Audio Spatially-Guided Fusion for Audio-Visual Navigation

Audio-visual Navigation refers to an agent utilizing visual and auditory information in complex 3D environments to accomplish target localization and path planning, thereby achieving autonomous navigation. The core challenge of this task lies in the following: how the agent can break free from the dependence on training data and achieve autonomous navigation with good generalization performance when facing changes in environments and sound sources. To address this challenge, we propose an Audio Spatially-Guided Fusion for Audio-Visual Navigation method. First, we design an audio spatial feature encoder, which adaptively extracts target-related spatial state information through an audio intensity attention mechanism; based on this, we introduce an Audio Spatial State Guided Fusion (ASGF) to achieve dynamic alignment and adaptive fusion of multimodal features, effectively alleviating noise interference caused by perceptual uncertainty. Experimental results on the Replica and Matterport3D datasets indicate that our method is particularly effective on unheard tasks, demonstrating improved generalization under unknown sound source distributions.

Offline RL for Adaptive Policy Retrieval in Prior Authorization

Prior authorization (PA) requires interpretation of complex and fragmented coverage policies, yet existing retrieval-augmented systems rely on static top-$K$ strategies with fixed numbers of retrieved sections. Such fixed retrieval can be inefficient and gather irrelevant or insufficient information. We model policy retrieval for PA as a sequential decision-making problem, formulating adaptive retrieval as a Markov Decision Process (MDP). In our system, an agent iteratively selects policy chunks from a top-$K$ candidate set or chooses to stop and issue a decision. The reward balances decision correctness against retrieval cost, capturing the trade-off between accuracy and efficiency. We train policies using Conservative Q-Learning (CQL), Implicit Q-Learning (IQL), and Direct Preference Optimization (DPO) in an offline RL setting on logged trajectories generated from baseline retrieval strategies over synthetic PA requests derived from publicly available CMS coverage data. On a corpus of 186 policy chunks spanning 10 CMS procedures, CQL achieves 92% decision accuracy (+30 percentage points over the best fixed-$K$ baseline) via exhaustive retrieval, while IQL matches the best baseline accuracy using 44% fewer retrieval steps and achieves the only positive episodic return among all policies. Transition-level DPO matches CQL's 92% accuracy while using 47% fewer retrieval steps (10.6 vs. 20.0), occupying a "selective-accurate" region on the Pareto frontier that dominates both CQL and BC. A behavioral cloning baseline matches CQL, confirming that advantage-weighted or preference-based policy extraction is needed to learn selective retrieval. Lambda ablation over step costs $λ\in \{0.05, 0.1, 0.2\}$ reveals a clear accuracy-efficiency inflection: only at $λ= 0.2$ does CQL transition from exhaustive to selective retrieval.

Semantic Sensing: A Task-Oriented Paradigm

Sensing and communication are fundamental enablers of next-generation networks. While communication technologies have advanced significantly, sensing remains limited to conventional parameter estimation and is far from fully explored. Motivated by these limitations, we propose semantic sensing (SemS), a novel framework that shifts the design objective from reconstruction fidelity to semantic effective recognition. Specifically, we mathematically formulate the interaction between transmit waveforms and semantic entities, thereby establishing SemS as a semantics-oriented transceiver design. Within this architecture, we leverage the information bottleneck (IB) principle as a theoretical criterion to derive a unified objective, guiding the sensing pipeline to maximize task-relevant information extraction. To practically solve this optimization problem, we develop a deep learning (DL)-based framework that jointly designs transmit waveform parameters and receiver representations. The framework is implemented in an orthogonal frequency division multiplexing (OFDM) system, featuring a shared semantic encoder that employs a Gumbel-Softmax-based pilot selector to discretely mask task-irrelevant resources. At the receiver, we design distinct decoding architectures tailored to specific sensing objectives, comprising a 2D residual network (ResNet)-based classifier for target recognition and a correlation-driven 1D regression network for high-precision delay estimation. Numerical results demonstrate that the proposed semantic pilot design achieves superior classification accuracy and ranging precision compared to reconstruction-based baselines, particularly under constrained resource budgets.

