Recently, generative pre-training based models have demonstrated remarkable results on Aspect-based Sentiment Analysis (ABSA) task. However, previous works overemphasize crafting various templates to paraphrase training targets for enhanced decoding, ignoring the internal optimizations on generative models. Despite notable results achieved by these target-oriented optimization methods, they struggle with the complicated long texts since the implicit long-distance relation, e.g., aspect-opinion relation, is difficult to extract under the position embedding mechanism in generative models. Thus, in this paper, we first clarify the causes of the problem and introduce two sequence optimization strategies: the rule-based static optimization and the score-based dynamic optimization. The rule-based approach relies on handcraft priority of dependency relation to reorder the context, while the score-based algorithm dynamically regulates the contextual sequence by calculating word position scores using neural network. Based on the dynamic optimization structure, we further propose a unified Prompt-based Generative Sequence Optimization network (named PGSO), which jointly optimizes the training target as well as the generative model. Specifically, PGSO contains two components, namely, prompt construction and sequence regulator. The former constructs a task-specific prompt based on unsupervised training objects to fully utilize the pre-trained model. The latter jointly leverages semantic, syntactic and original-sequence information to dynamically regulate contextual sequence. Our experiments conducted on four ABSA tasks across multiple benchmarks indicate that PGSO outperforms state-of-the-art methods, with an average improvement of 3.52% in F1 score.
Recent text-to-image diffusion models leverage cross-attention layers, which have been effectively utilized to enhance a range of visual generative tasks. However, our understanding of cross-attention layers remains somewhat limited. In this study, we present a method for constructing Head Relevance Vectors (HRVs) that align with useful visual concepts. An HRV for a given visual concept is a vector with a length equal to the total number of cross-attention heads, where each element represents the importance of the corresponding head for the given visual concept. We develop and employ an ordered weakening analysis to demonstrate the effectiveness of HRVs as interpretable features. To demonstrate the utility of HRVs, we propose concept strengthening and concept adjusting methods and apply them to enhance three visual generative tasks. We show that misinterpretations of polysemous words in image generation can be corrected in most cases, five challenging attributes in image editing can be successfully modified, and catastrophic neglect in multi-concept generation can be mitigated. Overall, our work provides an advancement in understanding cross-attention layers and introduces new approaches for fine-controlling these layers at the head level.
The Generative Agents framework recently developed by Park et al. has enabled numerous new technical solutions and problem-solving approaches. Academic and industrial interest in generative agents has been explosive as a result of the effectiveness of generative agents toward emulating human behaviour. However, it is necessary to consider the ethical challenges and concerns posed by this technique and its usage. In this position paper, we discuss the extant literature that evaluate the ethical considerations regarding generative agents and similar generative tools, and identify additional concerns of significant importance. We also suggest guidelines and necessary future research on how to mitigate some of the ethical issues and systemic risks associated with generative agents.
Self-supervised monocular depth estimation (MDE) has gained popularity for obtaining depth predictions directly from videos. However, these methods often produce scale invariant results, unless additional training signals are provided. Addressing this challenge, we introduce a novel self-supervised metric-scaled MDE model that requires only monocular video data and the camera's mounting position, both of which are readily available in modern vehicles. Our approach leverages planar-parallax geometry to reconstruct scene structure. The full pipeline consists of three main networks, a multi-frame network, a singleframe network, and a pose network. The multi-frame network processes sequential frames to estimate the structure of the static scene using planar-parallax geometry and the camera mounting position. Based on this reconstruction, it acts as a teacher, distilling knowledge such as scale information, masked drivable area, metric-scale depth for the static scene, and dynamic object mask to the singleframe network. It also aids the pose network in predicting a metric-scaled relative pose between two subsequent images. Our method achieved state-of-the-art results for the driving benchmark KITTI for metric-scaled depth prediction. Notably, it is one of the first methods to produce self-supervised metric-scaled depth prediction for the challenging Cityscapes dataset, demonstrating its effectiveness and versatility.
