Search

Democratizing biomarker testing at the point-of-care requires innovations that match laboratory-grade sensitivity and precision in an accessible format. Here, we demonstrate high-sensitivity detection of cardiac troponin I (cTnI) through innovations in chemiluminescence-based sensing, imaging, and deep learning-driven analysis. This chemiluminescence vertical flow assay (CL-VFA) enables rapid, low-cost, and precise quantification of cTnI, a key cardiac protein for assessing heart muscle damage and myocardial infarction. The CL-VFA integrates a user-friendly chemiluminescent paper-based sensor, a polymerized enzyme-based conjugate, a portable high-performance CL reader, and a neural network-based cTnI concentration inference algorithm. The CL-VFA measures cTnI over a broad dynamic range covering six orders of magnitude and operates with 50 uL of serum per test, delivering results in 25 min. This system achieves a detection limit of 0.16 pg/mL with an average coefficient of variation under 15%, surpassing traditional benchtop analyzers in sensitivity by an order of magnitude. In blinded validation, the computational CL-VFA accurately measured cTnI concentrations in patient samples, demonstrating a robust correlation against a clinical-grade FDA-cleared analyzer. These results highlight the potential of CL-VFA as a robust diagnostic tool for accessible, rapid cardiac biomarker testing that meets the needs of diverse healthcare settings, from emergency care to underserved regions., Comment: 24 Pages, 4 Figures

In this note we consider the big algebra recently introduced by Hausel for the $\mathrm{GL}_n$-action on the coordinate ring of the matrix space $\operatorname{Mat}(n,r)$. In particular, we obtain explicit formulas for the big algebra generators in terms of differential operators with polynomial coefficients. We show that big algebras in type $A$ are commutative and relate them to the Bethe subalgebra in the Yangian $\mathrm{Y}(\mathfrak{gl}_{n})$. We apply these results to big algebras of symmetric powers of the standard representation of $\mathrm{GL}_n$., Comment: 40 pages

Deep Neural Networks (DNNs) have gained considerable traction in recent years due to the unparalleled results they gathered. However, the cost behind training such sophisticated models is resource intensive, resulting in many to consider DNNs to be intellectual property (IP) to model owners. In this era of cloud computing, high-performance DNNs are often deployed all over the internet so that people can access them publicly. As such, DNN watermarking schemes, especially backdoor-based watermarks, have been actively developed in recent years to preserve proprietary rights. Nonetheless, there lies much uncertainty on the robustness of existing backdoor watermark schemes, towards both adversarial attacks and unintended means such as fine-tuning neural network models. One reason for this is that no complete guarantee of robustness can be assured in the context of backdoor-based watermark. In this paper, we extensively evaluate the persistence of recent backdoor-based watermarks within neural networks in the scenario of fine-tuning, we propose/develop a novel data-driven idea to restore watermark after fine-tuning without exposing the trigger set. Our empirical results show that by solely introducing training data after fine-tuning, the watermark can be restored if model parameters do not shift dramatically during fine-tuning. Depending on the types of trigger samples used, trigger accuracy can be reinstated to up to 100%. Our study further explores how the restoration process works using loss landscape visualization, as well as the idea of introducing training data in fine-tuning stage to alleviate watermark vanishing., Comment: Preprint. Under Review

Recent advancements in large language models (LLMs) based embedding models have established new state-of-the-art benchmarks for text embedding tasks, particularly in dense vector-based retrieval. However, these models predominantly focus on English, leaving multilingual embedding capabilities largely unexplored. To address this limitation, we present LUSIFER, a novel zero-shot approach that adapts LLM-based embedding models for multilingual tasks without requiring multilingual supervision. LUSIFER's architecture combines a multilingual encoder, serving as a language-universal learner, with an LLM-based embedding model optimized for embedding-specific tasks. These components are seamlessly integrated through a minimal set of trainable parameters that act as a connector, effectively transferring the multilingual encoder's language understanding capabilities to the specialized embedding model. Additionally, to comprehensively evaluate multilingual embedding performance, we introduce a new benchmark encompassing 5 primary embedding tasks, 123 diverse datasets, and coverage across 14 languages. Extensive experimental results demonstrate that LUSIFER significantly enhances the multilingual performance across various embedding tasks, particularly for medium and low-resource languages, without requiring explicit multilingual training data.

