We propose an autofocusing algorithm to obtain, relatively accurately, the 3D position of each particle, particularly its axial location, and particle number of a dense transparent particle solution via its hologram. First, morphological analyses and constrained intensity are used on raw reconstructed images to obtain information on candidate focused particles. Second, axial resolution is used to obtain the real focused particles. Based on the mean intensity and equivalent diameter of each candidate focused particle, all focused particles are eventually secured. Our proposed method can rapidly provide relatively accurate ground-truth axial positions to solve the autofocusing problem that occurs with dense particles.
Reciprocity-based beamforming-most commonly employed in time-division duplexing-uses noisy, estimated (i.e., measured) channel state information (CSI) acquired on the uplink. While computationally efficient, reciprocity-based beamforming suffers severe losses under (i) low signal-to-noise ratio (SNR) and (ii) user mobility because it ignores the underlying physics of the radio channel beyond its reciprocity. Based on a physics-driven geometry-based channel model, we propose a method that jointly infers the mobile user's position and environment map on the uplink. It then leverages the estimated user position and environment map to predict CSI on the downlink. We demonstrate significant efficiency gains under both (i) low SNR and (ii) user mobility on measured data. While the user position may allow efficient beamforming in strong line-of-sight (LoS) channels, inferring an environment map allows bypassing obstructed LoS conditions using non-LoS beamforming via multipath components. We further propose "channel fusion," a probabilistic (Bayesian) combination of estimated and predicted CSI, which increases the beamforming robustness, particularly when either source of CSI is unreliable. Notably, this approach shares similarities with the minimum mean square error (MMSE) channel estimator, with geometry-based prior parameters inferred from the data.
Movable antennas offer new potential for wireless communication by introducing degrees of freedom in antenna positioning, which has recently been explored for improving sum rates. In this paper, we aim to fully leverage the capabilities of movable antennas (MAs) by assuming that both the transmitter and receiver can optimize their antenna positions in multi-user multiple-input multiple-output (MU-MIMO) communications. Recognizing that WMMSE beamforming is a highly effective method for maximizing the MU-MIMO sum rate, we modify it to integrate antenna position optimization for MA systems, which we refer to as flexible WMMSE (F-WMMSE) beamforming. Importantly, we reformulate the subproblems within WMMSE to develop regularized sparse optimization frameworks to achieve joint beamforming (antenna coefficient optimization) and element movement (antenna position optimization). We then propose a regularized least squares-based simultaneous orthogonal matching pursuit (RLS-SOMP) algorithm to address the resulting sparse optimization problem. To enhance practical applications, the low-complexity implementation of the proposed framework is developed based on the pre-calculations and matrix inverse lemma. The overall F-WMMSE algorithm converges similarly to WMMSE, and our findings indicate that F-WMMSE achieves a significant sum rate improvement compared to traditional WMMSE, exceeding 20% under appropriate simulation conditions
We consider finite $n$-person deterministic graphical games and study the existence of pure stationary Nash-equilibrium in such games. We assume that all infinite plays are equivalent and form a unique outcome, while each terminal position is a separate outcome. It is known that for $n=2$ such a game always has a Nash equilibrium, while that may not be true for $n > 2$. A game is called {\em play-once} if each player controls a unique position and {\em terminal} if any terminal outcome is better than the infinite one for each player. We prove in this paper that play-once games have Nash equilibria. We also show that terminal games have Nash equilibria if they have at most three terminals.
