Search

While a large body of work inspects language models for biases concerning gender, race, occupation and religion, biases of geographical nature are relatively less explored. Some recent studies benchmark the degree to which large language models encode geospatial knowledge. However, the impact of the encoded geographical knowledge (or lack thereof) on real-world applications has not been documented. In this work, we examine large language models for two common scenarios that require geographical knowledge: (a) travel recommendations and (b) geo-anchored story generation. Specifically, we study four popular language models, and across about $100$K travel requests, and $200$K story generations, we observe that travel recommendations corresponding to poorer countries are less unique with fewer location references, and stories from these regions more often convey emotions of hardship and sadness compared to those from wealthier nations., Comment: Submitted to ARR - October 2024

Scene understanding is a fundamental capability needed in many domains, ranging from question-answering to robotics. Unlike recent end-to-end approaches that must explicitly learn varying compositions of the same scene, our method reasons over their constituent objects and analyzes their arrangement to infer a scene's meaning. We propose a novel approach that reasons over a scene's scene- and knowledge-graph, capturing spatial information while being able to utilize general domain knowledge in a joint graph search. Empirically, we demonstrate the feasibility of our method on the ADE20K dataset and compare it to current scene understanding approaches.

We investigate the cosmic evolution of the Universe across different cosmological epochs in exponential Weyl-type $f(Q, T)$ gravity model. The theoretical analysis involves a detailed dynamical system approach, where we define dimensionless variables and derive a system of linear differential equations to identify critical points corresponding to the radiation, matter and de Siter phase. The findings show the transition from deceleration to acceleration phase, with stable and unstable critical points characterizing different phases of the evolution. In the second approach, we validate the theoretical predictions by using observational data from Cosmic Chronometers ($CC$) and $Pantheon^+$ datasets. We constrain the Hubble parameter and subsequently analysed the other cosmological and geometrical parameters. In this approach also, the transition from deceleration to acceleration has been confirmed, with the equation of state (EoS) parameter approaching $\Lambda$CDM at late times. The further validate this, we present the behaviour of state finder pair. We obtain the age of the Universe $13.81$ Gyr according to $CC$ data and $13.96$ Gyr with the $Pantheon^+$ dataset. The model behaviour in both the approaches shows strong agreement in the late-time behavior of the Universe. The evolutionary behaviour of Hubble parameter and distance modulus, reinforcing the reliability of the Weyl-type $f(Q, T)$ gravity model in describing the expansion history of Universe., Comment: 17 pages, 18 figures

Due to the dynamic nature of financial markets, maintaining models that produce precise predictions over time is difficult. Often the goal isn't just point prediction but determining uncertainty. Quantifying uncertainty, especially the aleatoric uncertainty due to the unpredictable nature of market drivers, helps investors understand varying risk levels. Recently, quantile regression forests (QRF) have emerged as a promising solution: Unlike most basic quantile regression methods that need separate models for each quantile, quantile regression forests estimate the entire conditional distribution of the target variable with a single model, while retaining all the salient features of a typical random forest. We introduce a novel approach to compute quantile regressions from random forests that leverages the proximity (i.e., distance metric) learned by the model and infers the conditional distribution of the target variable. We evaluate the proposed methodology using publicly available datasets and then apply it towards the problem of forecasting the average daily volume of corporate bonds. We show that using quantile regression using Random Forest proximities demonstrates superior performance in approximating conditional target distributions and prediction intervals to the original version of QRF. We also demonstrate that the proposed framework is significantly more computationally efficient than traditional approaches to quantile regressions., Comment: 9 pages, 5 figures, 3 tables

Rapid advancements in GPU computational power has outpaced memory capacity and bandwidth growth, creating bottlenecks in Large Language Model (LLM) inference. Post-training quantization is the leading method for addressing memory-related bottlenecks in LLM inference, but it suffers from significant performance degradation below 4-bit precision. This paper addresses these challenges by investigating the pretraining of low-bitwidth models specifically Ternary Language Models (TriLMs) as an alternative to traditional floating-point models (FloatLMs) and their post-training quantized versions (QuantLMs). We present Spectra LLM suite, the first open suite of LLMs spanning multiple bit-widths, including FloatLMs, QuantLMs, and TriLMs, ranging from 99M to 3.9B parameters trained on 300B tokens. Our comprehensive evaluation demonstrates that TriLMs offer superior scaling behavior in terms of model size (in bits). Surprisingly, at scales exceeding one billion parameters, TriLMs consistently outperform their QuantLM and FloatLM counterparts for a given bit size across various benchmarks. Notably, the 3.9B parameter TriLM matches the performance of the FloatLM 3.9B across all benchmarks, despite having fewer bits than FloatLM 830M. Overall, this research provides valuable insights into the feasibility and scalability of low-bitwidth language models, paving the way for the development of more efficient LLMs. To enhance understanding of low-bitwidth models, we are releasing 500+ intermediate checkpoints of the Spectra suite at https://github.com/NolanoOrg/SpectraSuite., Comment: 42 pages, 21 figures, and 13 tables