Simultaneously transmitting and reflecting reconfigurable intelligent surface (STAR-RIS)-aided cell-free massive multiple-input multiple-output (CF-mMIMO) systems are investigated under spatially correlated fading channels using realistic imperfect hardware. Specifically, the transceiver distortions, \textcolor{black}{time-varying phase noise, and RIS phase shift errors} are considered. Upon considering imperfect hardware and pilot contamination, we derive a linear minimum mean-square error (MMSE) criterion-based cascaded channel estimator. Moreover, a closed-form expression of the downlink ergodic spectral efficiency (SE) is derived based on maximum ratio (MR) based transmit precoding and channel statistics, where both a finite number of access points (APs) and STAR-RIS elements as well as imperfect hardware are considered. Furthermore, by exploiting the ergodic signal-to-interference-plus-noise ratios (SINRs) among user equipment (UE), a max-min fairness problem is formulated for the joint optimization of the passive transmitting and reflecting beamforming (BF) at the STAR-RIS as well as of the power control coefficients. An alternating optimization (AO) algorithm is proposed for solving the resultant problems, where iterative adaptive particle swarm optimization (APSO) and bisection methods are proposed for circumventing the non-convexity of the RIS passive BF and the quasi-concave power control sub-problems, respectively. Our simulation results illustrate that the STAR-RIS-aided CF-mMIMO system attains higher SE than its RIS-aided counterpart. The performance of different hardware parameters is also evaluated. Additionally, it is demonstrated that the SE of the worst UE can be significantly improved by exploiting the proposed AO-based algorithm compared to conventional solutions associated with random passive BF and equal-power scenarios., Comment: This paper has been accepted by IEEE TWC

Visual Language Models have demonstrated remarkable capabilities across tasks, including visual question answering and image captioning. However, most models rely on text-based instructions, limiting their effectiveness in human-machine interactions. Moreover, the quality of language models depends on reasoning and prompting techniques, such as COT, which remain underexplored when using speech instructions. To address these challenges, we propose SilVar, a novel end-to-end multimodal model that uses speech instructions for reasoning in visual question answering. In addition, we investigate reasoning techniques with levels including conversational, simple, and complex speech instruction. SilVar is built upon CLIP, Whisper, and LLaMA 3.1-8B, enabling intuitive interactions by allowing users to provide verbal or text instructions. To this end, we introduce a dataset designed to challenge models with speech-based reasoning tasks for object localization. This dataset enhances the model ability to process and explain visual scenes from spoken input, moving beyond object recognition to reasoning-based interactions. The experiments show that SilVar achieves SOTA performance on the MMMU and ScienceQA benchmarks despite the challenge of speech-based instructions. We believe SilVar will inspire next-generation multimodal reasoning models, toward expert artificial general intelligence. Our code and dataset are available here., Comment: 10 pages

This year, we explore generation-augmented retrieval for the TRECVid AVS task. Specifically, the understanding of textual query is enhanced by three generations, including Text2Text, Text2Image, and Image2Text, to address the out-of-vocabulary problem. Using different combinations of them and the rank list retrieved by the original query, we submitted four automatic runs. For manual runs, we use a large language model (LLM) (i.e., GPT4) to rephrase test queries based on the concept bank of the search engine, and we manually check again to ensure all the concepts used in the rephrased queries are in the bank. The result shows that the fusion of the original and generated queries outperforms the original query on TV24 query sets. The generated queries retrieve different rank lists from the original query.