Resolution generalization in image generation tasks enables the production of higher-resolution images with lower training resolution overhead. However, a significant challenge in resolution generalization, particularly in the widely used Diffusion Transformers, lies in the mismatch between the positional encodings encountered during testing and those used during training. While existing methods have employed techniques such as interpolation, extrapolation, or their combinations, none have fully resolved this issue. In this paper, we propose a novel two-dimensional randomized positional encodings (RPE-2D) framework that focuses on learning positional order of image patches instead of the specific distances between them, enabling seamless high- and low-resolution image generation without requiring high- and low-resolution image training. Specifically, RPE-2D independently selects positions over a broader range along both the horizontal and vertical axes, ensuring that all position encodings are trained during the inference phase, thus improving resolution generalization. Additionally, we propose a random data augmentation technique to enhance the modeling of position order. To address the issue of image cropping caused by the augmentation, we introduce corresponding micro-conditioning to enable the model to perceive the specific cropping patterns. On the ImageNet dataset, our proposed RPE-2D achieves state-of-the-art resolution generalization performance, outperforming existing competitive methods when trained at a resolution of $256 \times 256$ and inferred at $384 \times 384$ and $512 \times 512$, as well as when scaling from $512 \times 512$ to $768 \times 768$ and $1024 \times 1024$. And it also exhibits outstanding capabilities in low-resolution image generation, multi-stage training acceleration and multi-resolution inheritance.
Lung cancer is a leading cause of cancer-related deaths globally. PET-CT is crucial for imaging lung tumors, providing essential metabolic and anatomical information, while it faces challenges such as poor image quality, motion artifacts, and complex tumor morphology. Deep learning-based models are expected to address these problems, however, existing small-scale and private datasets limit significant performance improvements for these methods. Hence, we introduce a large-scale PET-CT lung tumor segmentation dataset, termed PCLT20K, which comprises 21,930 pairs of PET-CT images from 605 patients. Furthermore, we propose a cross-modal interactive perception network with Mamba (CIPA) for lung tumor segmentation in PET-CT images. Specifically, we design a channel-wise rectification module (CRM) that implements a channel state space block across multi-modal features to learn correlated representations and helps filter out modality-specific noise. A dynamic cross-modality interaction module (DCIM) is designed to effectively integrate position and context information, which employs PET images to learn regional position information and serves as a bridge to assist in modeling the relationships between local features of CT images. Extensive experiments on a comprehensive benchmark demonstrate the effectiveness of our CIPA compared to the current state-of-the-art segmentation methods. We hope our research can provide more exploration opportunities for medical image segmentation. The dataset and code are available at https://github.com/mj129/CIPA.
Although Multimodal Large Language Models (MLLMs) excel at various image-related tasks, they encounter challenges in precisely aligning coordinates with spatial information within images, particularly in position-aware tasks such as visual grounding. This limitation arises from two key factors. First, MLLMs lack explicit spatial references, making it difficult to associate textual descriptions with precise image locations. Second, their feature extraction processes prioritize global context over fine-grained spatial details, leading to weak localization capability. To address this issue, we introduce VPP-LLaVA, an MLLM equipped with Visual Position Prompt (VPP) to improve its grounding capability. VPP-LLaVA integrates two complementary mechanisms. The global VPP overlays learnable, axis-like embeddings onto the input image to provide structured spatial cues. The local VPP focuses on fine-grained localization by incorporating position-aware queries, which suggests probable object locations. We also introduce a VPP-SFT dataset with 0.6M samples, consolidating high-quality visual grounding data into a compact format for efficient model training. Training on this dataset with VPP enhances the model's performance, achieving state-of-the-art results on standard grounding benchmarks despite using fewer training samples compared to other MLLMs like MiniGPT-v2, which rely on much larger datasets ($\sim$21M samples). The code and VPP-SFT dataset will be available at https://github.com/WayneTomas/VPP-LLaVA upon acceptance.
