A novel multiuser communication system with movable antennas (MAs) is proposed, where the antenna position optimization is exploited to enhance the downlink sum-rate. The joint optimization of the transmit beamforming vector and transmit MA positions is studied for a multiuser multiple-input single-input system. An efficient algorithm is proposed to tackle the formulated non-convex problem via capitalizing on fractional programming, alternating optimization, and gradient descent methods. To strike a better performance-complexity trade-off, a zero-forcing beamforming-based design is also proposed as an alternative. Numerical investigations are presented to verify the efficiency of the proposed algorithms and their superior performance compared with the benchmark relying on conventional fixed-position antennas (FPAs).
Reconstructing a surface from a point cloud is an underdetermined problem. We use a neural network to study and quantify this reconstruction uncertainty under a Poisson smoothness prior. Our algorithm addresses the main limitations of existing work and can be fully integrated into the 3D scanning pipeline, from obtaining an initial reconstruction to deciding on the next best sensor position and updating the reconstruction upon capturing more data.
Video memorability is a measure of how likely a particular video is to be remembered by a viewer when that viewer has no emotional connection with the video content. It is an important characteristic as videos that are more memorable are more likely to be shared, viewed, and discussed. This paper presents results of a series of experiments where we improved the memorability of a video by selectively cropping frames based on image saliency. We present results of a basic fixed cropping as well as the results from dynamic cropping where both the size of the crop and the position of the crop within the frame, move as the video is played and saliency is tracked. Our results indicate that especially for videos of low initial memorability, the memorability score can be improved.
This paper addresses the distributed localization problem for a network of sensors placed in a three-dimensional space, in which sensors are able to perform range measurements, i.e., measure the relative distance between them, and exchange information on a network structure. First, we derive a necessary and sufficient condition for node localizability using barycentric coordinates. Then, building on this theoretical result, we design a distributed localizability verification algorithm, in which we propose and employ a novel distributed finite-time algorithm for sum consensus. Finally, we develop a distributed localization algorithm based on conjugate gradient method, and we derive a theoretical guarantee on its performance, which ensures finite-time convergence to the exact position for all localizable nodes. The efficiency of our algorithm compared to the existing ones from the state-of-the-art literature is further demonstrated through numerical simulations.
In this paper, an adaptive nonlinear strategy for the motion and force control of flexible manipulators is proposed. The approach provides robust motion control until contact is detected when force control is then available--without any control switch--, and vice versa. This self-tuning in mixed contact/non-contact scenarios is possible thanks to the unified formulation of force and motion control, including an integral transpose-based inverse kinematics and adaptive-update laws for the flexible manipulator link and contact stiffnesses. Global boundedness of all signals and asymptotic stability of force and position are guaranteed through Lyapunov analysis. The control strategy and its implementation has been validated using a low-cost basic microcontroller and a manipulator with 3 flexible joints and 4 actuators. Complete experimental results are provided in a realistic mixed contact scenario, demonstrating very-low computational demand with inexpensive force sensors.
Accurate representation of tooth position is extremely important in treatment. 3D dental image segmentation is a widely used method, however labelled 3D dental datasets are a scarce resource, leading to the problem of small samples that this task faces in many cases. To this end, we address this problem with a pretrained SAM and propose a novel 3D-U-SAM network for 3D dental image segmentation. Specifically, in order to solve the problem of using 2D pre-trained weights on 3D datasets, we adopted a convolution approximation method; in order to retain more details, we designed skip connections to fuse features at all levels with reference to U-Net. The effectiveness of the proposed method is demonstrated in ablation experiments, comparison experiments, and sample size experiments.
