In this paper, we introduce a novel spatial attention module, that can be integrated to any convolutional network. This module guides the model to pay attention to the most discriminative part of an image. This enables the model to attain a better performance by an end-to-end training. In standard approaches, a spatial attention map is generated in a position-wise fashion. We observe that this results in very irregular boundaries. This could make it difficult to generalize to new samples. In our method, the attention region is constrained to be rectangular. This rectangle is parametrized by only 5 parameters, allowing for a better stability and generalization to new samples. In our experiments, our method systematically outperforms the position-wise counterpart. Thus, this provides us a novel useful spatial attention mechanism for convolutional models. Besides, our module also provides the interpretability concerning the ``where to look" question, as it helps to know the part of the input on which the model focuses to produce the prediction.
Co-optimization of both vehicle speed and gear position via model predictive control (MPC) has been shown to offer benefits for fuel-efficient autonomous driving. However, optimizing both the vehicle's continuous dynamics and discrete gear positions may be too computationally intensive for a real-time implementation. This work proposes a learning-based MPC scheme to address this issue. A policy is trained to select and fix the gear positions across the prediction horizon of the MPC controller, leaving a significantly simpler continuous optimization problem to be solved online. In simulation, the proposed approach is shown to have a significantly lower computation burden and a comparable performance, with respect to pure MPC-based co-optimization.
In the development of wireless communication technology, multiple-input multiple-output (MIMO) technology has emerged as a key enabler, significantly enhancing the capacity of communication systems. However, traditional MIMO systems, which rely on fixed-position antennas (FPAs) with spacing limitations, cannot fully exploit the channel variations in the continuous spatial domain, thus limiting the system's spatial multiplexing performance and diversity. To address these limitations, movable antennas (MAs) have been introduced, offering a breakthrough in signal processing and spatial multiplexing by overcoming the constraints of FPA-based systems. Furthermore, this paper extends the functionality of MAs by introducing movable rotatable antennas (MRAs), which enhance the system's ability to optimize performance in the spatial domain by adding rotational degrees of freedom. By incorporating a dynamic precoding framework based on both antenna position and rotation angle optimization, and employing the zero-forcing (ZF) precoding method, this paper proposes an efficient optimization approach aimed at improving signal quality, mitigating interference, and solving the non-linear, constrained optimization problem using the sequential quadratic programming (SQP) algorithm. This approach effectively enhances the communication system's performance.
Agentic workflows invoked by Large Language Models (LLMs) have achieved remarkable success in handling complex tasks. However, optimizing such workflows is costly and inefficient in real-world applications due to extensive invocations of LLMs. To fill this gap, this position paper formulates agentic workflows as computational graphs and advocates Graph Neural Networks (GNNs) as efficient predictors of agentic workflow performances, avoiding repeated LLM invocations for evaluation. To empirically ground this position, we construct FLORA-Bench, a unified platform for benchmarking GNNs for predicting agentic workflow performances. With extensive experiments, we arrive at the following conclusion: GNNs are simple yet effective predictors. This conclusion supports new applications of GNNs and a novel direction towards automating agentic workflow optimization. All codes, models, and data are available at https://github.com/youngsoul0731/Flora-Bench.
Denoising higher-resolution latents via a pre-trained U-Net leads to repetitive and disordered image patterns. Although recent studies make efforts to improve generative quality by aligning denoising process across original and higher resolutions, the root cause of suboptimal generation is still lacking exploration. Through comprehensive analysis of position encoding in U-Net, we attribute it to inconsistent position encoding, sourced by the inadequate propagation of position information from zero-padding to latent features in convolution layers as resolution increases. To address this issue, we propose a novel training-free approach, introducing a Progressive Boundary Complement (PBC) method. This method creates dynamic virtual image boundaries inside the feature map to enhance position information propagation, enabling high-quality and rich-content high-resolution image synthesis. Extensive experiments demonstrate the superiority of our method.
This paper presents a nonlinear control strategy for an aerial cooperative payload transportation system consisting of two quadrotor UAVs rigidly connected to a payload. The system includes human physical interaction facilitated by an admittance control. The proposed control framework integrates an adaptive Backstepping controller for the position subsystem and a Fast Nonsingular Terminal Sliding Mode Control (FNTSMC) for the attitude subsystem to ensure asymptotic stabilization. The admittance controller interprets the interaction forces from the human operator, generating reference trajectories for the position controller to ensure accurate tracking of the operator's guidance. The system aims to assist humans in payload transportation, providing both stability and responsiveness. The robustness and effectiveness of the proposed control scheme in maintaining system stability and performance under various conditions are presented.