The integration of Rotary Position Embedding (RoPE) in Multimodal Diffusion Transformer (MMDiT) has significantly enhanced text-to-image generation quality. However, the fundamental reliance of self-attention layers on positional embedding versus query-key similarity during generation remains an intriguing question. We present the first mechanistic analysis of RoPE-based MMDiT models (e.g., FLUX), introducing an automated probing strategy that disentangles positional information versus content dependencies by strategically manipulating RoPE during generation. Our analysis reveals distinct dependency patterns that do not straightforwardly correlate with depth, offering new insights into the layer-specific roles in RoPE-based MMDiT. Based on these findings, we propose a training-free, task-specific image editing framework that categorizes editing tasks into three types: position-dependent editing (e.g., object addition), content similarity-dependent editing (e.g., non-rigid editing), and region-preserved editing (e.g., background replacement). For each type, we design tailored key-value injection strategies based on the characteristics of the editing task. Extensive qualitative and quantitative evaluations demonstrate that our method outperforms state-of-the-art approaches, particularly in preserving original semantic content and achieving seamless modifications.
Recognizing surgical gestures in real-time is a stepping stone towards automated activity recognition, skill assessment, intra-operative assistance, and eventually surgical automation. The current robotic surgical systems provide us with rich multi-modal data such as video and kinematics. While some recent works in multi-modal neural networks learn the relationships between vision and kinematics data, current approaches treat kinematics information as independent signals, with no underlying relation between tool-tip poses. However, instrument poses are geometrically related, and the underlying geometry can aid neural networks in learning gesture representation. Therefore, we propose combining motion invariant measures (curvature and torsion) with vision and kinematics data using a relational graph network to capture the underlying relations between different data streams. We show that gesture recognition improves when combining invariant signals with tool position, achieving 90.3\% frame-wise accuracy on the JIGSAWS suturing dataset. Our results show that motion invariant signals coupled with position are better representations of gesture motion compared to traditional position and quaternion representations. Our results highlight the need for geometric-aware modeling of kinematics for gesture recognition.
A point-to-point movable element (ME) enabled reconfigurable intelligent surface (ME-RIS) communication system is investigated, where each element position can be flexibly adjusted to create favorable channel conditions. For maximizing the communication rate, an efficient ME position optimization approach is proposed. Specifically, by characterizing the cascaded channel power gain in an element-wise manner, the position of each ME is iteratively updated by invoking the successive convex approximation method. Numerical results unveil that 1) the proposed element-wise ME position optimization algorithm outperforms the gradient descent algorithm; and 2) the ME-RIS significantly improves the communication rate compared to the conventional RIS with fixed-position elements.
Rotor position feedback is required in many industrial and automotive applications, e.g. for field-oriented control of brushless motors. Traditionally, magnetic sensors, resolvers or optical encoders are used to measure the rotor position. However, advances in inductive sensing concepts enable a low-cost, high-precision position measurement principle which is robust against magnetic stray fields exceeding 4000 A/m. The operating principle is based on the coupling of a transmitter coil with several receiver coils in the megahertz frequency range. The coils are part of a printed circuit board (PCB) which also comprises circuitry for demodulation and signal processing. The transmitter coil induces eddy currents in an electrically conductive passive coupling element, which provides position-dependent amplitude modulation. The voltage induced in the receiver coils encodes the rotor angle information, typically in quadrature signals. The coupling element requires no rare-earth materials and can be made of stainless steel, for instance. The PCB-based design of the sensor offers considerable flexibility in optimizing its performance. By tailoring the coil geometry and arrangement, accuracy, air gap and overall sensor dimensions can be adjusted to meet a broad range of application-specific requirements. A sensor design sample exhibits a mechanical angle error less than 0.02{\deg} (0.1{\deg} electrical) in both, finite-element simulation and test bench measurement, with good agreement.
