Amateur and professional astronomers can easily capture a large number of deep sky images with recent smart telescopes. However, afterwards verification is still required to check whether the celestial objects targeted are actually visible in the images produced. Depending on the magnitude of the targets, the observation conditions and the time during which the data is captured, it is possible that only stars are present in the images. In this study, we propose an approach based on explainable Artificial Intelligence to automatically detect the presence and position of captured objects. -- -- Gr\^ace \`a l'apport des t\'elescopes automatis\'es grand public, les astronomes amateurs et professionnels peuvent capturer facilement une grande quantit\'e d'images du ciel profond (comme par exemple les galaxies, n\'ebuleuses, ou amas globulaires). N\'eanmoins, une v\'erification reste n\'ecessaire \`a post\'eriori pour v\'erifier si les objets c\'elestes vis\'es sont effectivement visibles dans les images produites: cela d\'epend notamment de la magnitude des cibles, des conditions d'observation mais aussi de la dur\'ee pendant laquelle les donn\'ees sont captur\'ees. Dans cette \'etude, nous proposons une approche bas\'ee sur l'IA explicable pour d\'etecter automatiquement la pr\'esence et la position des objets captur\'es.
Timely treatment of stroke is critical to minimize brain damage. Therefore, efforts are being made to educate the public on detecting stroke symptoms, e.g., face, arms, and speech test (FAST). In this position paper, we propose to perform the arm weakness test using the integrated video tracking from an iPhone - some general tests to assess the tracking quality and discuss potential critical points. The test has been performed on 4 stroke patients. The result is compared with the report of the clinician. Although presenting some limitations, the system proved to be able to detect arm weakness as a symptom of stroke. We envisage that introducing a portable body tracking system in such clinical tests will provide advantages in terms of objectivity, repeatability, and the possibility to record and compare groups of patients.
Reconfigurable intelligent surfaces (RISs) are considered as an enabling technology for the upcoming sixth generation of wireless systems, exhibiting significant potential for radio localization and sensing. An RIS is usually treated as an anchor point with known position and orientation when deployed to offer user localization. However, it can also be attached to a user to enable its localization in a semi-passive manner. In this paper, we consider a static user equipped with an RIS and study the RIS localization problem (i.e., joint three-dimensional position and orientation estimation), when operating in a system comprising a single-antenna transmitter and multiple synchronized single-antenna receivers with known locations. We present a multi-stage estimator using time-of-arrival and spatial frequency measurements, and derive the Cram\'er-Rao lower bounds for the estimated parameters to validate the estimator's performance. Our simulation results demonstrate the efficiency of the proposed RIS state estimation approach under various system operation parameters.
Detecting anomalies in a daily time series with a weekly pattern is a common task with a wide range of applications. A typical way of performing the task is by using decomposition method. However, the method often generates false positive results where a data point falls within its weekly range but is just off from its weekday position. We refer to this type of anomalies as "in-season anomalies", and propose a k-parameter approach to address the issue. The approach provides configurable extra tolerance for in-season anomalies to suppress misleading alerts while preserving real positives. It yields favorable result.
Ptychography has become prominent at synchrotron facilities worldwide for characterizing biological and material specimens' topological structures and properties at the nanometer or atomic scale, due to its lens - less, highly quantitative phase imaging. Its high - resolution imaging depends on accurate lateral scan position info, a large overlap ratio, and a stable probe function. But as research moves to atomic scales, meeting these requirements gets harder, often needing high - precision motion control and manual pre - calibration. This paper presents a new imaging framework. By adding a wavefront modulator and a new phase retrieval workflow, it removes the strict requirements of traditional ptychography. Significantly, our method doesn't need pre - calibration of the wavefront modulator. Optical validation showed the deviation between the recovered position and a top - tier motion stage was less than 10 nm. Sub - pixel position accuracy was achievable even with a 13% overlap ratio. In an X - ray experiment with a spatially unstable probe violating the ptychographic model and an 18% overlap ratio, our method simultaneously and quantitatively retrieved beam spatial deviation, scan position, probe function, and sample transmission function. Notably, it measured probe spatial deviations of 500nm along the X - axis and 50nm along the Y - axis, which is not feasible by previous methods. With these experimentally proven advantages, we anticipate our method to be a powerful imaging tool with auto - quantitative calibration of various parameters. It will simplify scanning diffraction microscopy implementation and expand its application scope, especially in nanometer and atomic scale imaging.
