Interpretable Measurement of CNN Deep Feature Density using Copula and the Generalized Characteristic Function

We present a novel empirical approach toward measuring the Probability Density Function (PDF) of the deep features of Convolutional Neural Networks (CNNs). Measurement of the deep feature PDF is a valuable problem for several reasons. Notably, a. Understanding the deep feature PDF yields new insight into deep representations. b. Feature density methods are important for tasks such as anomaly detection which can improve the robustness of deep learning models in the wild. Interpretable measurement of the deep feature PDF is challenging due to the Curse of Dimensionality (CoD), and the Spatial intuition Limitation. Our novel measurement technique combines copula analysis with the Method of Orthogonal Moments (MOM), in order to directly measure the Generalized Characteristic Function (GCF) of the multivariate deep feature PDF. We find that, surprisingly, the one-dimensional marginals of non-negative deep CNN features after major blocks are not well approximated by a Gaussian distribution, and that these features increasingly approximate an exponential distribution with increasing network depth. Furthermore, we observe that deep features become increasingly independent with increasing network depth within their typical ranges. However, we surprisingly also observe that many deep features exhibit strong dependence (either correlation or anti-correlation) with other extremely strong detections, even if these features are independent within typical ranges. We elaborate on these findings in our discussion, where we propose a new hypothesis that exponentially infrequent large valued features correspond to strong computer vision detections of semantic targets, which would imply that these large-valued features are not outliers but rather an important detection signal.

Every Breath You Don't Take: Deepfake Speech Detection Using Breath

Deepfake speech represents a real and growing threat to systems and society. Many detectors have been created to aid in defense against speech deepfakes. While these detectors implement myriad methodologies, many rely on low-level fragments of the speech generation process. We hypothesize that breath, a higher-level part of speech, is a key component of natural speech and thus improper generation in deepfake speech is a performant discriminator. To evaluate this, we create a breath detector and leverage this against a custom dataset of online news article audio to discriminate between real/deepfake speech. Additionally, we make this custom dataset publicly available to facilitate comparison for future work. Applying our simple breath detector as a deepfake speech discriminator on in-the-wild samples allows for accurate classification (perfect 1.0 AUPRC and 0.0 EER on test data) across 33.6 hours of audio. We compare our model with the state-of-the-art SSL-wav2vec model and show that this complex deep learning model completely fails to classify the same in-the-wild samples (0.72 AUPRC and 0.99 EER).

Parsing Table Structures in the Wild

This paper tackles the problem of table structure parsing (TSP) from images in the wild. In contrast to existing studies that mainly focus on parsing well-aligned tabular images with simple layouts from scanned PDF documents, we aim to establish a practical table structure parsing system for real-world scenarios where tabular input images are taken or scanned with severe deformation, bending or occlusions. For designing such a system, we propose an approach named Cycle-CenterNet on the top of CenterNet with a novel cycle-pairing module to simultaneously detect and group tabular cells into structured tables. In the cycle-pairing module, a new pairing loss function is proposed for the network training. Alongside with our Cycle-CenterNet, we also present a large-scale dataset, named Wired Table in the Wild (WTW), which includes well-annotated structure parsing of multiple style tables in several scenes like the photo, scanning files, web pages, \emph{etc.}. In experiments, we demonstrate that our Cycle-CenterNet consistently achieves the best accuracy of table structure parsing on the new WTW dataset by 24.6\% absolute improvement evaluated by the TEDS metric. A more comprehensive experimental analysis also validates the advantages of our proposed methods for the TSP task.

