Search

Research has shown the effectiveness of reasoning (e.g., Chain-of-Thought), planning (e.g., SelfAsk), and retrieval augmented generation strategies to improve the performance of Large Language Models (LLMs) on various tasks, such as question answering. However, using a single fixed strategy to answer different kinds of questions is suboptimal in performance and inefficient in terms of generated output tokens and performed retrievals. In our work, we propose a novel technique DyPlan, to induce a dynamic strategy selection process in LLMs, to improve performance and reduce costs in question-answering. DyPlan incorporates an initial decision step to select the most suitable strategy conditioned on the input question and guides the LLM's response generation accordingly. We extend DyPlan to DyPlan-verify, adding an internal verification and correction process to further enrich the generated answer. Experiments on three prominent multi-hop question answering (MHQA) datasets reveal how DyPlan can improve model performance by 7-13% while reducing the cost by 11-32% relative to the best baseline model., Comment: Under review at ACL Rolling Review

In this paper, a heuristic for a heterogeneous min-max multi-vehicle multi-depot traveling salesman problem is proposed, wherein heterogeneous vehicles start from given depot locations and need to cover a given set of targets. In the considered problem, vehicles can be structurally heterogeneous due to different vehicle speeds and/or functionally heterogeneous due to different vehicle-target assignments originating from different sensing capabilities of vehicles. The proposed heuristic for the considered problem has three stages: an initialization stage to generate an initial feasible solution, a local search stage to improve the incumbent solution by searching through different neighborhoods, and a perturbation/shaking stage, wherein the incumbent solution is perturbed to break from a local minimum. In this study, three types of neighborhood searches are employed. Furthermore, two different methods for constructing the initial feasible solution are considered, and multiple variations in the neighborhoods considered are explored in this study. The considered variations and construction methods are evaluated on a total of 128 instances generated with varying vehicle-to-target ratios, distribution for generating the targets, and vehicle-target assignment and are benchmarked against the best-known heuristic for this problem. Two heuristics were finally proposed based on the importance provided to objective value or computation time through extensive computational studies.

We present a novel experimental approach to detect dark matter by probing Yukawa interactions, commonly referred to as a fifth force, between dark matter and baryonic matter. Our method involves optically levitating nanoparticles within a Bessel-Gaussian beam to detect minute forces exerted by potential dark matter interaction with test masses. The non-diffracting properties of Bessel-Gaussian beams, combined with feedback cooling techniques, provide exceptional sensitivity to small perturbations in the motion of the nanoparticles. This setup allows for precise control over trapping conditions and enhances the detection sensitivity to forces on the order of \(10^{-18}\) N. We explore the parameter space of the Yukawa interaction, focusing on the coupling strength (\(\alpha\)) and interaction range (\(\lambda\)), and discuss the potential of this experiment to place new constraints on dark matter couplings, complementing existing direct detection methods., Comment: 22 pages, 7 figures, 1 table

In this article we report on the application of the Quantum Approximate Optimization Algorithm (QAOA) to solve the unweighted MaxCut problem on tree-structured graphs. Specifically, we utilize the Nauty (No Automorphisms, Yes?) package to identify graph automorphisms, focusing on determining edge equivalence classes. These equivalence classes also correspond to symmetries in the terms of the associated Ising Hamiltonian. By exploiting these symmetries, we achieve a significant reduction in the complexity of the Hamiltonian, thereby facilitating more efficient quantum simulations. We conduct benchmark experiments on graphs with up to 34 nodes on memory and CPU intensive TPU provided by google Colab, applying QAOA with a single layer ($p=1$). The approximation ratios obtained from both the full and symmetry-reduced Hamiltonians are systematically compared. Our results show that using automorphism-based symmetries to reduce the Pauli terms in the Hamiltonian can significantly decrease computational overhead without compromising the quality of the solutions obtained., Comment: 13 pages, 2 figures

We introduce Planning-guided Retrieval Augmented Generation (Plan$\times$RAG), a novel framework that augments the \emph{retrieve-then-reason} paradigm of existing RAG frameworks to \emph{plan-then-retrieve}. Plan$\times$RAG formulates a reasoning plan as a directed acyclic graph (DAG), decomposing queries into interrelated atomic sub-queries. Answer generation follows the DAG structure, allowing significant gains in efficiency through parallelized retrieval and generation. While state-of-the-art RAG solutions require extensive data generation and fine-tuning of language models (LMs), Plan$\times$RAG incorporates frozen LMs as plug-and-play experts to generate high-quality answers. Compared to existing RAG solutions, Plan$\times$RAG demonstrates significant improvements in reducing hallucinations and bolstering attribution due to its structured sub-query decomposition. Overall, Plan$\times$RAG offers a new perspective on integrating external knowledge in LMs while ensuring attribution by design, contributing towards more reliable LM-based systems., Comment: 22 pages, preprint

The use of social media applications, hate speech engagement, and public debates among teenagers, primarily by university and college students, is growing day by day. The feelings of tremendous stress, anxiety, and depression via social media among our youths have a direct impact on their daily lives and personal workspace apart from delayed sleep, social media addictions, and memory loss. The use of NO phone times and NO phone zones is now popular in workplaces and family cultures. The use of hate speech, negotiations, and toxic words can lead to verbal abuse and cybercrime. Growing concern of mobile device security, cyberbullying, ransomware attacks, and mental health issues are another serious impact of social media among university students. The future challenges including health issues of social media use and hate speech has a serious impact on livelihood, freedom, and diverse communities of university students. Our case study is related to social media use and hate speech related to public debates over university students. We have presented the analysis and impact of social media and hate speech with several conclusions, cybercrimes, and components. The use of questionnaires for collecting primary data over university students help in the analysis of case study. The conclusion of case study and future scope of the research is extremely important to counter negative impacts., Comment: 12 pages, 7 figures