Dance serves as a profound and universal expression of human culture, conveying emotions and stories through movements synchronized with music. Although some current works have achieved satisfactory results in the task of single-person dance generation, the field of multi-person dance generation remains relatively novel. In this work, we present a group choreography framework that leverages recent advancements in Large Language Models (LLM) by modeling the group dance generation problem as a sequence-to-sequence translation task. Our framework consists of a tokenizer that transforms continuous features into discrete tokens, and an LLM that is fine-tuned to predict motion tokens given the audio tokens. We show that by proper tokenization of input modalities and careful design of the LLM training strategies, our framework can generate realistic and diverse group dances while maintaining strong music correlation and dancer-wise consistency. Extensive experiments and evaluations demonstrate that our framework achieves state-of-the-art performance.
Due to the large number of parameters, the inference phase of Large Language Models (LLMs) is resource-intensive. Unlike traditional model compression, which needs retraining, recent dynamic computation methods show that not all components are required for inference, enabling a training-free pipeline. In this paper, we focus on the dynamic depth of LLM generation. A token-position aware layer skipping framework is proposed to save 1.5x times operations efficiently while maintaining performance. We first observed that tokens predicted later have lower perplexity and thus require less computation. Then, we propose a training-free algorithm called Position-Aware Depth Decay Decoding ($D^3$), which leverages a power-law decay function, $\left\lfloor L \times (\alpha^i) \right\rfloor$, to determine the number of layers to retain when generating token $T_i$. Remarkably, without any retraining, the $D^3$ achieves success across a wide range of generation tasks for the first time. Experiments on large language models (\ie the Llama) with $7 \sim 70$ billion parameters show that $D^3$ can achieve an average 1.5x speedup compared with the full-inference pipeline while maintaining comparable performance with nearly no performance drop ($<1\%$) on the GSM8K and BBH benchmarks.
We present TRACE, a novel system for live *common ground* tracking in situated collaborative tasks. With a focus on fast, real-time performance, TRACE tracks the speech, actions, gestures, and visual attention of participants, uses these multimodal inputs to determine the set of task-relevant propositions that have been raised as the dialogue progresses, and tracks the group's epistemic position and beliefs toward them as the task unfolds. Amid increased interest in AI systems that can mediate collaborations, TRACE represents an important step forward for agents that can engage with multiparty, multimodal discourse.
Age of Information (AoI) is a key metric used for evaluating data freshness in communication networks, particularly in systems requiring real-time updates. In positioning applications, maintaining low AoI is critical for ensuring timely and accurate position estimation. This paper introduces an age-informed metric, which we term as Age of Positioning (AoP), that captures the temporal evolution of positioning accuracy for agents following random trajectories and sharing sporadic location updates. Using the widely adopted Random Waypoint (RWP) mobility model, which captures stochastic user movement through waypoint-based trajectories, we derive closed-form expressions for this metric under various queuing disciplines and different modes of operation of the agent. The analytical results are verified with numerical simulations, and the existence of optimal operating conditions is demonstrated.
We present the Electronic Tensor Reconstruction Algorithm (ELECTRA) - an equivariant model for predicting electronic charge densities using floating orbitals. Floating orbitals are a long-standing concept in the quantum chemistry community that promises more compact and accurate representations by placing orbitals freely in space, as opposed to centering all orbitals at the position of atoms. Finding the ideal placement of these orbitals requires extensive domain knowledge, though, which thus far has prevented widespread adoption. We solve this in a data-driven manner by training a Cartesian tensor network to predict the orbital positions along with orbital coefficients. This is made possible through a symmetry-breaking mechanism that is used to learn position displacements with lower symmetry than the input molecule while preserving the rotation equivariance of the charge density itself. Inspired by recent successes of Gaussian Splatting in representing densities in space, we are using Gaussian orbitals and predicting their weights and covariance matrices. Our method achieves a state-of-the-art balance between computational efficiency and predictive accuracy on established benchmarks.
