End-to-end learning has shown great potential in autonomous parking, yet the lack of publicly available datasets limits reproducibility and benchmarking. While prior work introduced a visual-based parking model and a pipeline for data generation, training, and close-loop test, the dataset itself was not released. To bridge this gap, we create and open-source a high-quality dataset for end-to-end autonomous parking. Using the original model, we achieve an overall success rate of 85.16% with lower average position and orientation errors (0.24 meters and 0.34 degrees).
Large Reasoning Models (LRMs) like DeepSeek-R1 and OpenAI-o1 have demonstrated remarkable reasoning capabilities, raising important questions about their biases in LLM-as-a-judge settings. We present a comprehensive benchmark comparing judging biases between LLMs and LRMs across both subjective preference-alignment datasets and objective fact-based datasets. Through investigation of bandwagon, authority, position, and distraction biases, we uncover four key findings: (1) despite their advanced reasoning capabilities, LRMs remain susceptible to the above biases; (2) LRMs demonstrate better robustness than LLMs specifically on fact-related datasets; (3) LRMs exhibit notable position bias, preferring options in later positions; and (4) we identify a novel "superficial reflection bias" where phrases mimicking reasoning (e.g., "wait, let me think...") significantly influence model judgments. To address these biases, we design and evaluate three mitigation strategies: specialized system prompts that reduce judging biases by up to 19\% in preference alignment datasets and 14\% in fact-related datasets, in-context learning that provides up to 27\% improvement on preference tasks but shows inconsistent results on factual tasks, and a self-reflection mechanism that reduces biases by up to 10\% in preference datasets and 16\% in fact-related datasets, with self-reflection proving particularly effective for LRMs. Our work provides crucial insights for developing more reliable LLM-as-a-Judge frameworks, especially as LRMs become increasingly deployed as automated judges.
Collecting Indoor Environmental Quality (IEQ) data from an occupant's immediate surroundings can provide personalized insights for healthy environmental conditions aligned with occupant preferences, but effective sensor placement for data accuracy and reliability has not been thoroughly explored. This paper explores various positioning of IEQ multi-sensing devices at individual workstations in typical office settings, aiming to identify sensor placements that most accurately reflect the environmental conditions experienced by occupants. We examined five unique positions close to an occupant (above and below the monitor, right side of the desk, ceiling, and chair backrest), two orientations, and three desk locations characterized by different lighting levels, thermal and airflow conditions. Data on temperature, humidity, carbon dioxide (CO2), particulate matters (PM1, PM2.5, PM10), illuminance, and sound were collected over a 2-week longitudinal experiment, followed by short-term experiments simulating common pollution events such as coughing and sneezing. Principal Component Analysis, Spearman's rank correlation, R2, and Mean Absolute Error were applied to identify the position and orientation that best captures the most information and matches breathing zone measurements. It was found that above the monitor position, facing the occupant, best captures the IEQ conditions experienced by the occupant.
This paper proposes a Reinforcement Learning (RL)-based control framework for position and attitude control of an Unmanned Aerial System (UAS) subjected to significant disturbance that can be associated with an uncertain trigger signal. The proposed method learns the relationship between the trigger signal and disturbance force, enabling the system to anticipate and counteract the impending disturbances before they occur. We train and evaluate three policies: a baseline policy trained without exposure to the disturbance, a reactive policy trained with the disturbance but without the trigger signal, and a predictive policy that incorporates the trigger signal as an observation and is exposed to the disturbance during training. Our simulation results show that the predictive policy outperforms the other policies by minimizing position deviations through a proactive correction maneuver. This work highlights the potential of integrating predictive cues into RL frameworks to improve UAS performance.
Few-shot segmentation (FSS) aims to segment new classes using few annotated images. While recent FSS methods have shown considerable improvements by leveraging Segment Anything Model (SAM), they face two critical limitations: insufficient utilization of structural correlations in query images, and significant information loss when converting continuous position priors to discrete point prompts. To address these challenges, we propose CMaP-SAM, a novel framework that introduces contraction mapping theory to optimize position priors for SAM-driven few-shot segmentation. CMaP-SAM consists of three key components: (1) a contraction mapping module that formulates position prior optimization as a Banach contraction mapping with convergence guarantees. This module iteratively refines position priors through pixel-wise structural similarity, generating a converged prior that preserves both semantic guidance from reference images and structural correlations in query images; (2) an adaptive distribution alignment module bridging continuous priors with SAM's binary mask prompt encoder; and (3) a foreground-background decoupled refinement architecture producing accurate final segmentation masks. Extensive experiments demonstrate CMaP-SAM's effectiveness, achieving state-of-the-art performance with 71.1 mIoU on PASCAL-$5^i$ and 56.1 on COCO-$20^i$ datasets.