Gastrointestinal (GI) diseases represent a significant global health concern, with Capsule Endoscopy (CE) offering a non-invasive method for diagnosis by capturing a large number of GI tract images. However, the sheer volume of video frames necessitates automated analysis to reduce the workload on doctors and increase the diagnostic accuracy. In this paper, we present CapsuleNet, a deep learning model developed for the Capsule Vision 2024 Challenge, aimed at classifying 10 distinct GI abnormalities. Using a highly imbalanced dataset, we implemented various data augmentation strategies, reducing the data imbalance to a manageable level. Our model leverages a pretrained EfficientNet-b7 backbone, tuned with additional layers for classification and optimized with PReLU activation functions. The model demonstrated superior performance on validation data, achieving a micro accuracy of 84.5% and outperforming the VGG16 baseline across most classes. Despite these advances, challenges remain in classifying certain abnormalities, such as Erythema. Our findings suggest that CNN-based models like CapsuleNet can provide an efficient solution for GI tract disease classification, particularly when inference time is a critical factor., Comment: Capsule Vision 2024 Challenge

Factuality evaluation aims to detect factual errors produced by language models (LMs) and hence guide the development of more factual models. Towards this goal, we train a factuality evaluator, FenCE, that provides LM generators with claim-level factuality feedback. We conduct data augmentation on a combination of public judgment datasets to train FenCE to (1) generate textual critiques along with scores and (2) make claim-level judgment based on diverse source documents obtained by various tools. We then present a framework that leverages FenCE to improve the factuality of LM generators by constructing training data. Specifically, we generate a set of candidate responses, leverage FenCE to revise and score each response without introducing lesser-known facts, and train the generator by preferring highly scored revised responses. Experiments show that our data augmentation methods improve the evaluator's accuracy by 2.9% on LLM-AggreFact. With FenCE, we improve Llama3-8B-chat's factuality rate by 14.45% on FActScore, outperforming state-of-the-art factuality finetuning methods by 6.96%.

Automatic Speech Recognition (ASR) systems have been examined and shown to exhibit biases toward particular groups of individuals, influenced by factors such as demographic traits, accents, and speech styles. Noise can disproportionately impact speakers with certain accents, dialects, or speaking styles, leading to biased error rates. In this work, we introduce a novel framework DENOASR, which is a selective denoising technique to reduce the disparity in the word error rates between the two gender groups, male and female. We find that a combination of two popular speech denoising techniques, viz. DEMUCS and LE, can be effectively used to mitigate ASR disparity without compromising their overall performance. Experiments using two state-of-the-art open-source ASRs - OpenAI WHISPER and NVIDIA NEMO - on multiple benchmark datasets, including TIE, VOX-POPULI, TEDLIUM, and FLEURS, show that there is a promising reduction in the average word error rate gap across the two gender groups. For a given dataset, the denoising is selectively applied on speech samples having speech intelligibility below a certain threshold, estimated using a small validation sample, thus ameliorating the need for large-scale human-written ground-truth transcripts. Our findings suggest that selective denoising can be an elegant approach to mitigate biases in present-day ASR systems., Comment: Paper accepted at IEEE ICKG 2024

Digital payment systems have revolutionized financial transactions, offering unparalleled convenience and accessibility to users worldwide. However, the increasing popularity of these platforms has also attracted malicious actors seeking to exploit their vulnerabilities for financial gain. To address this challenge, robust and adaptable scam detection mechanisms are crucial for maintaining the trust and safety of digital payment ecosystems. This paper presents a comprehensive approach to scam detection, focusing on the Unified Payments Interface (UPI) in India, Google Pay (GPay) as a specific use case. The approach leverages Large Language Models (LLMs) to enhance scam classification accuracy and designs a digital assistant to aid human reviewers in identifying and mitigating fraudulent activities. The results demonstrate the potential of LLMs in augmenting existing machine learning models and improving the efficiency, accuracy, quality, and consistency of scam reviews, ultimately contributing to a safer and more secure digital payment landscape. Our evaluation of the Gemini Ultra model on curated transaction data showed a 93.33% accuracy in scam classification. Furthermore, the model demonstrated 89% accuracy in generating reasoning for these classifications. A promising fact, the model identified 32% new accurate reasons for suspected scams that human reviewers had not included in the review notes., Comment: 10 pages, 7 figures

The t-Distributed Stochastic Neighbor Embedding (t-SNE) has emerged as a popular dimensionality reduction technique for visualizing high-dimensional data. It computes pairwise similarities between data points by default using an RBF kernel and random initialization (in low-dimensional space), which successfully captures the overall structure but may struggle to preserve the local structure efficiently. This research proposes a novel approach called the Modified Isolation Kernel (MIK) as an alternative to the Gaussian kernel, which is built upon the concept of the Isolation Kernel. MIK uses adaptive density estimation to capture local structures more accurately and integrates robustness measures. It also assigns higher similarity values to nearby points and lower values to distant points. Comparative research using the normal Gaussian kernel, the isolation kernel, and several initialization techniques, including random, PCA, and random walk initializations, are used to assess the proposed approach (MIK). Additionally, we compare the computational efficiency of all $3$ kernels with $3$ different initialization methods. Our experimental results demonstrate several advantages of the proposed kernel (MIK) and initialization method selection. It exhibits improved preservation of the local and global structure and enables better visualization of clusters and subclusters in the embedded space. These findings contribute to advancing dimensionality reduction techniques and provide researchers and practitioners with an effective tool for data exploration, visualization, and analysis in various domains.