This paper explores the potential wireless communication applications of Reconfigurable Intelligent Surfaces (RIS) in reverberant wave propagation environments. Unlike in free space, we utilize the sensitivity to boundaries of the enclosed electromagnetic (EM) field and the equivalent perturbation of RISs. For the first time, we introduce the framework of reconfigurable boundary modulation in the cavities . We have proposed a robust boundary modulation scheme that exploits the continuity of object motion and the mutation of the codebook switch, which achieves pulse position modulation (PPM) by RIS-generated equivalent pulses for wireless communication in cavities. This approach achieves around 2 Mbps bit rate in the prototype and demonstrates strong resistance to channel's frequency selectivity resulting in an extremely low bit error rate (BER).
In this position paper, we propose a way of exploiting formal proofs to put forward several explainable natural language inference (NLI) tasks. The formal proofs will be produced by a reliable and high-performing logic-based NLI system. Taking advantage of the in-depth information available in the generated formal proofs, we show how it can be used to define NLI tasks with structured explanations. The proposed tasks can be ordered according to difficulty defined in terms of the granularity of explanations. We argue that the tasks will suffer with substantially fewer shortcomings than the existing explainable NLI tasks (or datasets).
The proliferation of space debris in LEO has become a major concern for the space industry. With the growing interest in space exploration, the prediction of potential collisions between objects in orbit has become a crucial issue. It is estimated that, in orbit, there are millions of fragments a few millimeters in size and thousands of inoperative satellites and discarded rocket stages. Given the high speeds that these fragments can reach, even fragments a few millimeters in size can cause fractures in a satellite's hull or put a serious crack in the window of a space shuttle. The conventional method proposed by Akella and Alfriend in 2000 remains widely used to estimate the probability of collision in short-term encounters. Given the small period of time, it is assumed that, during the encounter: (1) trajectories are represented by straight lines with constant velocity; (2) there is no velocity uncertainty and the position exhibits a stationary distribution throughout the encounter; and (3) position uncertainties are independent and represented by Gaussian distributions. This study introduces a novel derivation based on first principles that naturally allows for tight and fast upper and lower bounds for the probability of collision. We tested implementations of both probability and bound computations with the original and our formulation on a real CDM dataset used in ESA's Collision Avoidance Challenge. Our approach reduces the calculation of the probability to two one-dimensional integrals and has the potential to significantly reduce the processing time compared to the traditional method, from 80% to nearly real-time.
While large language models (LLMs) are equipped with longer text input capabilities than before, they are struggling to seek correct information in long contexts. The "lost in the middle" problem challenges most LLMs, referring to the dramatic decline in accuracy when correct information is located in the middle. To overcome this crucial issue, this paper proposes to enhance the information searching and reflection ability of LLMs in long contexts via specially designed tasks called Attention Strengthening Multi-doc QA (ASM QA). Following these tasks, our model excels in focusing more precisely on the desired information. Experimental results show substantial improvement in Multi-doc QA and other benchmarks, superior to state-of-the-art models by 13.7% absolute gain in shuffled settings, by 21.5% in passage retrieval task. We release our model, Ziya-Reader to promote related research in the community.
In this work, we propose FastCoT, a model-agnostic framework based on parallel decoding without any further training of an auxiliary model or modification to the LLM itself. FastCoT uses a size-varying context window whose size changes with position to conduct parallel decoding and auto-regressive decoding simultaneously, thus fully utilizing GPU computation resources. In FastCoT, the parallel decoding part provides the LLM with a quick glance of the future composed of approximate tokens, which could lead to faster answers compared to regular autoregressive decoding used by causal transformers. We also provide an implementation of parallel decoding within LLM, which supports KV-cache generation and batch processing. Through extensive experiments, we demonstrate that FastCoT saves inference time by nearly 20% with only a negligible performance drop compared to the regular approach. Additionally, we show that the context window size exhibits considerable robustness for different tasks.
