Individuals with tetraplegia and similar forms of paralysis suffer physically and emotionally due to a lack of autonomy. To help regain part of this autonomy, assistive robotic arms have been shown to increase living independence. However, users with paralysis pose unique challenging conditions for the control of these devices. In this article, we present the use of Diegetic Graphical User Interfaces, a novel, intuitive, and computationally inexpensive approach for gaze-controlled interfaces applied to robots. By using symbols paired with fiducial markers, interactive buttons can be defined in the real world which the user can trigger via gaze, and which can be embedded easily into the environment. We apply this system to pilot a 3-degree-of-freedom robotic arm for precision pick-and-place tasks. The interface is placed directly on the robot to allow intuitive and direct interaction, eliminating the need for context-switching between external screens, menus, and the robot. After calibration and a brief habituation period, twenty-one participants from multiple backgrounds, ages and eye-sight conditions completed the Yale-CMU-Berkeley (YCB) Block Pick and Place Protocol to benchmark the system, achieving a mean score of 13.71 out of the maximum 16.00 points. Good usability and user experience were reported (System Usability Score of 75.36) while achieving a low task workload measure (NASA-TLX of 44.76). Results show that users can employ multiple interface elements to perform actions with minimal practice and with a small cognitive load. To our knowledge, this is the first easily reconfigurable screenless system that enables robot control entirely via gaze for Cartesian robot control without the need for eye or face gestures.

Video Text Spotting (VTS) is a fundamental visual task that aims to predict the trajectories and content of texts in a video. Previous works usually conduct local associations and apply IoU-based distance and complex post-processing procedures to boost performance, ignoring the abundant temporal information and the morphological characteristics in VTS. In this paper, we propose a novel Global Video Text Spotting Transformer GloTSFormer to model the tracking problem as global associations and utilize the Gaussian Wasserstein distance to guide the morphological correlation between frames. Our main contributions can be summarized as three folds. 1). We propose a Transformer-based global tracking method GloTSFormer for VTS and associate multiple frames simultaneously. 2). We introduce a Wasserstein distance-based method to conduct positional associations between frames. 3). We conduct extensive experiments on public datasets. On the ICDAR2015 video dataset, GloTSFormer achieves 56.0 MOTA with 4.6 absolute improvement compared with the previous SOTA method and outperforms the previous Transformer-based method by a significant 8.3 MOTA.

Educators are increasingly concerned about the usage of Large Language Models (LLMs) such as ChatGPT in programming education, particularly regarding the potential exploitation of imperfections in Artificial Intelligence Generated Content (AIGC) Detectors for academic misconduct. In this paper, we present an empirical study where the LLM is examined for its attempts to bypass detection by AIGC Detectors. This is achieved by generating code in response to a given question using different variants. We collected a dataset comprising 5,069 samples, with each sample consisting of a textual description of a coding problem and its corresponding human-written Python solution codes. These samples were obtained from various sources, including 80 from Quescol, 3,264 from Kaggle, and 1,725 from LeetCode. From the dataset, we created 13 sets of code problem variant prompts, which were used to instruct ChatGPT to generate the outputs. Subsequently, we assessed the performance of five AIGC detectors. Our results demonstrate that existing AIGC Detectors perform poorly in distinguishing between human-written code and AI-generated code.

The understanding of the convoluted evolution of infant brain networks during the first postnatal year is pivotal for identifying the dynamics of early brain connectivity development. Existing deep learning solutions suffer from three major limitations. First, they cannot generalize to multi-trajectory prediction tasks, where each graph trajectory corresponds to a particular imaging modality or connectivity type (e.g., T1-w MRI). Second, existing models require extensive training datasets to achieve satisfactory performance which are often challenging to obtain. Third, they do not efficiently utilize incomplete time series data. To address these limitations, we introduce FedGmTE-Net++, a federated graph-based multi-trajectory evolution network. Using the power of federation, we aggregate local learnings among diverse hospitals with limited datasets. As a result, we enhance the performance of each hospital's local generative model, while preserving data privacy. The three key innovations of FedGmTE-Net++ are: (i) presenting the first federated learning framework specifically designed for brain multi-trajectory evolution prediction in a data-scarce environment, (ii) incorporating an auxiliary regularizer in the local objective function to exploit all the longitudinal brain connectivity within the evolution trajectory and maximize data utilization, (iii) introducing a two-step imputation process, comprising a preliminary KNN-based precompletion followed by an imputation refinement step that employs regressors to improve similarity scores and refine imputations. Our comprehensive experimental results showed the outperformance of FedGmTE-Net++ in brain multi-trajectory prediction from a single baseline graph in comparison with benchmark methods.