The performance of a text-to-speech (TTS) synthesis model depends on various factors, of which the quality of the training data is of utmost importance. Millions of data are collected around the globe for various languages, but resources for Indian languages are few. Although there are many efforts involved in data collection, a common set of protocols for data collection becomes necessary for building TTS systems in Indian languages primarily because of the need for a uniform development of TTS systems across languages. In this paper, we present our learnings on data collection efforts' for Indic languages over 15 years. These databases have been used in unit selection synthesis, hidden Markov model based, and end-to-end frameworks, and for generating prosodically rich TTS systems. The most significant feature of the data collected is that data purity enables building high-quality TTS systems with a comparatively small dataset compared to that of European/Chinese languages., Comment: Submitted to ICASSP 2025

In this paper, we study the problem of finding an envy-free allocation of indivisible goods among multiple agents. EFX, which stands for envy-freeness up to any good, is a well-studied relaxation of the envy-free allocation problem and has been shown to exist for specific scenarios. For instance, EFX is known to exist when there are only three agents [Chaudhury et al, EC 2020], and for any number of agents when there are only two types of valuations [Mahara, Discret. Appl. Math 2023]. We show that EFX allocations exist for any number of agents when there are at most three types of additive valuations.

Large Language Models (LLMs) have demonstrated remarkable performance across various domains, including healthcare. However, their ability to effectively represent structured non-textual data, such as the alphanumeric medical codes used in records like ICD-10 or SNOMED-CT, is limited and has been particularly exposed in recent research. This paper examines the challenges LLMs face in processing medical codes due to the shortcomings of current tokenization methods. As a result, we introduce the UniStruct architecture to design a multimodal medical foundation model of unstructured text and structured data, which addresses these challenges by adapting subword tokenization techniques specifically for the structured medical codes. Our approach is validated through model pre-training on both an extensive internal medical database and a public repository of structured medical records. Trained on over 1 billion tokens on the internal medical database, the proposed model achieves up to a 23% improvement in evaluation metrics, with around 2% gain attributed to our proposed tokenization. Additionally, when evaluated on the EHRSHOT public benchmark with a 1/1000 fraction of the pre-training data, the UniStruct model improves performance on over 42% of the downstream tasks. Our approach not only enhances the representation and generalization capabilities of patient-centric models but also bridges a critical gap in representation learning models' ability to handle complex structured medical data, alongside unstructured text., Comment: NeurIPS 2024 Workshop on Unifying Representations in Neural Models (UniReps 2024)

Messenger RNA (mRNA) plays a crucial role in protein synthesis, with its codon structure directly impacting biological properties. While Language Models (LMs) have shown promise in analyzing biological sequences, existing approaches fail to account for the hierarchical nature of mRNA's codon structure. We introduce Hierarchical Encoding for mRNA Language Modeling (HELM), a novel pre-training strategy that incorporates codon-level hierarchical structure into language model training. HELM modulates the loss function based on codon synonymity, aligning the model's learning process with the biological reality of mRNA sequences. We evaluate HELM on diverse mRNA datasets and tasks, demonstrating that HELM outperforms standard language model pre-training as well as existing foundation model baselines on six diverse downstream property prediction tasks and an antibody region annotation tasks on average by around 8\%. Additionally, HELM enhances the generative capabilities of language model, producing diverse mRNA sequences that better align with the underlying true data distribution compared to non-hierarchical baselines.

Understanding the structural and functional characteristics of proteins are crucial for developing preventative and curative strategies that impact fields from drug discovery to policy development. An important and popular technique for examining how amino acids make up these characteristics of the protein sequences with position-specific scoring (PSS). While the string kernel is crucial in natural language processing (NLP), it is unclear if string kernels can extract biologically meaningful information from protein sequences, despite the fact that they have been shown to be effective in the general sequence analysis tasks. In this work, we propose a weighted PSS kernel matrix (or W-PSSKM), that combines a PSS representation of protein sequences, which encodes the frequency information of each amino acid in a sequence, with the notion of the string kernel. This results in a novel kernel function that outperforms many other approaches for protein sequence classification. We perform extensive experimentation to evaluate the proposed method. Our findings demonstrate that the W-PSSKM significantly outperforms existing baselines and state-of-the-art methods and achieves up to 45.1\% improvement in classification accuracy.

Electroencephalography (EEG)--based turn intention prediction for lower limb movement is important to build an efficient brain-computer interface (BCI) system. This study investigates the feasibility of intention detection of left-turn, right-turn, and straight walk by utilizing EEG signals obtained before the event occurrence. Synchronous data was collected using 31-channel EEG and IMU-based motion capture systems for nine healthy participants while performing left-turn, right-turn, and straight walk movements. EEG data was preprocessed with steps including Artifact Subspace Reconstruction (ASR), re-referencing, and Independent Component Analysis (ICA) to remove data noise. Feature extraction from the preprocessed EEG data involved computing various statistical measures (mean, median, standard deviation, skew, and kurtosis), and Hjorth parameters (activity, mobility, and complexity). Further, the feature selection was performed using the Random forest algorithm for the dimensionality reduction. The feature set obtained was utilized for 3-class classification using XG boost, gradient boosting, and support vector machine (SVM) with RBF kernel classifiers in a five-fold cross-validation scheme. Using the proposed intention detection methodology, the SVM classifier using an EEG window of 1.5 s and 0 s time-lag has the best decoding performance with mean accuracy, precision, and recall of 81.23%, 85.35%, and 83.92%, respectively, across the nine participants. The decoding analysis shows the feasibility of turn intention prediction for lower limb movement using the EEG signal before the event onset., Comment: *Equal contributions by the authors