To improve the convergence speed and optimization accuracy of the Dung Beetle Optimizer (DBO), this paper proposes an improved algorithm based on circle mapping and longitudinal-horizontal crossover strategy (CICRDBO). First, the Circle method is used to map the initial population to increase diversity. Second, the longitudinal-horizontal crossover strategy is applied to enhance the global search ability by ensuring the position updates of the dung beetle. Simulations were conducted on 10 benchmark test functions, and the results demonstrate that the improved algorithm performs well in both convergence speed and optimization accuracy. The improved algorithm is further applied to the hyperparameter selection of the Random Forest classification algorithm for binary classification prediction in the retail industry. Various combination comparisons prove the practicality of the improved algorithm, followed by SHapley Additive exPlanations (SHAP) analysis.
Recent advances in multimodal models have demonstrated impressive capabilities in object recognition and scene understanding. However, these models often struggle with precise spatial localization - a critical capability for real-world applications. Inspired by how humans use grid-based references like chess boards and maps, we propose introducing explicit visual position encoding through a simple grid overlay approach. By adding a 9x9 black grid pattern onto input images, our method provides visual spatial guidance analogous to how positional encoding works in transformers, but in an explicit, visual form. Experiments on the COCO 2017 dataset demonstrate that our grid-based approach achieves significant improvements in localization accuracy, with a 107.4% increase in IoU (from 0.27 to 0.56) and a 194.4% improvement in GIoU (from 0.18 to 0.53) compared to baseline performance. Through attention visualization analysis, we show how this visual position encoding helps models better ground spatial relationships. Our method's simplicity and effectiveness make it particularly valuable for applications requiring accurate spatial reasoning, such as robotic manipulation, medical imaging, and autonomous navigation.
Tokenization methods like Byte-Pair Encoding (BPE) enhance computational efficiency in large language models (LLMs) but often obscure internal character structures within tokens. This limitation hinders LLMs' ability to predict precise character positions, which is crucial in tasks like Chinese Spelling Correction (CSC) where identifying the positions of misspelled characters accelerates correction processes. We propose Token Internal Position Awareness (TIPA), a method that significantly improves models' ability to capture character positions within tokens by training them on reverse character prediction tasks using the tokenizer's vocabulary. Experiments demonstrate that TIPA enhances position prediction accuracy in LLMs, enabling more precise identification of target characters in original text. Furthermore, when applied to downstream tasks that do not require exact position prediction, TIPA still boosts performance in tasks needing character-level information, validating its versatility and effectiveness.
In this position paper, we propose an approach for sustainable data collection in the field of optimal mix design for marble sludge reuse. Marble sludge, a calcium-rich residual from stone-cutting processes, can be repurposed by mixing it with various ingredients. However, determining the optimal mix design is challenging due to the variability in sludge composition and the costly, time-consuming nature of experimental data collection. Also, we investigate the possibility of using machine learning models using meta-learning as an optimization tool to estimate the correct quantity of stone-cutting sludge to be used in aggregates to obtain a mix design with specific mechanical properties that can be used successfully in the building industry. Our approach offers two key advantages: (i) through simulations, a large dataset can be generated, saving time and money during the data collection phase, and (ii) Utilizing machine learning models, with performance enhancement through hyper-parameter optimization via meta-learning, to estimate optimal mix designs reducing the need for extensive manual experimentation, lowering costs, minimizing environmental impact, and accelerating the processing of quarry sludge. Our idea promises to streamline the marble sludge reuse process by leveraging collective data and advanced machine learning, promoting sustainability and efficiency in the stonecutting sector.
In this paper, we introduce a novel pricing model for Uniswap V3, built upon stochastic processes and the Martingale Stopping Theorem. This model innovatively frames the valuation of positions within Uniswap V3. We further conduct a numerical analysis and examine the sensitivities through Greek risk measures to elucidate the model's implications. The results underscore the model's significant academic contribution and its practical applicability for Uniswap liquidity providers, particularly in assessing risk exposure and guiding hedging strategies.
Extending context window sizes allows large language models (LLMs) to process longer sequences and handle more complex tasks. Rotary Positional Embedding (RoPE) has become the de facto standard due to its relative positional encoding properties that benefit long-context training. However, we observe that using RoPE with BFloat16 format results in numerical issues, causing it to deviate from its intended relative positional encoding, especially in long-context scenarios. This issue arises from BFloat16's limited precision and accumulates as context length increases, with the first token contributing significantly to this problem. To address this, we develop AnchorAttention, a plug-and-play attention method that alleviates numerical issues caused by BFloat16, improves long-context capabilities, and speeds up training. AnchorAttention reduces unnecessary attention computations, maintains semantic coherence, and boosts computational efficiency by treating the first token as a shared anchor with a consistent position ID, making it visible to all documents within the training context. Experiments on three types of LLMs demonstrate that AnchorAttention significantly improves long-context performance and reduces training time by over 50\% compared to standard full attention mechanisms, while preserving the original LLM's capabilities on general tasks. Our code is available at https://github.com/haonan3/AnchorContext.