Multivariate time series (MTS) forecasting is vital in fields like weather, energy, and finance. However, despite deep learning advancements, traditional Transformer-based models often diminish the effect of crucial inter-variable relationships by singular token embedding and struggle to effectively capture complex dependencies among variables, especially in datasets with rare or extreme events. These events create significant imbalances and lead to high skewness, complicating accurate prediction efforts. This study introduces PFformer, a position-free Transformer-based model designed for single-target MTS forecasting, specifically for challenging datasets characterized by extreme variability. PFformer integrates two novel embedding strategies: Enhanced Feature-based Embedding (EFE) and Auto-Encoder-based Embedding (AEE). EFE effectively encodes inter-variable dependencies by mapping related sequence subsets to high-dimensional spaces without positional constraints, enhancing the encoder's functionality. PFformer shows superior forecasting accuracy without the traditional limitations of positional encoding in MTS modeling. We evaluated PFformer across four challenging datasets, focusing on two key forecasting scenarios: long sequence prediction for 3 days ahead and rolling predictions every four hours to reflect real-time decision-making processes in water management. PFformer demonstrated remarkable improvements, from 20% to 60%, compared with state-of-the-art models.
Large multimodal models (LMMs) excel in scene understanding but struggle with fine-grained spatiotemporal reasoning due to weak alignment between linguistic and visual representations. Existing methods map textual positions and durations into the visual space encoded from frame-based videos, but suffer from temporal sparsity that limits language-vision temporal coordination. To address this issue, we introduce LLaFEA (Large Language and Frame-Event Assistant) to leverage event cameras for temporally dense perception and frame-event fusion. Our approach employs a cross-attention mechanism to integrate complementary spatial and temporal features, followed by self-attention matching for global spatio-temporal associations. We further embed textual position and duration tokens into the fused visual space to enhance fine-grained alignment. This unified framework ensures robust spatio-temporal coordinate alignment, enabling LMMs to interpret scenes at any position and any time. In addition, we construct a dataset of real-world frames-events with coordinate instructions and conduct extensive experiments to validate the effectiveness of the proposed method.
Fluid antenna system (FAS) is an emerging technology that uses the new form of shape- and position-reconfigurable antennas to empower the physical layer for wireless communications. Prior studies on FAS were however limited to narrowband channels. Motivated by this, this paper addresses the integration of FAS in the fifth generation (5G) orthogonal frequency division multiplexing (OFDM) framework to address the challenges posed by wideband communications. We propose the framework of the wideband FAS OFDM system that includes a novel port selection matrix. Then we derive the achievable rate expression and design the adaptive modulation and coding (AMC) scheme based on the rate. Extensive link-level simulation results demonstrate striking improvements of FAS in the wideband channels, underscoring the potential of FAS in future wireless communications.
Channel tracking in millimeter wave (mmWave) vehicular systems is crucial for maintaining robust vehicle-to-infrastructure (V2I) communication links, which can be leveraged to achieve high accuracy vehicle position and orientation tracking as a byproduct of communication. While prior work tends to simplify the system model by omitting critical system factors such as clock offsets, filtering effects, antenna array orientation offsets, and channel estimation errors, we address the challenges of a practical mmWave multiple-input multiple-output (MIMO) communication system between a single base station (BS) and a vehicle while tracking the vehicle's position and orientation (PO) considering realistic driving behaviors. We first develop a channel tracking algorithm based on multidimensional orthogonal matching pursuit (MOMP) with factoring (F-MOMP) to reduce computational complexity and enable high-resolution channel estimates during the tracking stage, suitable for PO estimation. Then, we develop a network called VO-ChAT (Vehicle Orientation-Channel Attention for orientation Tracking), which processes the channel estimate sequence for orientation prediction. Afterward, a weighted least squares (WLS) problem that exploits the channel geometry is formulated to create an initial estimate of the vehicle's 2D position. A second network named VP-ChAT (Vehicle Position-Channel Attention for position Tracking) refines the geometric position estimate. VP-ChAT is a Transformer inspired network processing the historical channel and position estimates to provide the correction for the initial geometric position estimate. The proposed solution is evaluated using raytracing generated channels in an urban canyon environment. For 80% of the cases it achieves a 2D position tracking accuracy of 26 cm while orientation errors are kept below 0.5 degree.