People with visual impairments face numerous challenges in their daily lives, including mobility, access to information, independent living, and employment. Artificial Intelligence (AI) with Computer Vision (CV) has the potential to improve their daily lives, provide them with necessary independence, and it will also spawn new opportunities in education and employment. However, while many such AI/CV-based mobile applications are now available, these apps are still not the preferred choice amongst visually impaired persons and are generally limited to advanced users only, due to certain limitations. This study evaluates the challenges faced by visually impaired persons when using AI/CV-based mobile apps. Four popular AI/CV- based apps, namely Seeing AI, Supersense, Envision and Lookout, are assessed by blind and low-vision users. Hence these mobile applications are evaluated on a set of parameters, including generic parameters based on the Web Content Accessibility Guidelines (WCAG) and specific parameters related to mobile app testing. The evaluation not only focused on the guidelines but also on the feedback that was gathered from these users on parameters covering the apps' accuracy, response time, reliability, accessibility, privacy, energy efficiency and usability. The paper also identifies the areas of improvement in the development and innovation of these assistive apps. This work will help developers create better accessible AI-based apps for the visually impaired., Comment: 13 pages, 12 tables, Published in ITU Journal on Future and Evolving Technologies, Volume 4, Issue 4, December 2023, https://www.itu.int/dms_pub/itu-s/opb/jnl/S-JNL-VOL4.ISSUE4-2023-A45-PDF-E.pdf

Unlike reinforcement learning (RL) agents, humans remain capable multitaskers in changing environments. In spite of only experiencing the world through their own observations and interactions, people know how to balance focusing on tasks with learning about how changes may affect their understanding of the world. This is possible by choosing to solve tasks in ways that are interesting and generally informative beyond just the current task. Motivated by this, we propose an agent influence framework for RL agents to improve the adaptation efficiency of external models in changing environments without any changes to the agent's rewards. Our formulation is composed of two self-contained modules: interest fields and behavior shaping via interest fields. We implement an uncertainty-based interest field algorithm as well as a skill-sampling-based behavior-shaping algorithm to use in testing this framework. Our results show that our method outperforms the baselines in terms of external model adaptation on metrics that measure both efficiency and performance.

This study explores the relationship between informational support seeking questions, responses, and helpfulness ratings in online health communities. We created a labeled data set of question-response pairs and developed multimodal machine learning and deep learning models to reliably predict informational support questions and responses. We employed explainable AI to reveal the emotions embedded in informational support exchanges, demonstrating the importance of emotion in providing informational support. This complex interplay between emotional and informational support has not been previously researched. The study refines social support theory and lays the groundwork for the development of user decision aids. Further implications are discussed., Comment: 37 pages, 15 figures

Many neurological conditions, e.g., a stroke, can cause patients to experience upper limb (UL) motor impairments that hinder their daily activities. For such patients, while rehabilitation therapy is key for regaining autonomy and restoring mobility, its long-term nature entails ongoing time commitment and it is often not sufficiently engaging. Virtual reality (VR) can transform rehabilitation therapy into engaging game-like tasks that can be tailored to patient-specific activities, set goals, and provide rehabilitation assessment. Yet, most VR systems lack built-in methods to track progress over time and alter rehabilitation programs accordingly. We propose using arm kinematic modeling and capability maps to allow a VR system to understand a user's physical capability and limitation. Next, we suggest two use cases for the VR system to utilize the user's capability map for tailoring rehabilitation programs. Finally, for one use case, it is shown that the VR system can emphasize and assess the use of specific UL joints., Comment: 4 pages, 4 figures. Paper accepted at IEEE International Conference on Engineering in Medicine & Biology Society, 2024