When it comes to expensive black-box optimization problems, Bayesian Optimization (BO) is a well-known and powerful solution. Many real-world applications involve a large number of dimensions, hence scaling BO to high dimension is of much interest. However, state-of-the-art high-dimensional BO methods still suffer from the curse of dimensionality, highlighting the need for further improvements. In this work, we introduce BOIDS, a novel high-dimensional BO algorithm that guides optimization by a sequence of one-dimensional direction lines using a novel tailored line-based optimization procedure. To improve the efficiency, we also propose an adaptive selection technique to identify most optimal lines for each round of line-based optimization. Additionally, we incorporate a subspace embedding technique for better scaling to high-dimensional spaces. We further provide theoretical analysis of our proposed method to analyze its convergence property. Our extensive experimental results show that BOIDS outperforms state-of-the-art baselines on various synthetic and real-world benchmark problems., Comment: Published at AAAI Conference on Artificial Intelligence, 2025

Finding heavy hitters in databases and data streams is a fundamental problem, with applications ranging from network monitoring to database query optimization, anomaly detection, and more. Approximation algorithms offer practical solutions, but they present multi-faceted trade-offs involving throughput, memory usage, and accuracy. Moreover, evolving applications demand capabilities beyond sequential processing - they require both parallel performance scaling and support for concurrent queries/updates. To address these challenges holistically, we first propose a new algorithm, Cuckoo Heavy Keeper, that combines careful algorithmic design with system-aware perspectives, to effectively balance competing trade-offs. Recognizing the diverse needs of different applications, we then propose two parallel algorithms optimized for different workload patterns: one prioritizes insertion throughput while the other targets efficient heavy hitter queries, both achieving high performance via efficient parallel scaling while supporting concurrent operations. Besides discussing the algorithms' bounds, through extensive evaluation, we demonstrate that Cuckoo Heavy Keeper improves throughput by 1.7X to 5.6X and accuracy by 1.9X to 27,542X compared to state-of-the-art methods under tight memory constraints, maintaining these advantages even with low-skew datasets. The parallel variants achieve near-linear scaling up to 70 threads while maintaining heavy hitters query latencies as low as 36 {\mu}sec to 350 {\mu}sec.

The enhanced representational power and broad applicability of deep learning models have attracted significant interest from the research community in recent years. However, these models often struggle to perform effectively under domain shift conditions, where the training data (the source domain) is related to but exhibits different distributions from the testing data (the target domain). To address this challenge, previous studies have attempted to reduce the domain gap between source and target data by incorporating a few labeled target samples during training - a technique known as semi-supervised domain adaptation (SSDA). While this strategy has demonstrated notable improvements in classification performance, the network architectures used in these approaches primarily focus on exploiting the features of individual images, leaving room for improvement in capturing rich representations. In this study, we introduce a Hierarchical Graph of Nodes designed to simultaneously present representations at both feature and category levels. At the feature level, we introduce a local graph to identify the most relevant patches within an image, facilitating adaptability to defined main object representations. At the category level, we employ a global graph to aggregate the features from samples within the same category, thereby enriching overall representations. Extensive experiments on widely used SSDA benchmark datasets, including Office-Home, DomainNet, and VisDA2017, demonstrate that both quantitative and qualitative results substantiate the effectiveness of HiGDA, establishing it as a new state-of-the-art method., Comment: Accepted for presentation at AAAI2025

Adoption of machine learning models across industries have turned Neural Networks (DNNs) into a prized Intellectual Property (IP), which needs to be protected from being stolen or being used without authorization. This topic gave rise to multiple watermarking schemes, through which, one can establish the ownership of a model. Watermarking using backdooring is the most well established method available in the literature, with specific works demonstrating the difficulty in removing the watermarks, embedded as backdoors within the weights of the network. However, in our work, we have identified a critical flaw in the design of the watermark verification with backdoors, pertaining to the behaviour of the samples of the Trigger Set, which acts as the secret key. In this paper, we present BlockDoor, which is a comprehensive package of techniques that is used as a wrapper to block all three different kinds of Trigger samples, which are used in the literature as means to embed watermarks within the trained neural networks as backdoors. The framework implemented through BlockDoor is able to detect potential Trigger samples, through separate functions for adversarial noise based triggers, out-of-distribution triggers and random label based triggers. Apart from a simple Denial-of-Service for a potential Trigger sample, our approach is also able to modify the Trigger samples for correct machine learning functionality. Extensive evaluation of BlockDoor establishes that it is able to significantly reduce the watermark validation accuracy of the Trigger set by up to $98\%$ without compromising on functionality, delivering up to a less than $1\%$ drop on the clean samples. BlockDoor has been tested on multiple datasets and neural architectures., Comment: Accepted as a Work-in-Progress paper at SPACE 2024: Fourteenth International Conference on Security, Privacy and Applied Cryptographic Engineering