Accurate and efficient modeling of agent interactions is essential for trajectory generation, the core of autonomous driving systems. Existing methods, scene-centric, agent-centric, and query-centric frameworks, each present distinct advantages and drawbacks, creating an impossible triangle among accuracy, computational time, and memory efficiency. To break this limitation, we propose Directional Rotary Position Embedding (DRoPE), a novel adaptation of Rotary Position Embedding (RoPE), originally developed in natural language processing. Unlike traditional relative position embedding (RPE), which introduces significant space complexity, RoPE efficiently encodes relative positions without explicitly increasing complexity but faces inherent limitations in handling angular information due to periodicity. DRoPE overcomes this limitation by introducing a uniform identity scalar into RoPE's 2D rotary transformation, aligning rotation angles with realistic agent headings to naturally encode relative angular information. We theoretically analyze DRoPE's correctness and efficiency, demonstrating its capability to simultaneously optimize trajectory generation accuracy, time complexity, and space complexity. Empirical evaluations compared with various state-of-the-art trajectory generation models, confirm DRoPE's good performance and significantly reduced space complexity, indicating both theoretical soundness and practical effectiveness. The video documentation is available at https://drope-traj.github.io/.
The evolution of Large Vision-Language Models (LVLMs) has progressed from single to multi-image reasoning. Despite this advancement, our findings indicate that LVLMs struggle to robustly utilize information across multiple images, with predictions significantly affected by the alteration of image positions. To further explore this issue, we introduce Position-wise Question Answering (PQA), a meticulously designed task to quantify reasoning capabilities at each position. Our analysis reveals a pronounced position bias in LVLMs: open-source models excel in reasoning with images positioned later but underperform with those in the middle or at the beginning, while proprietary models show improved comprehension for images at the beginning and end but struggle with those in the middle. Motivated by this, we propose SoFt Attention (SoFA), a simple, training-free approach that mitigates this bias by employing linear interpolation between inter-image causal attention and bidirectional counterparts. Experimental results demonstrate that SoFA reduces position bias and enhances the reasoning performance of existing LVLMs.
This study developed an algorithm capable of detecting a reference line (a 0.2 mm thick piano wire) to accurately determine the position of an automated installation robot within an elevator shaft. A total of 3,245 images were collected from the experimental tower of H Company, the leading elevator manufacturer in South Korea, and the detection performance was evaluated using four experimental approaches (GCH, GSCH, GECH, FCH). During the initial image processing stage, Gaussian blurring, sharpening filter, embossing filter, and Fourier Transform were applied, followed by Canny Edge Detection and Hough Transform. Notably, the method was developed to accurately extract the reference line by averaging the x-coordinates of the lines detected through the Hough Transform. This approach enabled the detection of the 0.2 mm thick piano wire with high accuracy, even in the presence of noise and other interfering factors (e.g., concrete cracks inside the elevator shaft or safety bars for filming equipment). The experimental results showed that Experiment 4 (FCH), which utilized Fourier Transform in the preprocessing stage, achieved the highest detection rate for the LtoL, LtoR, and RtoL datasets. Experiment 2(GSCH), which applied Gaussian blurring and a sharpening filter, demonstrated superior detection performance on the RtoR dataset. This study proposes a reference line detection algorithm that enables precise position calculation and control of automated robots in elevator shaft installation. Moreover, the developed method shows potential for applicability even in confined working spaces. Future work aims to develop a line detection algorithm equipped with machine learning-based hyperparameter tuning capabilities.
In recent years, high-speed trains (HSTs) communications have developed rapidly to enhance the stability of train operations and improve passenger connectivity experiences. However, as the train continues to accelerate, urgent technological innovations are needed to overcome challenges such as frequency handover and significant Doppler effects. In this paper, we present a novel architecture featuring movable antennas (MAs) to fully exploit macro spatial diversity, enabling a cell-free (CF) massive multiple-input multiple-output (MIMO) system that supports high-speed train communications. Considering the high likelihood of line-of-sight (LoS) transmission in HST scenario, we derive the uplink spectral efficiency (SE) expression for the movable CF massive MIMO system. Moreover, an optimization problem is formulated to maximize the sum SE of the considered system by optimizing the positions of the antennas. Since the formulated problem is non-convex and highly non-linear, we improve a deep reinforcement learning algorithm to address it by using proximal policy optimization (PPO). Different from traditional optimization approaches, which optimize variables separately and alternately, our improved PPO-based approach optimizes all the variables in unison. Simulation results demonstrate that movable CF massive MIMO effectively suppresses the negative impact of the Doppler effect in HST communications.