This study proposes a new deep learning method for reconstructing depth images of moving objects within a specific area using Wi-Fi channel state information (CSI). The Wi-Fi-based depth imaging technique has novel applications in domains such as security and elder care. However, reconstructing depth images from CSI is challenging because learning the mapping function between CSI and depth images, both of which are high-dimensional data, is particularly difficult. To address the challenge, we propose a new approach called Wi-Depth. The main idea behind the design of Wi-Depth is that a depth image of a moving object can be decomposed into three core components: the shape, depth, and position of the target. Therefore, in the depth-image reconstruction task, Wi-Depth simultaneously estimates the three core pieces of information as auxiliary tasks in our proposed VAE-based teacher-student architecture, enabling it to output images with the consistency of a correct shape, depth, and position. In addition, the design of Wi-Depth is based on our idea that this decomposition efficiently takes advantage of the fact that shape, depth, and position relate to primitive information inferred from CSI such as angle-of-arrival, time-of-flight, and Doppler frequency shift.
The detection of irregularly spaced pulses of non-negligible width is a fascinating yet under-explored topic in signal processing. It sits adjacent to other core topics such as radar and symbol detection yet has its own distinctive challenges. Even modern techniques such as compressed sensing perform worse than may be expected on pulse processing problems. Real-world applications include nuclear spectroscopy, flow cytometry, seismic signal processing and neural spike sorting, and these in turn have applications to environmental radiation monitoring, surveying, diagnostic medicine, industrial imaging, biomedical imaging, top-down proteomics, and security screening, to name just a few. This overview paper endeavours to position the pulse processing problem in the context of signal processing. It also describes some current challenges in the field.
Various control methods have been studied to control the position and attitude of quadrotors. There are some differences in the mathematical equations between the two types of quadrotor configurations that lead to different control efficiency in disturbance environments. This paper described the nonlinear back stepping approach based on the Lyapunov function theory and LaSalle Principle for the quadrotor control system, which can provide the stability of all system states during the tracking of the desired trajectory. Accordingly, a mathematical model of the cross quadrotor configuration together with the controller has been built to stabilize the altitude and position of the quadrotor. To clarify the effectiveness of this method with the selected quadrotor configuration, we compare it with a traditional PID controller in an environment affected by disturbances. The simulation results in MATLAB show satisfactory stability of the quadrotor flight and following certain trajectories, confirming the accuracy and validity of the control method.
Egocentric human body estimation allows for the inference of user body pose and shape from a wearable camera's first-person perspective. Although research has used pose estimation techniques to overcome self-occlusions and image distortions caused by head-mounted fisheye images, similar advances in 3D human mesh recovery (HMR) techniques have been limited. We introduce Fish2Mesh, a fisheye-aware transformer-based model designed for 3D egocentric human mesh recovery. We propose an egocentric position embedding block to generate an ego-specific position table for the Swin Transformer to reduce fisheye image distortion. Our model utilizes multi-task heads for SMPL parametric regression and camera translations, estimating 3D and 2D joints as auxiliary loss to support model training. To address the scarcity of egocentric camera data, we create a training dataset by employing the pre-trained 4D-Human model and third-person cameras for weak supervision. Our experiments demonstrate that Fish2Mesh outperforms previous state-of-the-art 3D HMR models.
This paper investigates the impact of randomly initialized unique encoding of classification label position on the visual masked self-supervised pre-trained model when fine-tuning downstream classification tasks. Our findings indicate that different random initializations lead to significant variations in fine-tuned results, even when using the same allocation strategy for classification datasets. The accuracy gap between these results suggests that the visual masked self-supervised pre-trained model has an inherent preference for classification label positions. To investigate this, we compare it with the non-self-supervised visual pre-trained model and hypothesize that the masked self-supervised model exhibits a self-aware bias toward certain label positions. To mitigate the instability caused by random encoding, we propose a classification label position ranking algorithm, Label Ranker. It is based on 1-D dimensionality reduction of feature maps using Linear Discriminant Analysis and position-rank encoding of them by unsupervised feature clustering using the similarity property of Euclidean distance. This algorithm ensures that label position encoding align with the model’s inherent preference. Extensive ablation experiments using ImageMAE and VideoMAE models on the CIFAR-100, UCF101, and HMDB51 classification datasets validate our approach. Results demonstrate that our method effectively stabilizes classification label position encoding, improving fine-tuned performance for visual masked self-supervised models.