To address catastrophic forgetting in Continual Relation Extraction (CRE), many current approaches rely on memory buffers to rehearse previously learned knowledge while acquiring new tasks. Recently, prompt-based methods have emerged as potent alternatives to rehearsal-based strategies, demonstrating strong empirical performance. However, upon analyzing existing prompt-based approaches for CRE, we identified several critical limitations, such as inaccurate prompt selection, inadequate mechanisms for mitigating forgetting in shared parameters, and suboptimal handling of cross-task and within-task variances. To overcome these challenges, we draw inspiration from the relationship between prefix-tuning and mixture of experts, proposing a novel approach that employs a prompt pool for each task, capturing variations within each task while enhancing cross-task variances. Furthermore, we incorporate a generative model to consolidate prior knowledge within shared parameters, eliminating the need for explicit data storage. Extensive experiments validate the efficacy of our approach, demonstrating superior performance over state-of-the-art prompt-based and rehearsal-free methods in continual relation extraction., Comment: Accepted to AAAI 2025

Cell-free (CF) architecture and full-duplex (FD) communication are leading candidates for next-generation wireless networks. The CF framework removes cell boundaries in traditional cell-based systems, thereby mitigating inter-cell interference and improving coverage probability. In contrast, FD communication allows simultaneous transmission and reception on the same frequency-time resources, effectively doubling the spectral efficiency (SE). The integration of these technologies, known as CF FD communication, leverages the advantages of both approaches to enhance the spectral and energy efficiency in wireless networks. CF FD communication is particularly promising due to the low-power and cost-effective FD-enabled access points (APs), which are ideal for short-range transmissions between APs and users. Despite its potential, a comprehensive survey or tutorial on CF FD communication has been notably absent. This paper aims to address this gap in the literature. It begins with an overview of FD communication fundamentals, self-interference cancellation techniques, and CF technology principles, including their implications for current wireless networks. The discussion then moves to the integration and compatibility of CF and FD technologies, focusing on channel estimation, performance analysis, and resource allocation in CF FD massive multiple-input multiple-output (mMIMO) networks, supported by an extensive literature review and case studies., Comment: 25 pages, 10 figures, Overview paper

We propose 4Real-Video, a novel framework for generating 4D videos, organized as a grid of video frames with both time and viewpoint axes. In this grid, each row contains frames sharing the same timestep, while each column contains frames from the same viewpoint. We propose a novel two-stream architecture. One stream performs viewpoint updates on columns, and the other stream performs temporal updates on rows. After each diffusion transformer layer, a synchronization layer exchanges information between the two token streams. We propose two implementations of the synchronization layer, using either hard or soft synchronization. This feedforward architecture improves upon previous work in three ways: higher inference speed, enhanced visual quality (measured by FVD, CLIP, and VideoScore), and improved temporal and viewpoint consistency (measured by VideoScore and Dust3R-Confidence)., Comment: Project page: https://snap-research.github.io/4Real-Video/

We present numerous aspects of the evolution of the LP 890-9 (SPECULOOS-2/TOI-4306) planetary system, focusing on the likelihood that planet c can support life. We find that the host star reaches the main sequence in 1 Gyr and that planet c lies close to the inner boundary of the habitable zone. We find the magma ocean stage can last up to 50 Myr, remove 8 Earth-oceans of water, and leave up to 2000 bars of oxygen in the atmosphere. However, if the planet forms with a hydrogen envelope as small as 0.1 Earth-masses, no water will be lost during the star's pre-main sequence phase from thermal escape processes. We find that the planets are unlikely to be in a 3:1 mean motion resonance and that both planets tidally circularize within 0.5 Gyr when tidal dissipation is held constant. However, if tidal dissipation is a function of mantle temperature and rheology, then we find that planet c's orbit may require more than 7 Gyr to circularize, during which time tidal heating may reach hundreds of terawatts. We thus conclude that the habitability of planet c depends most strongly on the initial volatile content and internal properties, but no data yet preclude the viability of an active biosphere on the planet., Comment: 16 pages, 9 figures, accepted to PSJ