Modern recommender systems increasingly leverage large language models (LLMs) for reranking to improve personalization. However, existing approaches face two key limitations: (1) heavy reliance on manually crafted prompts that are difficult to scale, and (2) inadequate handling of unstructured item metadata that complicates preference inference. We present AGP (Auto-Guided Prompt Refinement), a novel framework that automatically optimizes user profile generation prompts for personalized reranking. AGP introduces two key innovations: (1) position-aware feedback mechanisms for precise ranking correction, and (2) batched training with aggregated feedback to enhance generalization.
Trustworthy AI encompasses many aspirational aspects for aligning AI systems with human values, including fairness, privacy, robustness, explainability, and uncertainty quantification. However, efforts to enhance one aspect often introduce unintended trade-offs that negatively impact others, making it challenging to improve all aspects simultaneously. In this position paper, we review notable approaches to these five aspects and systematically consider every pair, detailing the negative interactions that can arise. For example, applying differential privacy to model training can amplify biases in the data, undermining fairness. Drawing on these findings, we take the position that addressing trustworthiness along each axis in isolation is insufficient. Instead, research on Trustworthy AI must account for intersectionality between aspects and adopt a holistic view across all relevant axes at once. To illustrate our perspective, we provide guidance on how researchers can work towards integrated trustworthiness, a case study on how intersectionality applies to the financial industry, and alternative views to our position.
While text-to-image (T2I) generation models have achieved remarkable progress in recent years, existing evaluation methodologies for vision-language alignment still struggle with the fine-grained semantic matching. Current approaches based on global similarity metrics often overlook critical token-level correspondences between textual descriptions and visual content. To this end, we present TokenFocus-VQA, a novel evaluation framework that leverages Large Vision-Language Models (LVLMs) through visual question answering (VQA) paradigm with position-specific probability optimization. Our key innovation lies in designing a token-aware loss function that selectively focuses on probability distributions at pre-defined vocabulary positions corresponding to crucial semantic elements, enabling precise measurement of fine-grained semantical alignment. The proposed framework further integrates ensemble learning techniques to aggregate multi-perspective assessments from diverse LVLMs architectures, thereby achieving further performance enhancement. Evaluated on the NTIRE 2025 T2I Quality Assessment Challenge Track 1, our TokenFocus-VQA ranks 2nd place (0.8445, only 0.0001 lower than the 1st method) on public evaluation and 2nd place (0.8426) on the official private test set, demonstrating superiority in capturing nuanced text-image correspondences compared to conventional evaluation methods.
In this paper, to fully exploit the performance gains from moveable antennas (MAs) and reconfigurable intelligent surface (RIS), a RIS-aided directional modulation \textcolor{blue}{(DM)} network with movable antenna at base station (BS) is established Based on the principle of DM, a BS equipped with MAs transmits legitimate information to a single-antenna user (Bob) while exploiting artificial noise (AN) to degrade signal reception at the eavesdropper (Eve). The combination of AN and transmission beamforming vectors is modeled as joint beamforming vector (JBV) to achieve optimal power allocation. The objective is to maximize the achievable secrecy rate (SR) by optimizing MAs antenna position, phase shift matrix (PSM) of RIS, and JBV. The limited movable range (MR) and discrete candidate positions of the MAs at the BS are considered, which renders the optimization problem non-convex. To address these challenges, an optimization method under perfect channel state information (CSI) is firstly designed, in which the MAs antenna positions are obtained using compressive sensing (CS) technology, and JBV and PSM are iteratively optimized. Then, the design method and SR performance under imperfect CSI is investigated. The proposed algorithms have fewer iterations and lower complexity. Simulation results demonstrate that MAs outperform fixed-position antennas in SR performance when there is an adequately large MR available.