Large Language Models (LLMs) are trained with a pre-defined context length, restricting their use in scenarios requiring long inputs. Previous efforts for adapting LLMs to a longer length usually requires fine-tuning with this target length (Full-length fine-tuning), suffering intensive training cost. To decouple train length from target length for efficient context window extension, we propose Positional Skip-wisE (PoSE) training that smartly simulates long inputs using a fixed context window. This is achieved by first dividing the original context window into several chunks, then designing distinct skipping bias terms to manipulate the position indices of each chunk. These bias terms and the lengths of each chunk are altered for every training example, allowing the model to adapt to all positions within target length. Experimental results show that PoSE greatly reduces memory and time overhead compared with Full-length fine-tuning, with minimal impact on performance. Leveraging this advantage, we have successfully extended the LLaMA model to 128k tokens using a 2k training context window. Furthermore, we empirically confirm that PoSE is compatible with all RoPE-based LLMs and position interpolation strategies. Notably, our method can potentially support infinite length, limited only by memory usage in inference. With ongoing progress for efficient inference, we believe PoSE can further scale the context window beyond 128k.
In this paper, an efficient deployment strategy is proposed for a network of mobile and static sensors with nonidentical sensing and communication radii. The multiplicatively weighted Voronoi (MW-Voronoi) diagram is used to partition the field and assign the underlying coverage task to each mobile sensor. A gradient-based method is applied to find the best candidate point based on the detected coverage holes and the coverage priority considering the relative distance of the mobile sensor from the static ones and the obstacles in the field. The sensors move to a new position if such a relocation increases their local coverage. The efficiency of the proposed strategy in different scenarios is demonstrated by simulations.
Self-attention and position embedding are two key modules in transformer-based Large Language Models (LLMs). However, the potential relationship between them is far from well studied, especially for long context window extending. In fact, anomalous behaviors harming long context extrapolation exist between Rotary Position Embedding (RoPE) and vanilla self-attention unveiled by our work. To address this issue, we propose a novel attention mechanism, CoCA (Collinear Constrained Attention). Specifically, we enforce a collinear constraint between $Q$ and $K$ to seamlessly integrate RoPE and self-attention. While only adding minimal computational and spatial complexity, this integration significantly enhances long context window extrapolation ability. We provide an optimized implementation, making it a drop-in replacement for any existing transformer-based models. Extensive experiments show that CoCA performs extraordinarily well in extending context windows. A CoCA-based GPT model, trained with a context length of 512, can seamlessly extend the context window up to 32K (60$\times$), without any fine-tuning. Additionally, by dropping CoCA in LLaMA-7B, we achieve extrapolation up to 32K within only 2K training length. Our code is publicly available at: https://github.com/codefuse-ai/Collinear-Constrained-Attention
This paper describes the design of a linear quadratic gaussian (LQG) for trajectory tracking control of UAV Bicopter. In this work, disturbance in the form of payload significantly affects the trajectory tracking control process on the UAV Bicopter when using a linear quadratic regulator (LQR) controller. The use of a LQR control will be optimal in the case of a state regulator towards an equilibrium point in a system, but for the tracking case, the LQR controller is not capable of optimally, especially in systems that have high levels of nonlinearity and system dynamic changes such as inertial disturbances. Therefore, this paper proposes the design of a LQG control that is expected to overcome system dynamic changes, in this case in the form of inertial disturbances to the UAV Bicopter when carrying a payload. The success of LQG control was tested in two scenarios, the first trajectory tracking at a circular position and the second with the position of the trajectory number "8". The simulation results show that the proposed LQG controller successfully overcame inertial disturbances when the UAV Bicopter performs trajectory tracking. When given an inertial disturbance, the trajectory tracking test results show that the LQG control has a lower root mean square error (RMSE) value than the LQR control.
We present a new publicly available dataset that contains simulated data of a novel calorimeter to be installed at the CERN Large Hadron Collider. This detector will have more than six-million channels with each channel capable of position, ionisation and precision time measurement. Reconstructing these events in an efficient way poses an immense challenge which is being addressed with the latest machine learning techniques. As part of this development a large prototype with 12,000 channels was built and a beam of high-energy electrons incident on it. Using machine learning methods we have reconstructed the energy of incident electrons from the energies of three-dimensional hits, which is known to some precision. By releasing this data publicly we hope to encourage experts in the application of machine learning to develop efficient and accurate image reconstruction of these electrons.