The proliferating adoption of platform-based gig work increasingly raises concerns for worker conditions. Past studies documented how platforms leveraged design to exploit labor, withheld information to generate power asymmetries, and left workers alone to manage logistical overheads as well as social isolation. However, researchers also called attention to the potential of helping workers overcome such costs via worker-led datasharing, which can enable collective actions and mutual aid among workers, while offering advocates, lawmakers and regulatory bodies insights for improving work conditions. To understand stakeholders' desiderata for a data-sharing system (i.e. functionality and policy initiatives that it can serve), we interviewed 11 policy domain experts in the U.S. and conducted co-design workshops with 14 active gig workers across four domains. Our results outline policymakers' prioritized initiatives, information needs, and (mis)alignments with workers' concerns and desires around data collectives. We offer design recommendations for data-sharing systems that support worker needs while bringing us closer to legislation that promote more thriving and equitable gig work futures.

Uncovering hidden topics from short texts is challenging for traditional and neural models due to data sparsity, which limits word co-occurrence patterns, and label sparsity, stemming from incomplete reconstruction targets. Although data aggregation offers a potential solution, existing neural topic models often overlook it due to time complexity, poor aggregation quality, and difficulty in inferring topic proportions for individual documents. In this paper, we propose a novel model, GloCOM (Global Clustering COntexts for Topic Models), which addresses these challenges by constructing aggregated global clustering contexts for short documents, leveraging text embeddings from pre-trained language models. GloCOM can infer both global topic distributions for clustering contexts and local distributions for individual short texts. Additionally, the model incorporates these global contexts to augment the reconstruction loss, effectively handling the label sparsity issue. Extensive experiments on short text datasets show that our approach outperforms other state-of-the-art models in both topic quality and document representations.

Learning diverse policies for non-prehensile manipulation is essential for improving skill transfer and generalization to out-of-distribution scenarios. In this work, we enhance exploration through a two-fold approach within a hybrid framework that tackles both discrete and continuous action spaces. First, we model the continuous motion parameter policy as a diffusion model, and second, we incorporate this into a maximum entropy reinforcement learning framework that unifies both the discrete and continuous components. The discrete action space, such as contact point selection, is optimized through Q-value function maximization, while the continuous part is guided by a diffusion-based policy. This hybrid approach leads to a principled objective, where the maximum entropy term is derived as a lower bound using structured variational inference. We propose the Hybrid Diffusion Policy algorithm (HyDo) and evaluate its performance on both simulation and zero-shot sim2real tasks. Our results show that HyDo encourages more diverse behavior policies, leading to significantly improved success rates across tasks - for example, increasing from 53% to 72% on a real-world 6D pose alignment task. Project page: https://leh2rng.github.io/hydo, Comment: 8 pages

Large language models have gained widespread popularity for their ability to process natural language inputs and generate insights derived from their training data, nearing the qualities of true artificial intelligence. This advancement has prompted enterprises worldwide to integrate LLMs into their services. So far, this effort is dominated by commercial cloud-based solutions like OpenAI's ChatGPT and Microsoft Azure. As the technology matures, however, there is a strong incentive for independence from major cloud providers through self-hosting "LLM as a Service", driven by privacy, cost, and customization needs. In practice, hosting LLMs independently presents significant challenges due to their complexity and integration issues with existing systems. In this paper, we discuss our vision for a forward-looking middleware system architecture that facilitates the deployment and adoption of LLMs in enterprises, even for advanced use cases in which we foresee LLMs to serve as gateways to a complete application ecosystem and, to some degree, absorb functionality traditionally attributed to the middleware.

Parameter-efficient fine-tuning multimodal large language models (MLLMs) presents significant challenges, including reliance on high-level visual features that limit fine-grained detail comprehension, and data conflicts that arise from task complexity. To address these issues, we propose an efficient fine-tuning framework with two novel approaches: Vision Cue Enhancement (VCE) and Dual Low-Rank Adaptation (Dual-LoRA). VCE enhances the vision projector by integrating multi-level visual cues, improving the model's ability to capture fine-grained visual features. Dual-LoRA introduces a dual low-rank structure for instruction tuning, decoupling learning into skill and task spaces to enable precise control and efficient adaptation across diverse tasks. Our method simplifies implementation, enhances visual comprehension, and improves adaptability. Experiments on both downstream tasks and general benchmarks demonstrate the effectiveness of our proposed approach.