This paper introduces a robust, learning-based method for diagnosing the state of distribution network switchgear, which is crucial for maintaining the power quality for end users. Traditional diagnostic models often rely heavily on expert knowledge and lack robustness. To address this, our method incorporates an expanded feature vector that includes environmental data, temperature readings, switch position, motor operation, insulation conditions, and local discharge information. We tackle the issue of high dimensionality through feature mapping. The method introduces a decision radius to categorize unlabeled samples and updates the model parameters using a combination of supervised and unsupervised loss, along with a consistency regularization function. This approach ensures robust learning even with a limited number of labeled samples. Comparative analysis demonstrates that this method significantly outperforms existing models in both accuracy and robustness.
Reconfigurable intelligent surface (RIS) is known as a promising technology to improve the performance of wireless communication networks, which has been extensively studied. Movable antenna (MA) is a novel technology that fully exploits the antenna position for enhancing the channel capacity. In this paper, we propose a new RIS-aided multiuser communication system with MAs. The sum-rate is maximized by jointly optimizing the beamforming, the reflection coefficient (RC) values of RIS and the positions of MAs. A fractional programming-based iterative algorithm is proposed to solve the formulated non-convex problem, considering three assumptions for the RIS. Numerical results are presented to verify the effectiveness of the proposed algorithm and the superiority of the proposed MA-based system in terms of sum-rate.
This paper presents a trajectory-tracking controller for multi-rotor unmanned aerial vehicles (UAVs) in scenarios where only the desired position and heading are known without the higher-order derivatives. The proposed solution modifies the state-of-the-art geometric controller, effectively addressing challenges related to the non-existence of the desired attitude and ensuring positive total thrust input for all time. We tackle the additional challenge of the non-availability of the higher derivatives of the trajectory by introducing novel nonlinear filter structures. We formalize theoretically the effect of these filter structures on the system error dynamics. Subsequently, through a rigorous theoretical analysis, we demonstrate that the proposed controller leads to uniformly ultimately bounded system error dynamics.
Beam steering is the process involving the calibration of the angle and position at which a particle accelerator's electron beam is incident upon the x-ray target with respect to the rotation axis of the collimator. Beam Steering is an essential task for light sources. In the case under study, the LINAC To Undulator (LTU) section of the beamline is difficult to aim. Each use of the accelerator requires re-calibration of the magnets in this section. This involves a substantial amount of time and effort from human operators, while reducing scientific throughput of the light source. We investigate the use of deep neural networks to assist in this task. The deep learning models are trained on archival data and then validated on simulation data. The performance of the deep learning model is contrasted against that of trained human operators.
Generating natural human motion from a story has the potential to transform the landscape of animation, gaming, and film industries. A new and challenging task, Story-to-Motion, arises when characters are required to move to various locations and perform specific motions based on a long text description. This task demands a fusion of low-level control (trajectories) and high-level control (motion semantics). Previous works in character control and text-to-motion have addressed related aspects, yet a comprehensive solution remains elusive: character control methods do not handle text description, whereas text-to-motion methods lack position constraints and often produce unstable motions. In light of these limitations, we propose a novel system that generates controllable, infinitely long motions and trajectories aligned with the input text. (1) We leverage contemporary Large Language Models to act as a text-driven motion scheduler to extract a series of (text, position, duration) pairs from long text. (2) We develop a text-driven motion retrieval scheme that incorporates motion matching with motion semantic and trajectory constraints. (3) We design a progressive mask transformer that addresses common artifacts in the transition motion such as unnatural pose and foot sliding. Beyond its pioneering role as the first comprehensive solution for Story-to-Motion, our system undergoes evaluation across three distinct sub-tasks: trajectory following, temporal action composition, and motion blending, where it outperforms previous state-of-the-art motion synthesis methods across the board. Homepage: https://story2motion.github.io/.