JaWildText: A Benchmark for Vision-Language Models on Japanese Scene Text Understanding

Japanese scene text poses challenges that multilingual benchmarks often fail to capture, including mixed scripts, frequent vertical writing, and a character inventory far larger than the Latin alphabet. Although Japanese is included in several multilingual benchmarks, these resources do not adequately capture the language-specific complexities. Meanwhile, existing Japanese visual text datasets have primarily focused on scanned documents, leaving in-the-wild scene text underexplored. To fill this gap, we introduce JaWildText, a diagnostic benchmark for evaluating vision-language models (VLMs) on Japanese scene text understanding. JaWildText contains 3,241 instances from 2,961 images newly captured in Japan, with 1.12 million annotated characters spanning 3,643 unique character types. It comprises three complementary tasks that vary in visual organization, output format, and writing style: (i) Dense Scene Text Visual Question Answering (STVQA), which requires reasoning over multiple pieces of visual text evidence; (ii) Receipt Key Information Extraction (KIE), which tests layout-aware structured extraction from mobile-captured receipts; and (iii) Handwriting OCR, which evaluates page-level transcription across various media and writing directions. We evaluate 14 open-weight VLMs and find that the best model achieves an average score of 0.64 across the three tasks. Error analyses show recognition remains the dominant bottleneck, especially for kanji. JaWildText enables fine-grained, script-aware diagnosis of Japanese scene text capabilities, and will be released with evaluation code.

Generation, Annihilation and Flow of Structural Information in Ultrasonic Nondestructive Evaluation

Non-destructive testing using ultrasound is based on the interaction of sound waves with the object being tested and any defects it may contain. The aim is to extract as much information as possible about the object and its defects from the scattered wave field. In this paper, the concept of information in the context of ultrasonic testing is formalized and quantified physically for the first time. To this end, a balance equation for information is derived, analogous to Poynting's theorem for elastic energy. Various examples demonstrate how structural information is generated and annihilated within a component and along which pathways it travels from the defect to the sensor. Subsequently, the significance and potential of this new information concept for practical ultrasonic testing, structural health monitoring, numerical simulation, and machine learning are discussed. Finally, similarities and differences to mathematical Shannon information and statistical Fisher information are highlighted.

SBF: An Effective Representation to Augment Skeleton for Video-based Human Action Recognition

Many modern video-based human action recognition (HAR) approaches use 2D skeleton as the intermediate representation in their prediction pipelines. Despite overall encouraging results, these approaches still struggle in many common scenes, mainly because the skeleton does not capture critical action-related information pertaining to the depth of the joints, contour of the human body, and interaction between the human and objects. To address this, we propose an effective approach to augment skeleton with a representation capturing action-related information in the pipeline of HAR. The representation, termed Scale-Body-Flow (SBF), consists of three distinct components, namely a scale map volume given by the scale (and hence depth information) of each joint, a body map outlining the human subject, and a flow map indicating human-object interaction given by pixel-wise optical flow values. To predict SBF, we further present SFSNet, a novel segmentation network supervised by the skeleton and optical flow without extra annotation overhead beyond the existing skeleton extraction. Extensive experiments across different datasets demonstrate that our pipeline based on SBF and SFSNet achieves significantly higher HAR accuracy with similar compactness and efficiency as compared with the state-of-the-art skeleton-only approaches.