Nonintrusive projection-based reduced order models (ROMs) are essential for dynamics prediction in multi-query applications where access to the source of the underlying full order model (FOM) is unavailable; that is, FOM is a black-box. This article proposes a learn-then-project approach for nonintrusive model reduction. In the first step of this approach, high-dimensional stable sparse learned differential operators (S-LDOs) are determined using the generated data. In the second step, the ordinary differential equations, comprising these S-LDOs, are used with suitable dimensionality reduction and low-dimensional subspace projection methods to provide equations for the evolution of reduced states. This approach allows easy integration into the existing intrusive ROM framework to enable nonintrusive model reduction while allowing the use of Petrov-Galerkin projections. The applicability of the proposed approach is demonstrated for Galerkin and LSPG projection-based ROMs through three numerical experiments: 1-D advection equation, 1-D Burgers equation and 2-D advection equation. The results indicate that the proposed nonintrusive ROM strategy provides accurate and stable dynamics prediction.

Accurate prediction of RNA properties, such as stability and interactions, is crucial for advancing our understanding of biological processes and developing RNA-based therapeutics. RNA structures can be represented as 1D sequences, 2D topological graphs, or 3D all-atom models, each offering different insights into its function. Existing works predominantly focus on 1D sequence-based models, which overlook the geometric context provided by 2D and 3D geometries. This study presents the first systematic evaluation of incorporating explicit 2D and 3D geometric information into RNA property prediction, considering not only performance but also real-world challenges such as limited data availability, partial labeling, sequencing noise, and computational efficiency. To this end, we introduce a newly curated set of RNA datasets with enhanced 2D and 3D structural annotations, providing a resource for model evaluation on RNA data. Our findings reveal that models with explicit geometry encoding generally outperform sequence-based models, with an average prediction RMSE reduction of around 12% across all various RNA tasks and excelling in low-data and partial labeling regimes, underscoring the value of explicitly incorporating geometric context. On the other hand, geometry-unaware sequence-based models are more robust under sequencing noise but often require around 2-5x training data to match the performance of geometry-aware models. Our study offers further insights into the trade-offs between different RNA representations in practical applications and addresses a significant gap in evaluating deep learning models for RNA tasks.

In recent years, reinforcement learning (RL) based quadrupedal locomotion control has emerged as an extensively researched field, driven by the potential advantages of autonomous learning and adaptation compared to traditional control methods. This paper provides a comprehensive study of the latest research in applying RL techniques to develop locomotion controllers for quadrupedal robots. We present a detailed overview of the core concepts, methodologies, and key advancements in RL-based locomotion controllers, including learning algorithms, training curricula, reward formulations, and simulation-to-real transfer techniques. The study covers both gait-bound and gait-free approaches, highlighting their respective strengths and limitations. Additionally, we discuss the integration of these controllers with robotic hardware and the role of sensor feedback in enabling adaptive behavior. The paper also outlines future research directions, such as incorporating exteroceptive sensing, combining model-based and model-free techniques, and developing online learning capabilities. Our study aims to provide researchers and practitioners with a comprehensive understanding of the state-of-the-art in RL-based locomotion controllers, enabling them to build upon existing work and explore novel solutions for enhancing the mobility and adaptability of quadrupedal robots in real-world environments., Comment: 12 pages, 3 figures

Understanding the evolution of galaxies cannot exclude the important role played by the central supermassive black hole and the circumgalactic medium (CGM). Simulations have strongly suggested the negative feedback of AGN Jet/wind/outflows on the ISM/CGM of a galaxy leading to the eventual decline of star formation. However, no "smoking gun" evidence exists so far where relics of feedback, observed in any band, are consistent with the time scale of a major decline in star formation, in any sample of galaxies. Relics of any AGN-driven outflows will be observed as a faint and fuzzy structure which may be difficult to characterise by automated algorithms but trained citizen scientists can possibly perform better through their intuitive vision with additional heterogeneous data available anywhere on the Internet. RAD@home, launched on 15th April 2013, is not only the first Indian Citizen Science Research (CSR) platform in astronomy but also the only CSR publishing discoveries using any Indian telescope. We briefly report 11 CSR discoveries collected over the last eleven years. While searching for such relics we have spotted cases of offset relic lobes from elliptical and spiral, episodic radio galaxies with overlapping lobes as the host galaxy is in motion, large diffuse spiral-shaped emission, cases of jet-galaxy interaction, kinks and burls on the jets, a collimated synchrotron thread etc. Such exotic sources push the boundaries of our understanding of classical Seyferts and radio galaxies with jets and the process of discovery prepares the next generation for science with the upgraded GMRT and Square Kilometre Array Observatory (SKAO)., Comment: 14 pages, 8 figures. Accepted for publication in the Springer-Nature conference proceedings for "ISRA 2023: The Relativistic Universe: From Classical to Quantum Proceedings of the International Symposium on Recent Developments in Relativistic Astrophysics". Comments and collaborations, most welcome! Please visit #RADatHomeIndia website at radathomeindia.org

Magnetic skyrmions are topologically protected quasiparticles and have drawn much attention because of their potential applications in next-generation spintronics devices. Their inherent topological stability, nanoscale size, and efficient manipulation via spin currents make them promising candidates for high-density data storage and novel computing paradigms. We micromagnetically investigate the nucleation dynamics of magnetic skyrmion pairs excited underneath two 30 nm nanocontacts with varying separations on top of an extended Co/Pt bilayer thin film. At close separation of 100 nm, the magnetization configurations strongly interact, giving rise to the formation of stable merged skyrmion states. As the separation increases beyond 200 nm, topologically distinct metastable configurations emerge, including the coexistence of tunable skyrmion-antiskyrmion pairs through Dzyaloshinskii-Moriya interaction (DMI) strengths and current pulse amplitudes. These metastable states eventually relax into two stable skyrmions that can be independently toggled ON and OFF using a weak in-plane magnetic field, enabling complex logic operations and more flexible circuit designs. Beyond the fundamental interest in skyrmion interaction dynamics, the independent control of skyrmion-antiskyrmion states holds promise for next-generation spintronic devices, with potential applications in memory, logic, and computing.