A Temporal-oriented Broadcast ResNet for COVID-19 Detection

Detecting COVID-19 from audio signals, such as breathing and coughing, can be used as a fast and efficient pre-testing method to reduce the virus transmission. Due to the promising results of deep learning networks in modelling time sequences, and since applications to rapidly identify COVID in-the-wild should require low computational effort, we present a temporal-oriented broadcasting residual learning method that achieves efficient computation and high accuracy with a small model size. Based on the EfficientNet architecture, our novel network, named Temporal-oriented ResNet~(TorNet), constitutes of a broadcasting learning block, i.e. the Alternating Broadcast (AB) Block, which contains several Broadcast Residual Blocks (BC ResBlocks) and a convolution layer. With the AB Block, the network obtains useful audio-temporal features and higher level embeddings effectively with much less computation than Recurrent Neural Networks~(RNNs), typically used to model temporal information. TorNet achieves 72.2% Unweighted Average Recall (UAR) on the INTERPSEECH 2021 Computational Paralinguistics Challenge COVID-19 cough Sub-Challenge, by this showing competitive results with a higher computational efficiency than other state-of-the-art alternatives.

Efficient handover based on Near-field and Far-field RIS for seamless connectivity

Reconfigurable Intelligent Surfaces (RIS) is becoming a transformative technology for the upcoming 6G communication networks, providing a way for smartly maneuvering the electromagnetic waves to enhance coverage and connectivity. This paper presents an efficient handover (HO) management scheme leveraging RIS in the Fresnel region i.e., in both the near-field (NF) and far-field (FF) regions to reduce signaling overhead and optimize mobility management. For this, we analyzed the signal strength variations in the considered RIS-aided networks, considering the radiative NF and FF regions, and derive the probability density function (PDF) of the RIS-UE distance in the NF region to quantify RIS reflection gains along the user equipment (UE) trajectory. We propose a new HO algorithm incorporating several HO categories like hard handover (HHO), soft handover (SHO), RIS-aided cell breathing (RIS-CB), and RIS-aided ping-pong avoidance (RIS-PP) strategies. The proposed algorithm uses bit error rate (BER) as a key parameter to predict the minimization of unnecessary HOs by using RIS-aided pathways to retain connectivity with the serving base station (BS), which minimizes the requirement for frequent target BS searching and ultimately optimizes the HO. By restricting measurement reports and HO requests, the suggested method improves spectrum efficiency (SE) and energy efficiency (EE), especially in crowded cellular networks. Numerical results highlight significant reductions in HO rates and signaling load, ensuring seamless connectivity and improved quality of service (QoS) in 6G systems.

CSI-Bench: A Large-Scale In-the-Wild Dataset for Multi-task WiFi Sensing

WiFi sensing has emerged as a compelling contactless modality for human activity monitoring by capturing fine-grained variations in Channel State Information (CSI). Its ability to operate continuously and non-intrusively while preserving user privacy makes it particularly suitable for health monitoring. However, existing WiFi sensing systems struggle to generalize in real-world settings, largely due to datasets collected in controlled environments with homogeneous hardware and fragmented, session-based recordings that fail to reflect continuous daily activity. We present CSI-Bench, a large-scale, in-the-wild benchmark dataset collected using commercial WiFi edge devices across 26 diverse indoor environments with 35 real users. Spanning over 461 hours of effective data, CSI-Bench captures realistic signal variability under natural conditions. It includes task-specific datasets for fall detection, breathing monitoring, localization, and motion source recognition, as well as a co-labeled multitask dataset with joint annotations for user identity, activity, and proximity. To support the development of robust and generalizable models, CSI-Bench provides standardized evaluation splits and baseline results for both single-task and multi-task learning. CSI-Bench offers a foundation for scalable, privacy-preserving WiFi sensing systems in health and broader human-centric applications.

Capturing Logical Structure of Visually Structured Documents with Multimodal Transition Parser

While many NLP papers, tasks and pipelines assume raw, clean texts, many texts we encounter in the wild are not so clean, with many of them being visually structured documents (VSDs) such as PDFs. Conventional preprocessing tools for VSDs mainly focused on word segmentation and coarse layout analysis, while fine-grained logical structure analysis (such as identifying paragraph boundaries and their hierarchies) of VSDs is underexplored. To that end, we proposed to formulate the task as prediction of transition labels between text fragments that maps the fragments to a tree, and developed a feature-based machine learning system that fuses visual, textual and semantic cues. Our system significantly outperformed baselines in identifying different structures in VSDs. For example, our system obtained a paragraph boundary detection F1 score of 0.951 which is significantly better than a popular PDF-to-text tool with a F1 score of 0.739.