Direct position estimation (DPE) is an effective solution to the MP issue at the signal processing level. Unlike two-step positioning (2SP) receivers, DPE directly solves for the receiver position, velocity, and time (PVT) in the navigation domain, without the estimation of intermediate measurements, thus allowing it to provide more robust and accurate PVT estimates in the presence of multipath (MP) and weak signals. But GNSS positioning with DPE is mostly left unapplied commercially, and continuing research into DPE has remained relatively stagnant over the past few years. To encourage further research on DPE by the GNSS community, we propose a DPE plug-in module that can be integrated into the conventional 2SP software-defined receivers (SDRs). Programmed in MATLAB, the proposed DPE plug-in module is aimed for better understanding and familiarity of a practical implementation of DPE. Its plug-in module architecture allows it to be incorporated with 2SP MATLAB SDRs, both vector tracking and scalar tracking with minimum changes, making it easy to use, and provides greater flexibility for researchers using various 2SP SDRs. We propose to further improve the performance of DPE against MP by incorporating Multipath Mitigation Technology (MMT) into DPE. Referred to as MMT-DPE, it is proposed as a variant of DPE that adds the MP components into DPE signal model by integrating MMT cost function into DPE, with the aim to better suit DPE for urban environment applications. Results show that while in MP-only conditions, an MMT-integrated 2SP (MMT-2SP) has similar performance with MMT-DPE, the proposed MMT-DPE manages to show great superiority against NLOS, making it the preferable option for applications in urban environments.
If an AI system makes decisions over time, how should we evaluate how aligned it is with a group of stakeholders (who may have conflicting values and preferences)? In this position paper, we advocate for consideration of temporal aspects including stakeholders' changing levels of satisfaction and their possibly temporally extended preferences. We suggest how a recent approach to evaluating fairness over time could be applied to a new form of pluralistic alignment: temporal pluralism, where the AI system reflects different stakeholders' values at different times.
In recent years, with the rapid development of augmented reality (AR) technology, there is an increasing demand for multi-user collaborative experiences. Unlike for single-user experiences, ensuring the spatial localization of every user and maintaining synchronization and consistency of positioning and orientation across multiple users is a significant challenge. In this paper, we propose a multi-user localization system based on ORB-SLAM2 using monocular RGB images as a development platform based on the Unity 3D game engine. This system not only performs user localization but also places a common virtual object on a planar surface (such as table) in the environment so that every user holds a proper perspective view of the object. These generated virtual objects serve as reference points for multi-user position synchronization. The positioning information is passed among every user's AR devices via a central server, based on which the relative position and movement of other users in the space of a specific user are presented via virtual avatars all with respect to these virtual objects. In addition, we use deep learning techniques to estimate the depth map of an image from a single RGB image to solve occlusion problems in AR applications, making virtual objects appear more natural in AR scenes.
Collimator detection remains a challenging task in X-ray systems with unreliable or non-available information about the detectors position relative to the source. This paper presents a physically motivated image processing pipeline for simulating the characteristics of collimator shadows in X-ray images. By generating randomized labels for collimator shapes and locations, incorporating scattered radiation simulation, and including Poisson noise, the pipeline enables the expansion of limited datasets for training deep neural networks. We validate the proposed pipeline by a qualitative and quantitative comparison against real collimator shadows. Furthermore, it is demonstrated that utilizing simulated data within our deep learning framework not only serves as a suitable substitute for actual collimators but also enhances the generalization performance when applied to real-world data.
We introduce a novel class of systemic risk measures, the Vulnerability Conditional risk measures, which try to capture the "tail risk" of a risky position in scenarios where one or more market participants is experiencing financial distress. Various theoretical properties of Vulnerability Conditional risk measures, along with a series of related contribution measures, have been considered in this paper. We further introduce the backtesting procedures of VCoES and MCoES. Through numerical examples, we validate our theoretical insights and further apply our newly proposed risk measures to the empirical analysis of cryptocurrencies, demonstrating their practical relevance and utility in capturing systemic risk.