Hospitals generate thousands of handwritten prescriptions, a practice that remains prevalent despite the availability of Electronic Medical Records (EMR). This method of record-keeping hinders the examination of long-term medication effects, impedes statistical analysis, and makes the retrieval of records challenging. Handwritten prescriptions pose a unique challenge, requiring specialized data for training models to recognize medications and their patterns of recommendation. While current handwriting recognition approaches typically employ 2-D LSTMs, recent studies have explored the use of Large Language Models (LLMs) for Optical Character Recognition (OCR). Building on this approach, we focus on extracting medication names from medical records. Our methodology MIRAGE (Multimodal Identification and Recognition of Annotations in indian GEneral prescriptions) involves fine-tuning the LLaVA 1.6 and Idefics2 models. Our research utilizes a dataset provided by Medyug Technology, consisting of 743,118 fully annotated high-resolution simulated medical records from 1,133 doctors across India. We demonstrate that our methodology exhibits 82% accuracy in medication name and dosage extraction. We provide a detailed account of our research methodology and results, notes about HWR with Multimodal LLMs, and release a small dataset of 100 medical records with labels., Comment: 8 pages, 11 figures, 2 tables

When ultracold plasma is generated using photonization of laser cooled atoms, some atoms reach only upto Rydberg states. These in turn interact with the free electrons of the plasma and get ionized further. We study the interaction of electron-Rydberg atom using potential scattering technique in quantum mechanical domain and compute the associated cross sections for Cesium atoms, analytically. We notice a close agreement with the experimental data of ionization of Rydberg atoms as reported in Phys. Rev. A 71, 013416 (2005). The experiments showed a rapid increase in ionization above a specific Rydberg state. Our theory supports the same, and also indicates that this is due to the relation between scattering length and the radius of the orbit., Comment: 10 pages, 10 figures

Sensing with RF signals such as mmWave radar has gained considerable interest in recent years. This is particularly relevant to 6G networks, which aim to integrate sensing and communication (ISAC) capabilities for enhanced functionality. The contextual information provided by such sensing, whether collected by standalone non-ISAC units or integrated within ISAC, can not only optimize cellular network assets but can also serve as a valuable tool for a wide range of applications beyond network optimization. In this context, we present a novel methodology for crowd size estimation using monostatic mmWave radar, which is capable of accurately counting large crowds that are unevenly distributed across space. Our estimation approach relies on the rigorous derivation of occlusion probabilities, which are then used to mathematically characterize the probability distributions that describe the number of agents visible to the radar as a function of the crowd size. We then estimate the true crowd size by comparing these derived mathematical models to the empirical distribution of the number of visible agents detected by the radar. This method requires minimal sensing capabilities (e.g., angle-of-arrival information is not needed), thus being well suited for either a dedicated mmWave radar or an ISAC system. Extensive numerical simulations validate our methodology, demonstrating strong performance across diverse spatial distributions and for crowd sizes of up to (and including) 30 agents. We achieve a mean absolute error (MAE) of 0.48 agents, significantly outperforming a baseline which assumes that the agents are uniformly distributed in the area. Overall, our approach holds significant promise for a variety of applications including network resource allocation, crowd management, and urban planning.

Large Language Models (LLMs) are gaining significant popularity in recent years for specialized tasks using prompts due to their low computational cost. Standard methods like prefix tuning utilize special, modifiable tokens that lack semantic meaning and require extensive training for best performance, often falling short. In this context, we propose a novel method called Semantic Knowledge Tuning (SK-Tuning) for prompt and prefix tuning that employs meaningful words instead of random tokens. This method involves using a fixed LLM to understand and process the semantic content of the prompt through zero-shot capabilities. Following this, it integrates the processed prompt with the input text to improve the model's performance on particular tasks. Our experimental results show that SK-Tuning exhibits faster training times, fewer parameters, and superior performance on tasks such as text classification and understanding compared to other tuning methods. This approach offers a promising method for optimizing the efficiency and effectiveness of LLMs in processing language tasks., Comment: Accepted in Nature Scientific Reports

In the current legal environment, it is essential to prioritize the protection and reliability of data to promote trust and effectiveness. This study examines how blockchain technology in the form of blockLAW can be applicable to investigate its effects on legal automation, cybersecurity, and ethical concerns. The decentralized ledger and unchangeable characteristics of Blockchain provide opportunities to simplify legal procedures, automate contract execution with smart contracts, and improve transparency in legal transactions. Blockchain is seen as a crucial instrument for updating legal processes while maintaining ethical standards, tackling issues like scalability, regulatory adherence, and ethical dilemmas such as privacy and fairness. The study examines recent developments and evaluates blockchain impact on legal structures, offering perspectives on its potential to enhance legal procedures and guarantee transparency in legal systems. It further emphasizes blockchain ability to redefine how legal professionals handle and protect sensitive information, leading to stronger, more effective, and reliable legal procedures. We have also discussed the technological considerations when it comes to blockchain integration into legal systems like integration planning, implementation strategies, innovations, advancements, trends with Blockchain Integration Framework for legal systems., Comment: 14 pages, 2 figures