Latent space optimization (LSO) is a powerful method for designing discrete, high-dimensional biological sequences that maximize expensive black-box functions, such as wet lab experiments. This is accomplished by learning a latent space from available data and using a surrogate model to guide optimization algorithms toward optimal outputs. However, existing methods struggle when labeled data is limited, as training the surrogate model with few labeled data points can lead to subpar outputs, offering no advantage over the training data itself. We address this challenge by introducing GROOT, a Graph-based Latent Smoothing for Biological Sequence Optimization. In particular, GROOT generates pseudo-labels for neighbors sampled around the training latent embeddings. These pseudo-labels are then refined and smoothed by Label Propagation. Additionally, we theoretically and empirically justify our approach, demonstrate GROOT's ability to extrapolate to regions beyond the training set while maintaining reliability within an upper bound of their expected distances from the training regions. We evaluate GROOT on various biological sequence design tasks, including protein optimization (GFP and AAV) and three tasks with exact oracles from Design-Bench. The results demonstrate that GROOT equalizes and surpasses existing methods without requiring access to black-box oracles or vast amounts of labeled data, highlighting its practicality and effectiveness. We release our code at https://anonymous.4open.science/r/GROOT-D554

We present a theoretical approach, for the first time, to investigate optical and photothermal properties of high-entropy alloy nanoparticles with a focus on FeCoNi-based alloys. We systematically analyze the absorption spectra of spherical nanoparticles composed of pure metals and alloys in various surrounding media. Through comparison with experimental data, we select appropriate dielectric data for the constituent elements to accurately compute absorption spectra for FeCoNi-based high-entropy-alloy nanoparticles. Then, we predict the temperature rise over time within a substrate comprised of Fe nanoparticles exposed to solar irradiation and find quantitative agreement with experimental data for FeCoNi nanoparticles reported in previous studies. The striking similarity between the optical and photothermal behaviors of FeCoNi nanoparticles and their pure iron counterparts suggests that iron nanoparticles can effectively serve as a model for understanding the optical and thermal response of FeCoNi-based alloy nanoparticles. These findings offer a simplified approach for theoretical modeling of complex high-entropy alloys and provide valuable insights into their nanoscale optical behavior., Comment: 11 pages, 9 figures, the manuscript has been accepted for publication in Materials Today Communications

Integrated sensing and communications (ISAC) is envisioned as a key feature in future wireless communications networks. Its integration with massive multiple-input-multiple-output (MIMO) techniques promises to leverage substantial spatial beamforming gains for both functionalities. In this work, we consider a massive MIMO-ISAC system employing a uniform planar array with zero-forcing and maximum-ratio downlink transmission schemes combined with monostatic radar-type sensing. Our focus lies on deriving closed-form expressions for the achievable communications rate and the Cram\'er--Rao lower bound (CRLB), which serve as performance metrics for communications and sensing operations, respectively. The expressions enable us to investigate important operational characteristics of massive MIMO-ISAC, including the mutual effects of communications and sensing as well as the advantages stemming from using a very large antenna array for each functionality. Furthermore, we devise a power allocation strategy based on successive convex approximation to maximize the communications rate while guaranteeing the CRLB constraints and transmit power budget. Extensive numerical results are presented to validate our theoretical analyses and demonstrate the efficiency of the proposed power allocation approach., Comment: This paper has been submitted to IEEE Transaction on Signal Processing (on 15 April 2024) for possible publication

