plays an important role. The main challenge of passive sensing is how to achieve high sensing performance in the condition of communication demodulation errors. In this paper, we propose an ISAC network (ISAC-NET) that combines passive sensing with communication signal detection by using model-driven deep learning (DL). Dissimilar to existing passive sensing algorithms that first demodulate the transmitted symbols and then obtain passive sensing results from the demodulated symbols, ISAC-NET obtains passive sensing results and communication demodulated symbols simultaneously. Different from the data-driven DL method, we adopt the block-by-block signal processing method that divides the ISAC-NET into the passive sensing module, signal detection module and channel reconstruction module. From the simulation results, ISAC-NET obtains better communication performance than the traditional signal demodulation algorithm, which is close to OAMP-Net2. Compared to the 2D-DFT algorithm, ISAC-NET demonstrates significantly enhanced sensing performance. In summary, ISAC-NET is a promising tool for passive sensing and communication in wireless communications. This work is supported in part by the National Key Research and Development Program under Grant 2020YFA0711302, and in part by the BUPT Excellent Ph.D. Students Foundation under Grant CX2022207. Zhang is with the School of Information and Communication Engineering, Beijing University of Posts and Telecommunications, and also with the State Key Laboratory of Networking and Switching Technology, Beijing 100876, China (email: pzhang@bupt.edu.cn).

Passive speakers are the easiest to understand--they're the speakers we all grew up with, and they're the speakers you need to complete a traditional audio system. They have no power supply of their own and need to receive an amplified electrical signal in order to function. So you don't plug them into the mains--instead, you wire them to an amplifier that provides the electrical impetus they need to create sound. Bluetooth, as you know, is a method of wirelessly streaming audio information--so a Bluetooth speaker has its own power supply (from the mains or batteries) and amplification, and once it receives a Bluetooth signal it can decode it and turn it into sound. A wireless speaker has its own source of power and its own amplification--and there's every chance it will be able to deal with a Bluetooth signal. But in addition, it can deal with audio information using a Wi-Fi network or cloud storage--so if you subscribe to a streaming service, its cloud-based service (such as Spotify Connect) is available without the need for a Bluetooth connection.

Recognizing facial activity is a well-understood (but non-trivial) computer vision problem. However, reliable solutions require a camera with a good view of the face, which is often unavailable in wearable settings. Furthermore, in wearable applications, where systems accompany users throughout their daily activities, a permanently running camera can be problematic for privacy (and legal) reasons. This work presents an alternative solution based on the fusion of wearable inertial sensors, planar pressure sensors, and acoustic mechanomyography (muscle sounds). The sensors were placed unobtrusively in a sports cap to monitor facial muscle activities related to facial expressions. We present our integrated wearable sensor system, describe data fusion and analysis methods, and evaluate the system in an experiment with thirteen subjects from different cultural backgrounds (eight countries) and both sexes (six women and seven men). In a one-model-per-user scheme and using a late fusion approach, the system yielded an average F1 score of 85.00% for the case where all sensing modalities are combined. With a cross-user validation and a one-model-for-all-user scheme, an F1 score of 79.00% was obtained for thirteen participants (six females and seven males). Moreover, in a hybrid fusion (cross-user) approach and six classes, an average F1 score of 82.00% was obtained for eight users. The results are competitive with state-of-the-art non-camera-based solutions for a cross-user study. In addition, our unique set of participants demonstrates the inclusiveness and generalizability of the approach.

Text style transfer aims to controllably generate text with targeted stylistic changes while maintaining core meaning from the source sentence constant. Many of the existing style transfer benchmarks primarily focus on individual high-level semantic changes (e.g. positive to negative), which enable controllability at a high level but do not offer fine-grained control involving sentence structure, emphasis, and content of the sentence. In this paper, we introduce a large-scale benchmark, StylePTB, with (1) paired sentences undergoing 21 fine-grained stylistic changes spanning atomic lexical, syntactic, semantic, and thematic transfers of text, as well as (2) compositions of multiple transfers which allow modeling of fine-grained stylistic changes as building blocks for more complex, high-level transfers. By benchmarking existing methods on StylePTB, we find that they struggle to model fine-grained changes and have an even more difficult time composing multiple styles. As a result, StylePTB brings novel challenges that we hope will encourage future research in controllable text style transfer, compositional models, and learning disentangled representations. Solving these challenges would present important steps towards controllable text generation.

Robust loss functions are essential for training accurate deep neural networks (DNNs) in the presence of noisy (incorrect) labels. It has been shown that the commonly used Cross Entropy (CE) loss is not robust to noisy labels. Whilst new loss functions have been designed, they are only partially robust. In this paper, we theoretically show by applying a simple normalization that: any loss can be made robust to noisy labels. However, in practice, simply being robust is not sufficient for a loss function to train accurate DNNs. By investigating several robust loss functions, we find that they suffer from a problem of underfitting. To address this, we propose a framework to build robust loss functions called Active Passive Loss (APL). APL combines two robust loss functions that mutually boost each other. Experiments on benchmark datasets demonstrate that the family of new loss functions created by our APL framework can consistently outperform state-of-the-art methods by large margins, especially under large noise rates such as 60% or 80% incorrect labels.