Large-scale industrial recommendation models predict the most relevant items from catalogs containing millions or billions of options. To train these models efficiently, a small set of irrelevant items (negative samples) is selected from the vast catalog for each relevant item (positive example), helping the model distinguish between relevant and irrelevant items. Choosing the right negative sampling method is a common challenge. We address this by implementing and comparing various negative sampling methods - random, popularity-based, in-batch, mixed, adaptive, and adaptive with mixed variants - on modern sequential recommendation models. Our experiments, including hyperparameter optimization and 20x repeats on three benchmark datasets with varying popularity biases, show how the choice of method and dataset characteristics impact key model performance metrics. We also reveal that average performance metrics often hide imbalances across popularity bands (head, mid, tail). We find that commonly used random negative sampling reinforces popularity bias and performs best for head items. Popularity-based methods (in-batch and global popularity negative sampling) can offer balanced performance at the cost of lower overall model performance results. Our study serves as a practical guide to the trade-offs in selecting a negative sampling method for large-scale sequential recommendation models. Code, datasets, experimental results and hyperparameters are available at: https://github.com/apple/ml-negative-sampling., Comment: Workshop for Large Recommender Systems (LargeRecSys), 18th ACM Conference on Recommender Systems, 2024, Bari, Italy

A particle-hole symmetry protected 2D non-Hermitian Su-Schrieffer-Heeger (SSH) model is investigated. This version differs from the usual Hermitian version by the inclusion of gain and/or loss terms which are represented by complex on-site potentials. The exceptional points occur, when the dimensionless potential magnitude and the hopping amplitudes become close to unity, leading to the coalescence of eigenvalues and nontrivial eigenvector degeneracies. Furthermore, the vectored Zak phase quantization has been obtained and a topolectric RLC circuit has been analysed. If realized experimentally (in photonic and acoustic crystals), the quantization is expected to lead to an extended bulk-boundary correspondence., Comment: 22 pages, 6 Figures

This paper investigates the behavior of mutual information, entanglement negativity, and multipartite correlations in holographic RG flows, particularly during phase transitions. Mutual information provides a UV-finite measure of total correlations between subsystems, while entanglement negativity and multipartite correlations offer finer insights into quantum structures, especially near critical points. Through numerical simulations, we show that while mutual information remains relatively smooth, both entanglement negativity and multipartite correlations exhibit sharp changes near phase transitions. These results support the hypothesis that multipartite correlations play a dominant role in signaling critical phenomena in strongly coupled quantum systems., Comment: 21 pages, 5 figures

Curating datasets that span multiple languages is challenging. To make the collection more scalable, researchers often incorporate one or more imperfect classifiers in the process, like language identification models. These models, however, are prone to failure, resulting in some language subsets being unreliable for downstream tasks. We introduce a statistical test, the Preference Proportion Test, for identifying such unreliable subsets. By annotating only 20 samples for a language subset, we're able to identify systematic transcription errors for 10 language subsets in a recent large multilingual transcribed audio dataset, X-IPAPack (Zhu et al., 2024). We find that filtering this low-quality data out when training models for the downstream task of phonetic transcription brings substantial benefits, most notably a 25.7% relative improvement on transcribing recordings in out-of-distribution languages. Our method lays a path forward for systematic and reliable multilingual dataset auditing., Comment: 16 pages, 6 figures

Laser-based surgical ablation relies heavily on surgeon involvement, restricting precision to the limits of human error. The interaction between laser and tissue is governed by various laser parameters that control the laser irradiance on the tissue, including the laser power, distance, spot size, orientation, and exposure time. This complex interaction lends itself to robotic automation, allowing the surgeon to focus on high-level tasks, such as choosing the region and method of ablation, while the lower-level ablation plan can be handled autonomously. This paper describes a sampling-based model predictive control (MPC) scheme to plan ablation sequences for arbitrary tissue volumes. Using a steady-state point ablation model to simulate a single laser-tissue interaction, a random search technique explores the reachable state space while preserving sensitive tissue regions. The sampled MPC strategy provides an ablation sequence that accounts for parameter uncertainty without violating constraints, such as avoiding critical nerve bundles or blood vessels., Comment: 7 pages, 6 figures, submitted to IEEE ICRA 2025

Robot-assisted ultrasound scanning promises to advance autonomous and accessible medical imaging. However, ensuring patient safety and compliant human-robot interaction (HRI) during probe contact poses a significant challenge. Most existing systems either have high mechanical stiffness or are compliant but lack sufficient force and precision. This paper presents a novel single-degree-of-freedom end-effector for safe and accurate robotic ultrasound imaging, using a quasi-direct drive actuator to achieve both passive mechanical compliance and precise active force regulation, even during motion. The end-effector demonstrates an effective force control bandwidth of 100 Hz and can apply forces ranging from 2.5N to 15N. To validate the end-effector's performance, we developed a novel ex vivo actuating platform, enabling compliance testing of the end-effector on simulated abdominal breathing and sudden patient movements. Experiments demonstrate that the end-effector can maintain consistent probe contact during simulated respiratory motion at 2.5N, 5N, 10N, and 15N, with an average force tracking RMS error of 0.83N compared to 4.70N on a UR3e robot arm using conventional force control. This system represents the first compliant ultrasound end-effector tested on a tissue platform simulating dynamic movement. The proposed solution provides a novel approach for designing and evaluating compliant robotic ultrasound systems, advancing the path for more compliant and patient-friendly robotic ultrasound systems in clinical settings.