This letter considers a fluid antenna system (FAS)-aided secure and covert communication system, where the transmitter adjusts multiple fluid antennas' positions to achieve secure and covert transmission under the threat of an eavesdropper and the detection of a warden. This letter aims to maximize the secrecy rate while satisfying the covertness constraint. Unfortunately, the optimization problem is non-convex due to the coupled variables. To tackle this, we propose an alternating optimization (AO) algorithm to alternatively optimize the optimization variables in an iterative manner. In particular, we use a penalty-based method and the majorization-minimization (MM) algorithm to optimize the transmit beamforming and fluid antennas' positions, respectively. Simulation results show that FAS can significantly improve the performance of secrecy and covertness compared to the fixed-position antenna (FPA)-based schemes.
Interstellar objects (ISOs), astronomical objects not gravitationally bound to the sun, could present valuable opportunities to advance our understanding of the universe's formation and composition. In response to the unpredictable nature of their discoveries that inherently come with large and rapidly changing uncertainty in their state, this paper proposes a novel multi-spacecraft framework for locally maximizing information to be gained through ISO encounters with formal probabilistic guarantees. Given some approximated control and estimation policies for fully autonomous spacecraft operations, we first construct an ellipsoid around its terminal position, where the ISO would be located with a finite probability. The large state uncertainty of the ISO is formally handled here through the hierarchical property in stochastically contracting nonlinear systems. We then propose a method to find the terminal positions of the multiple spacecraft optimally distributed around the ellipsoid, which locally maximizes the information we can get from all the points of interest (POIs). This utilizes a probabilistic information cost function that accounts for spacecraft positions, camera specifications, and ISO position uncertainty, where the information is defined as visual data collected by cameras. Numerical simulations demonstrate the efficacy of this approach using synthetic ISO candidates generated from quasi-realistic empirical populations. Our method allows each spacecraft to optimally select its terminal state and determine the ideal number of POIs to investigate, potentially enhancing the ability to study these rare and fleeting interstellar visitors while minimizing resource utilization.
Many studies have predicted SocioEconomic Position (SEP) for aggregated spatial units such as villages using satellite data, but SEP prediction at the household level and other sources of imagery have not been yet explored. We assembled a dataset of 975 households in a semi-rural district in southern Mozambique, consisting of self-reported asset, expenditure, and income SEP data, as well as multimodal imagery including satellite images and a ground-based photograph survey of 11 household elements. We fine-tuned a convolutional neural network to extract feature vectors from the images, which we then used in regression analyzes to model household SEP using different sets of image types. The best prediction performance was found when modeling asset-based SEP using random forest models with all image types, while the performance for expenditure- and income-based SEP was lower. Using SHAP, we observed clear differences between the images with the largest positive and negative effects, as well as identified the most relevant household elements in the predictions. Finally, we fitted an additional reduced model using only the identified relevant household elements, which had an only slightly lower performance compared to models using all images. Our results show how ground-based household photographs allow to zoom in from an area-level to an individual household prediction while minimizing the data collection effort by using explainable machine learning. The developed workflow can be potentially integrated into routine household surveys, where the collected household imagery could be used for other purposes, such as refined asset characterization and environmental exposure assessment.
We establish a duality relation between Hamiltonian systems and neural network-based learning systems. We show that the Hamilton-Jacobi equations for position and momentum variables correspond to the equations governing the activation dynamics of non-trainable variables and the learning dynamics of trainable variables. The duality is then applied to model various field theories using the activation and learning dynamics of neural networks. For Klein-Gordon fields, the corresponding weight tensor is symmetric, while for Dirac fields, the weight tensor must contain an anti-symmetric tensor factor. The dynamical components of the weight and bias tensors correspond, respectively, to the temporal and spatial components of the gauge field.
Non-prehensile manipulation, such as pushing objects to a desired target position, is an important skill for robots to assist humans in everyday situations. However, the task is challenging due to the large variety of objects with different and sometimes unknown physical properties, such as shape, size, mass, and friction. This can lead to the object overshooting its target position, requiring fast corrective movements of the robot around the object, especially in cases where objects need to be precisely pushed. In this paper, we improve the state-of-the-art by introducing a new memory-based vision-proprioception RL model to push objects more precisely to target positions using fewer corrective movements.