Scene graphs have proven to be highly effective for various scene understanding tasks due to their compact and explicit representation of relational information. However, current methods often overlook the critical importance of preserving symmetry when generating scene graphs from 3D point clouds, which can lead to reduced accuracy and robustness, particularly when dealing with noisy, multi-view data. This work, to the best of our knowledge, presents the first implementation of an Equivariant Scene Graph Neural Network (ESGNN) to generate semantic scene graphs from 3D point clouds, specifically for enhanced scene understanding. Furthermore, a significant limitation of prior methods is the absence of temporal modeling to capture time-dependent relationships among dynamically evolving entities within a scene. To address this gap, we introduce a novel temporal layer that leverages the symmetry-preserving properties of ESGNN to fuse scene graphs across multiple sequences into a unified global representation by an approximate graph-matching algorithm. Our combined architecture, termed the Temporal Equivariant Scene Graph Neural Network (TESGNN), not only surpasses existing state-of-the-art methods in scene estimation accuracy but also achieves faster convergence. Importantly, TESGNN is computationally efficient and straightforward to implement using existing frameworks, making it well-suited for real-time applications in robotics and computer vision. This approach paves the way for more robust and scalable solutions to complex multi-view scene understanding challenges. Our source code is publicly available at: https://github.com/HySonLab/TESGraph, Comment: arXiv admin note: text overlap with arXiv:2407.00609

Retrieval-augmented generation (RAG) has emerged as a promising approach to enhance the performance of large language models (LLMs) in knowledge-intensive tasks such as those from medical domain. However, the sensitive nature of the medical domain necessitates a completely accurate and trustworthy system. While existing RAG benchmarks primarily focus on the standard retrieve-answer setting, they overlook many practical scenarios that measure crucial aspects of a reliable medical system. This paper addresses this gap by providing a comprehensive evaluation framework for medical question-answering (QA) systems in a RAG setting for these situations, including sufficiency, integration, and robustness. We introduce Medical Retrieval-Augmented Generation Benchmark (MedRGB) that provides various supplementary elements to four medical QA datasets for testing LLMs' ability to handle these specific scenarios. Utilizing MedRGB, we conduct extensive evaluations of both state-of-the-art commercial LLMs and open-source models across multiple retrieval conditions. Our experimental results reveals current models' limited ability to handle noise and misinformation in the retrieved documents. We further analyze the LLMs' reasoning processes to provides valuable insights and future directions for developing RAG systems in this critical medical domain.

The majority of previous researches addressing multi-lingual IE are limited to zero-shot cross-lingual single-transfer (one-to-one) setting, with high-resource languages predominantly as source training data. As a result, these works provide little understanding and benefit for the realistic goal of developing a multi-lingual IE system that can generalize to as many languages as possible. Our study aims to fill this gap by providing a detailed analysis on Cross-Lingual Multi-Transferability (many-to-many transfer learning), for the recent IE corpora that cover a diverse set of languages. Specifically, we first determine the correlation between single-transfer performance and a wide range of linguistic-based distances. From the obtained insights, a combined language distance metric can be developed that is not only highly correlated but also robust across different tasks and model scales. Next, we investigate the more general zero-shot multi-lingual transfer settings where multiple languages are involved in the training and evaluation processes. Language clustering based on the newly defined distance can provide directions for achieving the optimal cost-performance trade-off in data (languages) selection problem. Finally, a relational-transfer setting is proposed to further incorporate multi-lingual unlabeled data based on adversarial training using the relation induced from the above linguistic distance.

Given the potential applications of generating recipes from food images, this area has garnered significant attention from researchers in recent years. Existing works for recipe generation primarily utilize a two-stage training method, first generating ingredients and then obtaining instructions from both the image and ingredients. Large Multi-modal Models (LMMs), which have achieved notable success across a variety of vision and language tasks, shed light to generating both ingredients and instructions directly from images. Nevertheless, LMMs still face the common issue of hallucinations during recipe generation, leading to suboptimal performance. To tackle this, we propose a retrieval augmented large multimodal model for recipe generation. We first introduce Stochastic Diversified Retrieval Augmentation (SDRA) to retrieve recipes semantically related to the image from an existing datastore as a supplement, integrating them into the prompt to add diverse and rich context to the input image. Additionally, Self-Consistency Ensemble Voting mechanism is proposed to determine the most confident prediction recipes as the final output. It calculates the consistency among generated recipe candidates, which use different retrieval recipes as context for generation. Extensive experiments validate the effectiveness of our proposed method, which demonstrates state-of-the-art (SOTA) performance in recipe generation tasks on the Recipe1M dataset., Comment: ACCEPT on IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) 2025