By and large, the professional handling of huge data collections is regarded as a fundamental ingredient of the progress of machine learning and of its spectacular results in related disciplines, with a growing agreement on risks connected to the centralization of such data collections. This paper sustains the position that the time has come for thinking of new learning protocols where machines conquer cognitive skills in a truly human-like context centered on environmental interactions. This comes with specific restrictions on the learning protocol according to the collectionless principle, which states that, at each time instant, data acquired from the environment is processed with the purpose of contributing to update the current internal representation of the environment, and that the agent is not given the privilege of recording the temporal stream. Basically, there is neither permission to store the temporal information coming from the sensors, thus promoting the development of self-organized memorization skills at a more abstract level, instead of relying on bare storage to simulate learning dynamics that are typical of offline learning algorithms. This purposely extreme position is intended to stimulate the development of machines that learn to dynamically organize the information by following human-based schemes. The proposition of this challenge suggests developing new foundations on computational processes of learning and reasoning that might open the doors to a truly orthogonal competitive track on AI technologies that avoid data accumulation by design, thus offering a framework which is better suited concerning privacy issues, control and customizability. Finally, pushing towards massively distributed computation, the collectionless approach to AI will likely reduce the concentration of power in companies and governments, thus better facing geopolitical issues.
The position paper highlights the range of concerns that are engulfed in the injunction of explainable artificial intelligence in art (XAIxArt). Through a series of quick sub-questions, it points towards the ambiguities concerning 'explanation' and the postpositivist tradition of 'relevant explanation'. Rejecting both 'explanation' and 'relevant explanation', the paper takes a stance that XAIxArt is a symptom of insecurity of the anthropocentric notion of art and a nostalgic desire to return to outmoded notions of authorship and human agency. To justify this stance, the paper makes a distinction between an ornamentation model of explanation to a model of explanation as sense-making.
Cellular-connected unmanned aerial vehicles (UAVs) represent a promising technology for extending the coverage of 5G and 6G networks in a cost-effective manner. Additionally, Massive multiple-input multiple-output (MIMO) serves as an effective solution to interference mitigation in cellular-connected UAV communications. In this letter, we propose a fusion of wireless and sensor data to enhance beam alignment for cellular-connected UAV massive MIMO communications. We develop a predictive beamforming framework, including the frame structure and predictive beamformer. Moreover, we employ an extended Kalman filter (EKF) to integrate channel and sensor data and provide the corresponding state-space and observation models. Simulation results demonstrate that the proposed scheme can improve position/orientation estimation accuracy significantly, leading to higher spectral efficiency.
With the rapid development of Internet and the expanding scale of social media, social event classification has attracted increasing attention. The key to social event classification is effectively leveraging the visual and textual semantics for classification. However, most of the existing approaches may suffer from the following limitations: (1) Most of them just simply concatenate the image features and text features to get the multimodal features and ignore the fine-grained semantic relationship between modalities. (2) The majority of them hold the closed-world assumption that all classes in test are already seen in training, while this assumption can be easily broken in real-world applications. In practice, new events on Internet may not belong to any existing/seen class, and therefore cannot be correctly identified by closed-world learning algorithms. To tackle these challenges, we propose an Open-World Social Event Classifier (OWSEC) model in this paper. Firstly, we design a multimodal mask transformer network to capture cross-modal semantic relations and fuse fine-grained multimodal features of social events while masking redundant information. Secondly, we design an open-world classifier and propose a cross-modal event mixture mechanism with a novel open-world classification loss to capture the potential distribution space of the unseen class. Extensive experiments on two public datasets demonstrate the superiority of our proposed OWSEC model for open-world social event classification.