Off-road navigation is a challenging problem both at the planning level to get a smooth trajectory and at the control level to avoid flipping over, hitting obstacles, or getting stuck at a rough patch. There have been several recent works using classical approaches involving depth map prediction followed by smooth trajectory planning and using a controller to track it. We design an end-to-end reinforcement learning (RL) system for an autonomous vehicle in off-road environments using a custom-designed simulator in the Unity game engine. We warm-start the agent by imitating a rule-based controller and utilize Proximal Policy Optimization (PPO) to improve the policy based on a reward that incorporates Control Barrier Functions (CBF), facilitating the agent's ability to generalize effectively to real-world scenarios. The training involves agents concurrently undergoing domain-randomized trials in various environments. We also propose a novel simulation environment to replicate off-road driving scenarios and deploy our proposed approach on a real buggy RC car. Videos and additional results: https://sites.google.com/view/wroom-utd/home

With the STAR experiment at the BNL Relativisic Heavy Ion Collider, we characterize $\sqrt{s_\mathrm{NN}}$ = 200 GeV p+Au collisions by event activity (EA) measured within the pseudorapidity range $eta$ $in$ [-5, -3.4] in the Au-going direction and report correlations between this EA and hard- and soft- scale particle production at midrapidity ($\eta$ $\in$ [-1, 1]). At the soft scale, charged particle production in low-EA p+Au collisions is comparable to that in p+p collisions and increases monotonically with increasing EA. At the hard scale, we report measurements of high transverse momentum (pT) jets in events of different EAs. In contrast with the soft particle production, high-pT particle production and EA are found to be inversely related. To investigate whether this is a signal of jet quenching in high-EA events, we also report ratios of pT imbalance and azimuthal separation of dijets in high- and low-EA events. Within our measurement precision, no significant differences are observed, disfavoring the presence of jet quenching in the highest 30% EA p+Au collisions at $\sqrt{s_\mathrm{NN}}$ = 200 GeV., Comment: 12 page, 9 figures

This paper presents IITP-VDLand, a comprehensive dataset of Decentraland parcels sourced from diverse platforms. Unlike existing datasets which have limited attributes and records, IITP-VDLand offers a rich array of attributes, encompassing parcel characteristics, trading history, past activities, transactions, and social media interactions. Alongside, we introduce a key attribute in the dataset, namely Rarity score, which measures the uniqueness of each parcel within the virtual world. Addressing the significant challenge posed by the dispersed nature of this data across various sources, we employ a systematic approach, utilizing both available APIs and custom scripts, to gather it. Subsequently, we meticulously curate and organize the information into four distinct segments: (1) Characteristics Data-Fragment, (2) OpenSea Trading History Data-Fragment, (3) Ethereum Activity Transactions Data-Fragment, and (4) Social Media Data-Fragment. We envisage that this dataset would serve as a robust resource for training machine- and deep-learning models specifically designed to address real-world challenges within the domain of Decentraland parcels. The performance benchmarking of more than 20 state-of-the-art price prediction models on our dataset yields promising results, achieving a maximum R2 score of 0.8251 and an accuracy of 74.23% in case of Extra Trees Regressor and Classifier. The key findings reveal that the ensemble models performs better than both deep learning and linear models for our dataset. We observe a significant impact of coordinates, geographical proximity, rarity score, and few other economic indicators on the prediction of parcel prices.

In deep reinforcement learning (RL) research, there has been a concerted effort to design more efficient and productive exploration methods while solving sparse-reward problems. These exploration methods often share common principles (e.g., improving diversity) and implementation details (e.g., intrinsic reward). Prior work found that non-stationary Markov decision processes (MDPs) require exploration to efficiently adapt to changes in the environment with online transfer learning. However, the relationship between specific exploration characteristics and effective transfer learning in deep RL has not been characterized. In this work, we seek to understand the relationships between salient exploration characteristics and improved performance and efficiency in transfer learning. We test eleven popular exploration algorithms on a variety of transfer types -- or ``novelties'' -- to identify the characteristics that positively affect online transfer learning. Our analysis shows that some characteristics correlate with improved performance and efficiency across a wide range of transfer tasks, while others only improve transfer performance with respect to specific environment changes. From our analysis, make recommendations about which exploration algorithm characteristics are best suited to specific transfer situations.