Geological Carbon Storage GCS is arguably the only scalable net-negative CO2 emission technology available While promising subsurface complexities and heterogeneity of reservoir properties demand a systematic approach to quantify uncertainty when optimizing production and mitigating storage risks which include assurances of Containment and Conformance of injected supercritical CO2 As a first step towards the design and implementation of a Digital Twin for monitoring underground storage operations a machine learning based data-assimilation framework is introduced and validated on carefully designed realistic numerical simulations As our implementation is based on Bayesian inference but does not yet support control and decision-making we coin our approach an uncertainty-aware Digital Shadow To characterize the posterior distribution for the state of CO2 plumes conditioned on multi-modal time-lapse data the envisioned Shadow combines techniques from Simulation-Based Inference SBI and Ensemble Bayesian Filtering to establish probabilistic baselines and assimilate multi-modal data for GCS problems that are challenged by large degrees of freedom nonlinear multi-physics non-Gaussianity and computationally expensive to evaluate fluid flow and seismic simulations To enable SBI for dynamic systems a recursive scheme is proposed where the Digital Shadows neural networks are trained on simulated ensembles for their state and observed data well and/or seismic Once training is completed the systems state is inferred when time-lapse field data becomes available In this computational study we observe that a lack of knowledge on the permeability field can be factored into the Digital Shadows uncertainty quantification To our knowledge this work represents the first proof of concept of an uncertainty-aware in-principle scalable Digital Shadow.

This paper investigates the finite-temperature behavior of Conformal Field Theory (CFT) in Rindler vacuum, focusing on the relation between acceleration and thermality in quantum field theory. We illustrate how uniformly accelerated observers perceive the vacuum as a thermal state via Unruh effect, shedding light on the thermal properties of Rindler horizon. Through numerical simulations of the heat kernel, Unruh temperature, Planck distribution, and detector response, we demonstrate that acceleration enhances the thermal characteristics of quantum fields. These results provide important insights into horizon-induced thermality, with significant implications for black hole thermodynamics and quantum gravity., Comment: 15 pages, 4 figures

Automatic text summarization in Nepali language is an unexplored area in natural language processing (NLP). Although considerable research has been dedicated to extractive summarization, the area of abstractive summarization, especially for low-resource languages such as Nepali, remains largely unexplored. This study explores the use of multilingual transformer models, specifically mBART and mT5, for generating headlines for Nepali news articles through abstractive summarization. The research addresses key challenges associated with summarizing texts in Nepali by first creating a summarization dataset through web scraping from various Nepali news portals. These multilingual models were then fine-tuned using different strategies. The performance of the fine-tuned models were then assessed using ROUGE scores and human evaluation to ensure the generated summaries were coherent and conveyed the original meaning. During the human evaluation, the participants were asked to select the best summary among those generated by the models, based on criteria such as relevance, fluency, conciseness, informativeness, factual accuracy, and coverage. During the evaluation with ROUGE scores, the 4-bit quantized mBART with LoRA model was found to be effective in generating better Nepali news headlines in comparison to other models and also it was selected 34.05% of the time during the human evaluation, outperforming all other fine-tuned models created for Nepali News headline generation.

Effective epidemic forecasting is critical for public health strategies and efficient medical resource allocation, especially in the face of rapidly spreading infectious diseases. However, existing deep-learning methods often overlook the dynamic nature of epidemics and fail to account for the specific mechanisms of disease transmission. In response to these challenges, we introduce an innovative end-to-end framework called Epidemiology-Aware Neural ODE with Continuous Disease Transmission Graph (EARTH) in this paper. To learn continuous and regional disease transmission patterns, we first propose EANO, which seamlessly integrates the neural ODE approach with the epidemic mechanism, considering the complex spatial spread process during epidemic evolution. Additionally, we introduce GLTG to model global infection trends and leverage these signals to guide local transmission dynamically. To accommodate both the global coherence of epidemic trends and the local nuances of epidemic transmission patterns, we build a cross-attention approach to fuse the most meaningful information for forecasting. Through the smooth synergy of both components, EARTH offers a more robust and flexible approach to understanding and predicting the spread of infectious diseases. Extensive experiments show EARTH superior performance in forecasting real-world epidemics compared to state-of-the-art methods. The code will be available at https://github.com/Emory-Melody/EpiLearn.

This paper investigates the use of autoencoders and machine learning methods for detecting and analyzing quantum phase transitions in the Two-Component Bose-Hubbard Model. By leveraging deep learning models such as autoencoders, we investigate latent space representations, reconstruction error analysis, and cluster distance calculations to identify phase boundaries and critical points. The study is supplemented by dimensionality reduction techniques such as PCA and t-SNE for latent space visualization. The results demonstrate the potential of autoencoders to describe the dynamics of quantum phase transitions., Comment: 24 pages, 7 figures

This paper introduces the hypothetical track-length fitting algorithm, a novel method for measuring the kinetic energies of ionizing particles in liquid argon time projection chambers (LArTPCs). The algorithm finds the most probable offset in track length for a track-like object by comparing the measured ionization density as a function of position with a theoretical prediction of the energy loss as a function of the energy, including models of electron recombination and detector response. The algorithm can be used to measure the energies of particles that interact before they stop, such as charged pions that are absorbed by argon nuclei. The algorithm's energy measurement resolutions and fractional biases are presented as functions of particle kinetic energy and number of track hits using samples of stopping secondary charged pions in data collected by the ProtoDUNE-SP detector, and also in a detailed simulation. Additional studies describe impact of the dE/dx model on energy measurement performance. The method described in this paper to characterize the energy measurement performance can be repeated in any LArTPC experiment using stopping secondary charged pions.