Camera traps are valuable tools in animal ecology for biodiversity monitoring and conservation. However, challenges like poor generalization to deployment at new unseen locations limit their practical application. Images are naturally associated with heterogeneous forms of context possibly in different modalities. In this work, we leverage the structured context associated with the camera trap images to improve out-of-distribution generalization for the task of species identification in camera traps. For example, a photo of a wild animal may be associated with information about where and when it was taken, as well as structured biology knowledge about the animal species. While typically overlooked by existing work, bringing back such context offers several potential benefits for better image understanding, such as addressing data scarcity and enhancing generalization. However, effectively integrating such heterogeneous context into the visual domain is a challenging problem. To address this, we propose a novel framework that reformulates species classification as link prediction in a multimodal knowledge graph (KG). This framework seamlessly integrates various forms of multimodal context for visual recognition. We apply this framework for out-of-distribution species classification on the iWildCam2020-WILDS and Snapshot Mountain Zebra datasets and achieve competitive performance with state-of-the-art approaches. Furthermore, our framework successfully incorporates biological taxonomy for improved generalization and enhances sample efficiency for recognizing under-represented species.

Deep Gradient Leakage (DGL) is a highly effective attack that recovers private training images from gradient vectors. This attack casts significant privacy challenges on distributed learning from clients with sensitive data, where clients are required to share gradients. Defending against such attacks requires but lacks an understanding of when and how privacy leakage happens, mostly because of the black-box nature of deep networks. In this paper, we propose a novel Inversion Influence Function (I$^2$F) that establishes a closed-form connection between the recovered images and the private gradients by implicitly solving the DGL problem. Compared to directly solving DGL, I$^2$F is scalable for analyzing deep networks, requiring only oracle access to gradients and Jacobian-vector products. We empirically demonstrate that I$^2$F effectively approximated the DGL generally on different model architectures, datasets, modalities, attack implementations, and perturbation-based defenses. With this novel tool, we provide insights into effective gradient perturbation directions, the unfairness of privacy protection, and privacy-preferred model initialization. Our codes are provided in https://github.com/illidanlab/inversion-influence-function.

We address the challenge of ensuring differential privacy (DP) guarantees in training deep retrieval systems. Training these systems often involves the use of contrastive-style losses, which are typically non-per-example decomposable, making them difficult to directly DP-train with since common techniques require per-example gradient. To address this issue, we propose an approach that prioritizes ensuring query privacy prior to training a deep retrieval system. Our method employs DP language models (LMs) to generate private synthetic queries representative of the original data. These synthetic queries can be used in downstream retrieval system training without compromising privacy. Our approach demonstrates a significant enhancement in retrieval quality compared to direct DP-training, all while maintaining query-level privacy guarantees. This work highlights the potential of harnessing LMs to overcome limitations in standard DP-training methods.

Lately, propelled by the phenomenal advances around the transformer architecture, the legal NLP field has enjoyed spectacular growth. To measure progress, well curated and challenging benchmarks are crucial. However, most benchmarks are English only and in legal NLP specifically there is no multilingual benchmark available yet. Additionally, many benchmarks are saturated, with the best models clearly outperforming the best humans and achieving near perfect scores. We survey the legal NLP literature and select 11 datasets covering 24 languages, creating LEXTREME. To provide a fair comparison, we propose two aggregate scores, one based on the datasets and one on the languages. The best baseline (XLM-R large) achieves both a dataset aggregate score a language aggregate score of 61.3. This indicates that LEXTREME is still very challenging and leaves ample room for improvement. To make it easy for researchers and practitioners to use, we release LEXTREME on huggingface together with all the code required to evaluate models and a public Weights and Biases project with all the runs.

While recent research advances in speaker diarization mostly focus on improving the quality of diarization results, there is also an increasing interest in improving the efficiency of diarization systems. In this paper, we demonstrate that a multi-stage clustering strategy that uses different clustering algorithms for input of different lengths can address multi-faceted challenges of on-device speaker diarization applications. Specifically, a fallback clusterer is used to handle short-form inputs; a main clusterer is used to handle medium-length inputs; and a pre-clusterer is used to compress long-form inputs before they are processed by the main clusterer. Both the main clusterer and the pre-clusterer can be configured with an upper bound of the computational complexity to adapt to devices with different resource constraints. This multi-stage clustering strategy is critical for streaming on-device speaker diarization systems, where the budgets of CPU, memory and battery are tight.

In this paper, we present a Computer Vision (CV) based tracking and fusion algorithm, dedicated to a 3D printed gimbal system on drones operating in nature. The whole gimbal system can stabilize the camera orientation robustly in a challenging nature scenario by using skyline and ground plane as references. Our main contributions are the following: a) a light-weight Resnet-18 backbone network model was trained from scratch, and deployed onto the Jetson Nano platform to segment the image into binary parts (ground and sky); b) our geometry assumption from nature cues delivers the potential for robust visual tracking by using the skyline and ground plane as a reference; c) a spherical surface-based adaptive particle sampling, can fuse orientation from multiple sensor sources flexibly. The whole algorithm pipeline is tested on our customized gimbal module including Jetson and other hardware components. The experiments were performed on top of a building in the real landscape.