This study aims to compare the effectiveness of a robust ensemble model with the state-of-the-art ONE-PEACE Large Language Model (LLM) for accurate detection of sidewalks. Accurate sidewalk detection is crucial in improving road safety and urban planning. The study evaluated the model's performance on Cityscapes, Ade20k, and the Boston Dataset. The results showed that the ensemble model performed better than the individual models, achieving mean Intersection Over Union (mIOU) scores of 93.1\%, 90.3\%, and 90.6\% on these datasets under ideal conditions. Additionally, the ensemble model maintained a consistent level of performance even in challenging conditions such as Salt-and-Pepper and Speckle noise, with only a gradual decrease in efficiency observed. On the other hand, the ONE-PEACE LLM performed slightly better than the ensemble model in ideal scenarios but experienced a significant decline in performance under noisy conditions. These findings demonstrate the robustness and reliability of the ensemble model, making it a valuable asset for improving urban infrastructure related to road safety and curb space management. This study contributes positively to the broader context of urban health and mobility.

Task-oriented grasping of unfamiliar objects is a necessary skill for robots in dynamic in-home environments. Inspired by the human capability to grasp such objects through intuition about their shape and structure, we present a novel zero-shot task-oriented grasping method leveraging a geometric decomposition of the target object into simple, convex shapes that we represent in a graph structure, including geometric attributes and spatial relationships. Our approach employs minimal essential information - the object's name and the intended task - to facilitate zero-shot task-oriented grasping. We utilize the commonsense reasoning capabilities of large language models to dynamically assign semantic meaning to each decomposed part and subsequently reason over the utility of each part for the intended task. Through extensive experiments on a real-world robotics platform, we demonstrate that our grasping approach's decomposition and reasoning pipeline is capable of selecting the correct part in 92% of the cases and successfully grasping the object in 82% of the tasks we evaluate. Additional videos, experiments, code, and data are available on our project website: https://shapegrasp.github.io/., Comment: 8 pages

Human-robot teams involve humans and robots collaborating to achieve tasks under various environmental conditions. Successful teaming will require robots to adapt autonomously to a human teammate's internal state. An important element of such adaptation is the ability to estimate the human teammates' workload in unknown situations. Existing workload models use machine learning to model the relationships between physiological metrics and workload; however, these methods are susceptible to individual differences and are heavily influenced by other factors. These methods cannot generalize to unknown tasks, as they rely on standard machine learning approaches that assume data consists of independent and identically distributed (IID) samples. This assumption does not necessarily hold for estimating workload for new tasks. A survey of non-IID machine learning techniques is presented, where commonly used techniques are evaluated using three criteria: portability, model complexity, and adaptability. These criteria are used to argue which techniques are most applicable for estimating workload for unknown tasks in dynamic, real-time environments.

This manuscript presents a methodical examination of the utilization of Artificial Intelligence in the assessment of emotions in texts related to healthcare, with a particular focus on the incorporation of Natural Language Processing and deep learning technologies. We scrutinize numerous research studies that employ AI to augment sentiment analysis, categorize emotions, and forecast patient outcomes based on textual information derived from clinical narratives, patient feedback on medications, and online health discussions. The review demonstrates noteworthy progress in the precision of algorithms used for sentiment classification, the prognostic capabilities of AI models for neurodegenerative diseases, and the creation of AI-powered systems that offer support in clinical decision-making. Remarkably, the utilization of AI applications has exhibited an enhancement in personalized therapy plans by integrating patient sentiment and contributing to the early identification of mental health disorders. There persist challenges, which encompass ensuring the ethical application of AI, safeguarding patient confidentiality, and addressing potential biases in algorithmic procedures. Nevertheless, the potential of AI to revolutionize healthcare practices is unmistakable, offering a future where healthcare is not only more knowledgeable and efficient but also more empathetic and centered around the needs of patients. This investigation underscores the transformative influence of AI on healthcare, delivering a comprehensive comprehension of its role in examining emotional content in healthcare texts and highlighting the trajectory towards a more compassionate approach to patient care. The findings advocate for a harmonious synergy between AI's analytical capabilities and the human aspects of healthcare.