Dream11 is a fantasy sports platform that allows users to create their own virtual teams for real-life sports events. We host multiple sports and matches for our 200M+ user base. In this RMG (real money gaming) setting, users pay an entry amount to participate in various contest products that we provide to users. In our current work, we discuss the problem of predicting the user's propensity to spend in a gaming round, so it can be utilized for various downstream applications. e.g. Upselling users by incentivizing them marginally as per their spending propensity, or personalizing the product listing based on the user's propensity to spend. We aim to model the spending propensity of each user based on past transaction data. In this paper, we benchmark tree-based and deep-learning models that show good results on structured data, and we propose a new architecture change that is specifically designed to capture the rich interactions among the input features. We show that our proposed architecture outperforms the existing models on the task of predicting the user's propensity to spend in a gaming round. Our new transformer model surpasses the state-of-the-art FT-Transformer, improving MAE by 2.5\% and MSE by 21.8\%., Comment: 6 pages, 3 figures

Command injection and replay attacks are key threats in Cyber Physical Systems (CPS). We develop a novel actuator fingerprinting technique named Time Constant. Time Constant captures the transient dynamics of an actuator and physical process. The transient behavior is device-specific. We combine process and device transient characteristics to develop a copy-resistant actuator fingerprint that resists command injection and replay attacks in the face of insider adversaries. We validated the proposed scheme on data from a real water treatment testbed, as well as through real-time attack detection in the live plant. Our results show that we can uniquely distinguish between process states and actuators based on their Time Constant.

This paper proposes an improved deep learning based maximum power point tracking (MPPT) in solar photovoltaic cells considering various time series based environmental inputs. Generally, artificial neural network based MPPT algorithms use basic neural network architectures and inputs which do not represent the ambient conditions in a comprehensive manner. In this article, the ambient conditions of a location are represented through a comprehensive set of environmental features. Furthermore, the inclusion of time based features in the input data is considered to model cyclic patterns temporally within the atmospheric conditions leading to robust modeling of the MPPT algorithm. A transformer based deep learning architecture is trained as a time series prediction model using multidimensional time series input features. The model is trained on a dataset containing typical meteorological year data points of ambient weather conditions from 50 locations. The attention mechanism in the transformer modules allows the model to learn temporal patterns in the data efficiently. The proposed model achieves a 0.47% mean average percentage error of prediction on non zero operating voltage points in a test dataset consisting of data collected over a period of 200 consecutive hours resulting in the average power efficiency of 99.54% and peak power efficiency of 99.98%. The proposed model is validated through real time simulations. The proposed model performs power point tracking in a robust, dynamic, and nonlatent manner, over a wide range of atmospheric conditions., Comment: Published June 2022, in Energy Science and Engineering, Volume10, Issue9, Pages 3397-3410

This paper investigates the existence and uniqueness of the mild solutions and the exact null controllability for a class of non-autonomous parabolic evolution systems with nonlocal conditions in Hilbert spaces. We present sufficient conditions for achieving exact null controllability in these systems using the theory of linear evolution systems and the Schauder fixed point theorem. Importantly, our results do not require the compactness or Lipschitz conditions for the function \( g \) in the nonlocal conditions, which are often needed in other studies. We also provide an example to demonstrate the practical application of our results., Comment: 20 pages, 0 figure

We propose a low energy model for simulating an analog black hole on an optical lattice using ultracold atoms. Assuming the validity of the holographic principle, we employ the Sachdev-Ye-Kitaev (SYK) model, which describes a system of randomly infinite range interacting fermions, also conjectured to be an exactly solvable UV-complete model for an extremal black hole in a higher dimensional Anti-de Sitter (AdS) dilaton gravity. At low energies, the SYK model exhibits an emergent conformal symmetry and is dual to the extremal black hole solution in near AdS2 spacetime. Furthermore, we show how the SYK maximally chaotic behaviour at large N limit, found to be dual to a gauge theory in higher dimensions, can also be employed as a non-trivial investigation tool for the holographic principle. The proposed setup is a theoretical platform to realize the SYK model with relevant exotic effects and behaviour at low energies as a highly non-trivial example of the AdS/CFT duality and a framework for studying black holes., Comment: 15 pages, 3 figures

The relative contribution of emission from stellar sources and accretion onto supermassive black holes to reionization has been brought into focus again by the apparent high abundance of faint AGN at $4\lesssim z\lesssim11$ uncovered by JWST. We investigate the contribution of these faint AGN to hydrogen and the early stages of helium reionization using the GPU-based radiative transfer code ATON-HE by post-processing a cosmological hydrodynamical simulation from the SHERWOOD-RELICS suite of simulations. We study four models of reionization: two previously studied galaxy-only late-end reionization models and two new models -- a QSO-assisted model and a QSO-only model. In the QSO-assisted model, 1\% of the haloes host AGN with a 10~Myr lifetime, and the AGN luminosities are scaled such that the AGN contribution to the hydrogen-ionizing emissivity is 20\% of that contributed by galaxies. In the QSO-only model, quasars account for all the hydrogen-ionizing emissivity, with 10\% of the haloes hosting AGN, each with a 10 Myr lifetime. All models are calibrated to the observed mean Lyman-$\alpha$ forest transmission at $5\lesssim z\lesssim6.2$. We find that the QSO-assisted model requires an emissivity factor of $1.8$ lower than the galaxy-only models towards the end of reionization and fits the observed distribution of the Lyman-$\alpha$ optical depths well. Our QSO-only model is inconsistent with the observed Lyman-$\alpha$ optical depths distribution. It also results in too high IGM temperatures at $z\lesssim 5$ due to an early onset of HeII reionization unless the escape fraction of HeII-ionizing photons is assumed to be low. Our results suggest that a modest contribution to reionization by faint AGN is in good agreement with the Lyman-$\alpha$ forest data. In contrast, a scenario dominated by faint AGN appears difficult to reconcile with these observations., Comment: 19 pages, 11 figures