Accurate and efficient positioning in complex environments is critical for applications where traditional satellite-based systems face limitations, such as indoors or urban canyons. This paper introduces WK-Pnet, an FM-based indoor positioning framework that combines wavelet packet decomposition (WPD) and knowledge distillation. WK-Pnet leverages WPD to extract rich time-frequency features from FM signals, which are then processed by a deep learning model for precise position estimation. To address computational demands, we employ knowledge distillation, transferring insights from a high-capacity model to a streamlined student model, achieving substantial reductions in complexity without sacrificing accuracy. Experimental results across diverse environments validate WK-Pnet's superior positioning accuracy and lower computational requirements, making it a viable solution for positioning in real-time resource-constraint applications.
Millimeter-wave (mmWave) MIMO systems rely on highly directional beamforming to overcome severe path loss and ensure robust communication links. However, selecting the optimal beam pair efficiently remains a challenge due to the large search space and the overhead of conventional methods. This paper proposes a probabilistic position-aided beam selection approach that exploits the statistical dependence between user equipment (UE) positions and optimal beam indices. We model the underlying joint probability mass function (PMF) of the positions and the beam indices as a low-rank tensor and estimate its parameters from training data using Bayesian inference. The estimated model is then used to predict the best (or a list of the top) beam pair indices for new UE positions. The proposed method is evaluated using data generated from a state-of-the-art ray tracing simulator and compared with neural network-based and fingerprinting approaches. The results show that our approach achieves a high data rate with fewer training samples and a significantly reduced beam search space. These advantages render it a promising solution for practical mmWave MIMO deployments, reducing the beam search overhead while maintaining a reliable connectivity.
The intrinsic alignments (IA) of galaxies, a key contaminant in weak lensing analyses, arise from correlations in galaxy shapes driven by tidal interactions and galaxy formation processes. Accurate IA modeling is essential for robust cosmological inference, but current approaches rely on perturbative methods that break down on nonlinear scales or on expensive simulations. We introduce IAEmu, a neural network-based emulator that predicts the galaxy position-position ($\xi$), position-orientation ($\omega$), and orientation-orientation ($\eta$) correlation functions and their uncertainties using mock catalogs based on the halo occupation distribution (HOD) framework. Compared to simulations, IAEmu achieves ~3% average error for $\xi$ and ~5% for $\omega$, while capturing the stochasticity of $\eta$ without overfitting. The emulator provides both aleatoric and epistemic uncertainties, helping identify regions where predictions may be less reliable. We also demonstrate generalization to non-HOD alignment signals by fitting to IllustrisTNG hydrodynamical simulation data. As a fully differentiable neural network, IAEmu enables $\sim$10,000$\times$ speed-ups in mapping HOD parameters to correlation functions on GPUs, compared to CPU-based simulations. This acceleration facilitates inverse modeling via gradient-based sampling, making IAEmu a powerful surrogate model for galaxy bias and IA studies with direct applications to Stage IV weak lensing surveys.
This article presents a method for estimating the dynamic driving states (position, velocity, acceleration and heading) from noisy measurement data. The proposed approach is effective with both complete and partial observations, producing refined trajectory signals with kinematic consistency, ensuring that velocity is the integral of acceleration and position is the integral of velocity. Additionally, the method accounts for the constraint that vehicles can only move in the direction of their orientation. The method is implemented as a configurable python library that also enables trajectory estimation solely based on position data. Regularization is applied to prevent extreme state variations. A key application is enhancing recorded trajectory data for use as reference inputs in machine learning models. At the end, the article presents the results of the method along with a comparison to ground truth data.
Neuromorphic engineering is an emerging research domain that aims to realize important implementation advantages that brain-inspired technologies can offer over classical digital technologies, including energy efficiency, adaptability, and robustness. For the field of systems and control, neuromorphic controllers could potentially bring many benefits, but their advancement is hampered by lack of systematic analysis and design tools. In this paper, the objective is to show that hybrid systems methods can aid in filling this gap. We do this by formally analyzing rhythmic neuromorphic control of a pendulum system, which was recently proposed as a prototypical setup. The neuromorphic controller generates spikes, which we model as a Dirac delta pulse, whenever the pendulum angular position crosses its resting position, with the goal of inducing a stable limit cycle. This leads to modeling the closed-loop system as a hybrid dynamical system, which in between spikes evolves in open loop and where the jumps correspond to the spiking control actions. Exploiting the hybrid system model, we formally prove the existence, uniqueness, and a stability property of the hybrid limit cycle for the closed-loop system. Numerical simulations illustrate our approach. We finally elaborate on a possible spiking adaptation mechanism on the pulse amplitude to generate a hybrid limit cycle of a desired maximal angular amplitude.