Using the cosmological date sets, the cosmological parameters are constrained in this paper, with some well known form of Hubble parameter. To understand the dynamics of the Weyl type $f(Q,T)$, functional form $f(Q,T)$ has been introduced, where $Q$ and $T$ respectively represents the nonmetricity scalar and trace of energy-momentum tensor. Using the constrained values of the parameters, the other geometrical parameters are analysed and the accelerating behaviour has been shown. Further to get the complete evolutionary behaviour of the Universe, the dynamical system analysis has been performed., Comment: 17 pages, 7 figures, 4 tables. Suggestions and comments are welcome

A non-zero $\mathbb{F}$-linear map from a finite-dimensional commutative $\mathbb{F}$-algebra to $\mathbb{F}$ is called an $\mathbb{F}$-valued trace if its kernel does not contain any non-zero ideals. In this article, we utilize an $\mathbb{F}_2$-valued trace of the $\mathbb{F}_2$-algebra $\mathcal{R}_2:=\mathbb{F}_2[x]/\langle x^3-x\rangle$ to study binary subfield code $\mathcal{C}_D^{(2)}$ of $\mathcal{C}_D:=\{\left(x\cdot d\right)_{d\in D}: x\in \mathcal{R}_2^m\}$ for each defining set $D$ derived from a certain simplicial complex. For $m\in \mathbb{N}$ and $X\subseteq \{1, 2, \dots, m\}$, define $\Delta_X:=\{v\in \mathbb{F}_2^m: \Supp(v)\subseteq X\}$ and $D:=(1+u^2)D_1+u^2D_2+(u+u^2)D_3,$ a subset of $\mathcal{R}_2^m,$ where $u=x+\langle x^3-x\rangle, D_1\in \{\Delta_L, \Delta_L^c\},\, D_2\in \{\Delta_M, \Delta_M^c\}$ and $ D_3\in \{\Delta_N, \Delta_N^c\}$, for $L, M, N\subseteq \{1, 2, \dots, m\}.$ The parameters and the Hamming weight distribution of the binary subfield code $\mathcal{C}_D^{(2)}$ of $\mathcal{C}_D$ are determined for each $D.$ These binary subfield codes are minimal under certain mild conditions on the cardinalities of $L, M$ and $N$. Moreover, most of these codes are distance-optimal. Consequently, we obtain a few infinite families of minimal, self-orthogonal and distance-optimal binary linear codes that are either $2$-weight or $4$-weight. It is worth mentioning that we have obtained several new distance-optimal binary linear codes.

We consider the fundamental task of network exploration. A network is modeled as a simple connected undirected n-node graph with unlabeled nodes, and all ports at any node of degree d are arbitrarily numbered 0,.....,d-1. Each of two identical mobile agents, initially situated at distinct nodes, has to visit all nodes and stop. Agents execute the same deterministic algorithm and move in synchronous rounds: in each round, an agent can either remain at the same node or move to an adjacent node. Exploration must be collision-free: in every round at most one agent can be at any node. We assume that agents have vision of radius 2: an awake agent situated at a node v can see the subgraph induced by all nodes at a distance at most 2 from v, sees all port numbers in this subgraph, and the agents located at these nodes. Agents do not know the entire graph but they know an upper bound n on its size. The time of an exploration is the number of rounds since the wakeup of the later agent to the termination by both agents. We show a collision-free exploration algorithm working in time polynomial in n, for arbitrary graphs of size larger than 2. Moreover, we show that if agents have only vision of radius 1, then collision-free exploration is impossible, e.g., in any tree of diameter 2.

Flow coefficients ($v_2$ and $v_3$) are measured in high-multiplicity $p$+Au, $d$+Au, and $^{3}$He$+$Au collisions at a center-of-mass energy of $\sqrt{s_{_{\mathrm{NN}}}}$ = 200 GeV using the STAR detector. The measurements utilize two-particle correlations with a pseudorapidity requirement of $|\eta| <$ 0.9 and a pair gap of $|\Delta\eta|>1.0$. The primary focus is on analysis methods, particularly the subtraction of non-flow contributions. Four established non-flow subtraction methods are applied to determine $v_n$, validated using the HIJING event generator. $v_n$ values are compared across the three collision systems at similar multiplicities; this comparison cancels the final state effects and isolates the impact of initial geometry. While $v_2$ values show differences among these collision systems, $v_3$ values are largely similar, consistent with expectations of subnucleon fluctuations in the initial geometry. The ordering of $v_n$ differs quantitatively from previous measurements using two-particle correlations with a larger rapidity gap, which, according to model calculations, can be partially attributed to the effects of longitudinal flow decorrelations. The prospects for future measurements to improve our understanding of flow decorrelation and subnucleonic fluctuations are also discussed., Comment: 29 pages, 25 figures