This paper focuses on the DialFRED task, which is the task of embodied instruction following in a setting where an agent can actively ask questions about the task. To address this task, we propose DialMAT. DialMAT introduces Moment-based Adversarial Training, which incorporates adversarial perturbations into the latent space of language, image, and action. Additionally, it introduces a crossmodal parallel feature extraction mechanism that applies foundation models to both language and image. We evaluated our model using a dataset constructed from the DialFRED dataset and demonstrated superior performance compared to the baseline method in terms of success rate and path weighted success rate. The model secured the top position in the DialFRED Challenge, which took place at the CVPR 2023 Embodied AI workshop.
When connecting objects and their language referents in an embodied 3D environment, it is important to note that: (1) an object can be better characterized by leveraging comparative information between itself and other objects, and (2) an object's appearance can vary with camera position. As such, we present the Multi-view Approach to Grounding in Context (MAGiC), which selects an object referent based on language that distinguishes between two similar objects. By pragmatically reasoning over both objects and across multiple views of those objects, MAGiC improves over the state-of-the-art model on the SNARE object reference task with a relative error reduction of 12.9\% (representing an absolute improvement of 2.7\%). Ablation studies show that reasoning jointly over object referent candidates and multiple views of each object both contribute to improved accuracy. Code: https://github.com/rcorona/magic_snare/
The risk of collision between resident space objects has significantly increased in recent years. As a result, spacecraft collision avoidance procedures have become an essential part of satellite operations. To ensure safe and effective space activities, satellite owners and operators rely on constantly updated estimates of encounters. These estimates include the uncertainty associated with the position of each object at the expected TCA. These estimates are crucial in planning risk mitigation measures, such as collision avoidance manoeuvres. As the TCA approaches, the accuracy of these estimates improves, as both objects' orbit determination and propagation procedures are made for increasingly shorter time intervals. However, this improvement comes at the cost of taking place close to the critical decision moment. This means that safe avoidance manoeuvres might not be possible or could incur significant costs. Therefore, knowing the evolution of this variable in advance can be crucial for operators. This work proposes a machine learning model based on diffusion models to forecast the position uncertainty of objects involved in a close encounter, particularly for the secondary object (usually debris), which tends to be more unpredictable. We compare the performance of our model with other state-of-the-art solutions and a na\"ive baseline approach, showing that the proposed solution has the potential to significantly improve the safety and effectiveness of spacecraft operations.
When training a neural network, it will quickly memorise some source-target mappings from your dataset but never learn some others. Yet, memorisation is not easily expressed as a binary feature that is good or bad: individual datapoints lie on a memorisation-generalisation continuum. What determines a datapoint's position on that spectrum, and how does that spectrum influence neural models' performance? We address these two questions for neural machine translation (NMT) models. We use the counterfactual memorisation metric to (1) build a resource that places 5M NMT datapoints on a memorisation-generalisation map, (2) illustrate how the datapoints' surface-level characteristics and a models' per-datum training signals are predictive of memorisation in NMT, (3) and describe the influence that subsets of that map have on NMT systems' performance.
Window attention, position embeddings, and high resolution finetuning are core concepts in the modern transformer era of computer vision. However, we find that naively combining these near ubiquitous components can have a detrimental effect on performance. The issue is simple: interpolating position embeddings while using window attention is wrong. We study two state-of-the-art methods that have these three components, namely Hiera and ViTDet, and find that both do indeed suffer from this bug. To fix it, we introduce a simple absolute window position embedding strategy, which solves the bug outright in Hiera and allows us to increase both speed and performance of the model in ViTDet. We finally combine the two to obtain HieraDet, which achieves 61.7 box mAP on COCO, making it state-of-the-art for models that only use ImageNet-1k pretraining. This all stems from what is essentially a 3 line bug fix, which we name "absolute win".