Reducing Hallucinations in LLM-based Scientific Literature Analysis Using Peer Context Outlier Detection

Reducing hallucinations in Large Language Models (LLMs) is essential for improving the accuracy of data extraction from large text corpora. Current methods, like prompt engineering and chain-of-thought prompting, focus on individual documents but fail to consider relationships across a corpus. This paper introduces Peer Context Outlier Detection (P-COD), a novel approach that uses the relationships between documents to improve extraction accuracy. Our application domain is in scientific literature summarization, where papers with similar experiment settings should draw similar conclusions. By comparing extracted data to validated peer information within the corpus, we adjust confidence scores and flag low-confidence results for expert review. High-confidence results, supported by peer validation, are considered reliable. Our experiments demonstrate up to 98% precision in outlier detection across 6 domains of science, demonstrating that our design reduces hallucinations, enhances trust in automated systems, and allows researchers to focus on ambiguous cases, streamlining the data extraction workflows.

Rich-U-Net: A medical image segmentation model for fusing spatial depth features and capturing minute structural details

Medical image segmentation is of great significance in analysis of illness. The use of deep neural networks in medical image segmentation can help doctors extract regions of interest from complex medical images, thereby improving diagnostic accuracy and enabling better assessment of the condition to formulate treatment plans. However, most current medical image segmentation methods underperform in accurately extracting spatial information from medical images and mining potential complex structures and variations. In this article, we introduce the Rich-U-Net model, which effectively integrates both spatial and depth features. This fusion enhances the model's capability to detect fine structures and intricate details within complex medical images. Our multi-level and multi-dimensional feature fusion and optimization strategies enable our model to achieve fine structure localization and accurate segmentation results in medical image segmentation. Experiments on the ISIC2018, BUSI, GLAS, and CVC datasets show that Rich-U-Net surpasses other state-of-the-art models in Dice, IoU, and HD95 metrics.

Automated Framework to Evaluate and Harden LLM System Instructions against Encoding Attacks

System Instructions in Large Language Models (LLMs) are commonly used to enforce safety policies, define agent behavior, and protect sensitive operational context in agentic AI applications. These instructions may contain sensitive information such as API credentials, internal policies, and privileged workflow definitions, making system instruction leakage a critical security risk highlighted in the OWASP Top 10 for LLM Applications. Without incurring the overhead costs of reasoning models, many LLM applications rely on refusal-based instructions that block direct requests for system instructions, implicitly assuming that prohibited information can only be extracted through explicit queries. We introduce an automated evaluation framework that tests whether system instructions remain confidential when extraction requests are re-framed as encoding or structured output tasks. Across four common models and 46 verified system instructions, we observe high attack success rates (> 0.7) for structured serialization where models refuse direct extraction requests but disclose protected content in the requested serialization formats. We further demonstrate a mitigation strategy based on one-shot instruction reshaping using a Chain-of-Thought reasoning model, indicating that even subtle changes in wording and structure of system instructions can significantly reduce attack success rate without requiring model retraining.

Out-of-Air Computation: Enabling Structured Extraction from Wireless Superposition

Over-the-air computation (AirComp) has traditionally been built on the principle of pre-embedding computation into transmitted waveforms or on exploiting massive antenna arrays, often requiring the wireless multiple-access channel (MAC) to operate under conditions that approximate an ideal computational medium. This paper introduces a new computation framework, termed out-of-air computation (AirCPU), which establishes a joint source-channel coding foundation in which computation is not embedded before transmission but is instead extracted from the wireless superposition by exploiting structured coding. AirCPU operates directly on continuous-valued device data, avoiding the need for a separate source quantization stage, and employs a multi-layer nested lattice architecture that enables progressive resolution by decomposing each input into hierarchically scaled components, all transmitted over a common bounded digital constellation under a fixed power constraint. We formalize the notion of decoupled resolution, showing that in operating regimes where the decoding error probability is sufficiently small, the impact of channel noise and finite constellation constraints on distortion becomes negligible, and the resulting computation error is primarily determined by the target resolution set by the finest lattice. For fading MACs, we further introduce collective and successive computation mechanisms, in addition to the proposed direct computation, which exploit multiple decoded integer-coefficient functions and side-information functions as structural representations of the wireless superposition to significantly expand the reliable operating regime; in this context, we formulate and characterize the underlying reliability conditions and integer optimization problems, and develop a structured low-complexity two-group approximation to address them.