ActiveUMI: Robotic Manipulation with Active Perception from Robot-Free Human Demonstrations

We present ActiveUMI, a framework for a data collection system that transfers in-the-wild human demonstrations to robots capable of complex bimanual manipulation. ActiveUMI couples a portable VR teleoperation kit with sensorized controllers that mirror the robot's end-effectors, bridging human-robot kinematics via precise pose alignment. To ensure mobility and data quality, we introduce several key techniques, including immersive 3D model rendering, a self-contained wearable computer, and efficient calibration methods. ActiveUMI's defining feature is its capture of active, egocentric perception. By recording an operator's deliberate head movements via a head-mounted display, our system learns the crucial link between visual attention and manipulation. We evaluate ActiveUMI on six challenging bimanual tasks. Policies trained exclusively on ActiveUMI data achieve an average success rate of 70\% on in-distribution tasks and demonstrate strong generalization, retaining a 56\% success rate when tested on novel objects and in new environments. Our results demonstrate that portable data collection systems, when coupled with learned active perception, provide an effective and scalable pathway toward creating generalizable and highly capable real-world robot policies.

A Comparison of Independent and Joint Fine-tuning Strategies for Retrieval-Augmented Generation

A Comparison of Independent and Joint Fine-tuning Strategies for Retrieval-Augmented Generation Download PDF Neal Gregory Lawton, Alfy Samuel, Anoop Kumar, Daben Liu Published: 20 Aug 2025, Last Modified: 17 Sept 2025EMNLP 2025 FindingsConference, Publication Chairs, AuthorsRevisionsBibTeXCC BY 4.0 Keywords: Retrieval-Augmented Generation (RAG), Large Language Models (LLMs), Fine-tuning, Question Answering, Joint fine-tuning TL;DR: We evaluate and compare strategies for fine-tuning Retrieval Augmented Generation (RAG) pipelines, including independent fine-tuning, joint fine-tuning, and two-phase fine-tuning. Abstract: Retrieval augmented generation (RAG) is a popular framework for question answering that is powered by two large language models (LLMs): an embedding model that retrieves context documents from a database that are relevant to a given question, and a generator model that uses the retrieved context to generate an answer to the question. Both the embedding and generator models can be fine-tuned to increase performance of a RAG pipeline on a new task, but multiple fine-tuning strategies exist with different costs and benefits. In this paper, we evaluate and compare several RAG fine-tuning strategies, including independent, joint, and two-phase fine-tuning. In our experiments, we observe that all of these strategies achieve about equal improvement in EM and F1 generation quality metrics, although they have significantly different computational costs. We conclude the optimal fine-tuning strategy to use depends on whether the training dataset includes context labels and whether a grid search over the learning rates for the embedding and generator models is required.

MMDEW: Multipurpose Multiclass Density Estimation in the Wild

Density map estimation can be used to estimate object counts in dense and occluded scenes where discrete counting-by-detection methods fail. We propose a multicategory counting framework that leverages a Twins pyramid vision-transformer backbone and a specialised multi-class counting head built on a state-of-the-art multiscale decoding approach. A two-task design adds a segmentation-based Category Focus Module, suppressing inter-category cross-talk at training time. Training and evaluation on the VisDrone and iSAID benchmarks demonstrates superior performance versus prior multicategory crowd-counting approaches (33%, 43% and 64% reduction to MAE), and the comparison with YOLOv11 underscores the necessity of crowd counting methods in dense scenes. The method's regional loss opens up multi-class crowd counting to new domains, demonstrated through the application to a biodiversity monitoring dataset, highlighting its capacity to inform conservation efforts and enable scalable ecological insights.