The rapidly evolving field of Explainable Artificial Intelligence (XAI) has generated significant interest in developing methods to make AI systems more transparent and understandable. However, the problem of explainability cannot be exhaustively solved in the abstract, as there is no single approach that can be universally applied to generate adequate explanations for any given AI system, and this is especially true in the arts. In this position paper, we propose an Explanatory Pragmatism (EP) framework for XAI in music performance, emphasising the importance of context and audience in the development of explainability requirements. By tailoring explanations to specific audiences and continuously refining them based on feedback, EP offers a promising direction for enhancing the transparency and interpretability of AI systems in broad artistic applications and more specifically to music performance.
Deep neural networks (DNNs) are susceptible to bugs, just like other types of software systems. A significant uptick in using DNN, and its applications in wide-ranging areas, including safety-critical systems, warrant extensive research on software engineering tools for improving the reliability of DNN-based systems. One such tool that has gained significant attention in the recent years is DNN fault localization. This paper revisits mutation-based fault localization in the context of DNN models and proposes a novel technique, named deepmufl, applicable to a wide range of DNN models. We have implemented deepmufl and have evaluated its effectiveness using 109 bugs obtained from StackOverflow. Our results show that deepmufl detects 53/109 of the bugs by ranking the buggy layer in top-1 position, outperforming state-of-the-art static and dynamic DNN fault localization systems that are also designed to target the class of bugs supported by deepmufl. Moreover, we observed that we can halve the fault localization time for a pre-trained model using mutation selection, yet losing only 7.55% of the bugs localized in top-1 position.
We analyze a family of large language models in such a lightweight manner that can be done on a single GPU. Specifically, we focus on the OPT family of models ranging from 125m to 66b parameters and rely only on whether an FFN neuron is activated or not. First, we find that the early part of the network is sparse and represents many discrete features. Here, many neurons (more than 70% in some layers of the 66b model) are "dead", i.e. they never activate on a large collection of diverse data. At the same time, many of the alive neurons are reserved for discrete features and act as token and n-gram detectors. Interestingly, their corresponding FFN updates not only promote next token candidates as could be expected, but also explicitly focus on removing the information about triggering them tokens, i.e., current input. To the best of our knowledge, this is the first example of mechanisms specialized at removing (rather than adding) information from the residual stream. With scale, models become more sparse in a sense that they have more dead neurons and token detectors. Finally, some neurons are positional: them being activated or not depends largely (or solely) on position and less so (or not at all) on textual data. We find that smaller models have sets of neurons acting as position range indicators while larger models operate in a less explicit manner.
Horizon line (or sea line) detection (HLD) is a critical component in multiple marine autonomous navigation tasks, such as identifying the navigation area (i.e., the sea), obstacle detection and geo-localization, and digital video stabilization. A recent survey highlighted several weaknesses of such detectors, particularly on sea conditions lacking from the most extensive dataset currently used by HLD researchers. Experimental validation of more robust HLDs involves collecting an extensive set of these lacking sea conditions and annotating each collected image with the correct position and orientation of the horizon line. The annotation task is daunting without a proper tool. Therefore, we present the first public annotation software with tailored features to make the sea line annotation process fast and easy. The software is available at: https://drive.google.com/drive/folders/1c0ZmvYDckuQCPIWfh_70P7E1A_DWlIvF?usp=sharing
In this study, we present a feedforward control system designed for active gravity compensation on an upper body exoskeleton. The system utilizes only positional data from internal motor sensors to calculate torque, employing analytical control equations based on Newton-Euler Inverse Dynamics. Compared to feedback control systems, the feedforward approach offers several advantages. It eliminates the need for external torque sensors, resulting in reduced hardware complexity and weight. Moreover, the feedforward control exhibits a more proactive response, leading to enhanced performance. The exoskeleton used in the experiments is lightweight and comprises 4 Degrees of Freedom, closely mimicking human upper body kinematics and three-dimensional range of motion. We conducted tests on both hardware and simulations of the exoskeleton, demonstrating stable performance. The system maintained its position over an extended period, exhibiting minimal friction and avoiding undesired slewing.