This paper develops an input-output feedback linearization-based adaptive controller to stabilize and regulate a dual-rotor rotational system (DRRS), whose inertial properties as well as the geometric configuration of rotors are unknown. First, the equations of motion governing the dynamics of DRRS are derived using the Newton-Euler approach. Next, an input-output feedback linearization technique is used to linearize the dynamics from the rotor speeds to the angular position of the system. A finite-time convergent estimator, based on the portion of the DRRS dynamics, is used to update the required parameters in the controller. Finally, the proposed controller is validated in both step and harmonic command-following problems, and the robustness of the controller to the system's parameters is demonstrated.
This paper addresses the problem of Simultaneous Localization and Mapping (SLAM) for rigid body systems in three-dimensional space. We introduce a new matrix Lie group SE_{3+n}(3), whose elements are composed of the pose, gravity, linear velocity and landmark positions, and propose an almost globally asymptotically stable nonlinear geometric observer that integrates Inertial Measurement Unit (IMU) data with landmark measurements. The proposed observer estimates the pose and map up to a constant position and a constant rotation about the gravity direction. Numerical simulations are provided to validate the performance and effectiveness of the proposed observer, demonstrating its potential for robust SLAM applications.
This paper proposes an innovative technique for representing multidimensional datasets using icons inspired by Chernoff faces. Our approach combines classical projection techniques with the explicit assignment of selected data dimensions to avatar (facial) features, leveraging the innate human ability to interpret facial traits. We introduce a semantic division of data dimensions into intuitive and technical categories, assigning the former to avatar features and projecting the latter into a four-dimensional (or higher) spatial embedding. The technique is implemented as a plugin for the open-source dpVision visualization platform, enabling users to interactively explore data in the form of a swarm of avatars whose spatial positions and visual features jointly encode various aspects of the dataset. Experimental results with synthetic test data and a 12-dimensional dataset of Portuguese Vinho Verde wines demonstrate that the proposed method enhances interpretability and facilitates the analysis of complex data structures.
This position paper for the CHI 2025 workshop "Everyday AR through AI-in-the-Loop" reflects on whether as a field HCI needs to define Responsible XR as a parallel to, and in conjunction with, Responsible AI, addressing the unique vulnerabilities posed by mass adoption of wearable AI-enabled AR glasses and XR devices that could enact AI-driven human perceptual augmentation.
Riemannian metrics on the position-orientation space M(3) that are roto-translation group SE(3) invariant play a key role in image analysis tasks like enhancement, denoising, and segmentation. These metrics enable roto-translation equivariant algorithms, with the associated Riemannian distance often used in implementation. However, computing the Riemannian distance is costly, which makes it unsuitable in situations where constant recomputation is needed. We propose the mav (minimal angular velocity) distance, defined as the Riemannian length of a geometrically meaningful curve, as a practical alternative. We see an application of the mav distance in geometric deep learning. Namely, neural networks architectures such as PONITA, relies on geometric invariants to create their roto-translation equivariant model. The mav distance offers a trainable invariant, with the parameters that determine the Riemannian metric acting as learnable weights. In this paper we: 1) classify and parametrize all SE(3) invariant metrics on M(3), 2) describes how to efficiently calculate the mav distance, and 3) investigate if including the mav distance within PONITA can positively impact its accuracy in predicting molecular properties.
Euclidean E(3) equivariant neural networks that employ scalar fields on position-orientation space M(3) have been effectively applied to tasks such as predicting molecular dynamics and properties. To perform equivariant convolutional-like operations in these architectures one needs Euclidean invariant kernels on M(3) x M(3). In practice, a handcrafted collection of invariants is selected, and this collection is then fed into multilayer perceptrons to parametrize the kernels. We rigorously describe an optimal collection of 4 smooth scalar invariants on the whole of M(3) x M(3). With optimal we mean that the collection is independent and universal, meaning that all invariants are pertinent, and any invariant kernel is a function of them. We evaluate two collections of invariants, one universal and one not, using the PONITA neural network architecture. Our experiments show that using a collection of invariants that is universal positively impacts the accuracy of PONITA significantly.