The convergence of eXtremely Large (XL) antenna arrays and high-frequency bands in future wireless networks will inevitably give rise to near-field communications, localization, and sensing. Dynamic Metasurface Antennas (DMAs) have emerged as a key enabler of the XL Multiple-Input Multiple-Output (MIMO) paradigm, leveraging reconfigurable metamaterials to support large antenna arrays. However, DMAs are inherently lossy due to propagation losses in the microstrip lines and radiative losses from the metamaterial elements, which reduce their gain and alter their beamforming characteristics compared to a lossless aperture. In this paper, we address the gap in understanding how DMA losses affect near-field beamforming performance, by deriving novel analytical expressions for the beamforming gain of DMAs under misalignments between the focusing position and the intended user's position in 3D space. Additionally, we derive beam depth limits for varying attenuation conditions, from lossless to extreme attenuation, offering insights into the impact of losses on DMA near-field performance.
Piezo-stepper actuators enable accurate positioning through the sequential contraction and expansion of piezoelectric elements, generating a walking motion. The aim of this paper is to reduce velocity ripples caused by parasitic effects, due to hysteresis in the piezoelectric material and mechanical misalignments, through suitable feedforward control. The presented approach involves the integration of a rate-dependent hysteresis model with a position-dependent feedforward learning scheme to compensate for these effects. Experimental results show that this approach leads to a significant reduction in the velocity ripples, even when the target velocity is changed. These results enable the use of piezo-stepper actuators in applications requiring high positioning accuracy and stiffness over a long stroke, without requiring expensive position sensors for high-gain feedback.
This letter explores how pinching antennas, an advanced flexible-antenna system, can enhance the performance of integrated sensing and communication (ISAC) systems by leveraging their adaptability, cost-effectiveness, and ability to facilitate line-of-sight transmission. To achieve this, a joint antenna positioning and transmit power optimization problem is formulated to maximize the total communication data rate while meeting the target sensing requirements and the system energy constraint. To address the complex non-convex optimization problem, we propose a maximum entropy-based reinforcement learning (MERL) solution. By maximizing cumulative reward and policy entropy, this approach effectively balances exploration and exploitation to enhance robustness. Numerical results demonstrate that the proposed MERL algorithm surpasses other benchmark schemes in cumulative reward, total data rate, sensing signal-to-noise ratio, and stability.
Understanding time series data is crucial for multiple real-world applications. While large language models (LLMs) show promise in time series tasks, current approaches often rely on numerical data alone, overlooking the multimodal nature of time-dependent information, such as textual descriptions, visual data, and audio signals. Moreover, these methods underutilize LLMs' reasoning capabilities, limiting the analysis to surface-level interpretations instead of deeper temporal and multimodal reasoning. In this position paper, we argue that multimodal LLMs (MLLMs) can enable more powerful and flexible reasoning for time series analysis, enhancing decision-making and real-world applications. We call on researchers and practitioners to leverage this potential by developing strategies that prioritize trust, interpretability, and robust reasoning in MLLMs. Lastly, we highlight key research directions, including novel reasoning paradigms, architectural innovations, and domain-specific applications, to advance time series reasoning with MLLMs.
The growing demand for detailed building roof data has driven the development of automated extraction methods to overcome the inefficiencies of traditional approaches, particularly in handling complex variations in building geometries. Re:PolyWorld, which integrates point detection with graph neural networks, presents a promising solution for reconstructing high-detail building roof vector data. This study enhances Re:PolyWorld's performance on complex urban residential structures by incorporating attention-based backbones and additional area segmentation loss. Despite dataset limitations, our experiments demonstrated improvements in point position accuracy (1.33 pixels) and line distance accuracy (14.39 pixels), along with a notable increase in the reconstruction score to 91.99%. These findings highlight the potential of advanced neural network architectures in addressing the challenges of complex urban residential geometries.