In this work, we consider a cell-free massive multiple-input multiple-output (MIMO) integarted sensing and communications (ISAC) system with maximum-ratio transmission schemes combined with multistatic radar-type sensing. Our focus lies on deriving closed-form expressions for the achievable communications rate and the Cram\'er-Rao lower bound (CRLB), which serve as performance metrics for communications and sensing operations, respectively. The expressions enable us to investigate important operational characteristics of multistatic cell-free massive MIMO-ISAC, including the mutual effects of communications and sensing as well as the advantages stemming from using numerous distributed antenna arrays for each functionality. Furthermore, we optimize the power allocation among the access points to maximize the communications rate while guaranteeing the CRLB constraints and total transmit power budget. Extensive numerical results are presented to validate our theoretical findings and demonstrate the efficiency of the proposed power allocation approach., Comment: Abstract was accepted and presented at IEEE Asilomar 2024

Intelligent aerial platforms such as Unmanned Aerial Vehicles (UAVs) are expected to revolutionize various fields, including transportation, traffic management, field monitoring, industrial production, and agricultural management. Among these, precise control is a critical task that determines the performance and capabilities of UAV systems. However, current research primarily focuses on trajectory tracking and minimizing flight errors, with limited attention to improving flight time. In this paper, we propose a Model Predictive Control (MPC) approach aimed at minimizing flight time while addressing the limitations of the commonly used classical MPC controllers. Furthermore, the MPC method and its application for UAV control are presented in detail. Finally, the results demonstrate that the proposed controller outperforms the standard MPC in terms of efficiency. Moreover, this approach shows potential to become a foundation for integrating intelligent algorithms into basic controllers., Comment: In Vietnamese language, in the 26th National Conference on Electronics, Communications and Information Technology (REV-ECIT 2023), Hanoi, Vietnam

Accurate trajectory tracking is an essential characteristic for the safe navigation of a quadrotor in cluttered or disturbed environments. In this paper, we present in detail two state-of-the-art model-based control frameworks for trajectory tracking: the Linear Model Predictive Controller (LMPC) and the Nonlinear Model Predictive Controller (NMPC). Additionally, the kinematic and dynamic models of the quadrotor are comprehensively described. Finally, a simulation system is implemented to verify feasibility, demonstrating the effectiveness of both controllers., Comment: In Vietnamese language, in the 25th National Conference on Electronics, Communications and Information Technology (REV-ECIT 2022), Hanoi, Vietnam

This paper concerns the numerical approximation for the invariant distribution of Markovian switching L\'evy-driven stochastic differential equations. By combining the tamed-adaptive Euler-Maruyama scheme with the Multi-level Monte Carlo method, we propose an approximation scheme that can be applied to stochastic differential equations with super-linear growth drift and diffusion coefficients.

This paper proposes a distributed learning-based framework to tackle the sum ergodic rate maximization problem in cell-free massive multiple-input multiple-output (MIMO) systems by utilizing the graph neural network (GNN). Different from centralized schemes, which gather all the channel state information (CSI) at the central processing unit (CPU) for calculating the resource allocation, the local resource of access points (APs) is exploited in the proposed distributed GNN-based framework to allocate transmit powers. Specifically, APs can use a unique GNN model to allocate their power based on the local CSI. The GNN model is trained at the CPU using the local CSI of one AP, with partially exchanged information from other APs to calculate the loss function to reflect system characteristics, capturing comprehensive network information while avoiding computation burden. Numerical results show that the proposed distributed learning-based approach achieves a sum ergodic rate close to that of centralized learning while outperforming the model-based optimization., Comment: 6 pages, 4 figures, and 4 tables. Accepted by IEEE TVT

We propose a tamed-adaptive Milstein scheme for stochastic differential equations in which the first-order derivatives of the coefficients are locally H\"older continuous of order $\alpha$. We show that the scheme converges in the $L_2$-norm with a rate of $(1+\alpha)/2$ over both finite intervals $[0, T]$ and the infinite interval $(0, +\infty)$, under certain growth conditions on the coefficients.

Localization is one of the most crucial tasks for Unmanned Aerial Vehicle systems (UAVs) directly impacting overall performance, which can be achieved with various sensors and applied to numerous tasks related to search and rescue operations, object tracking, construction, etc. However, due to the negative effects of challenging environments, UAVs may lose signals for localization. In this paper, we present an effective path-planning system leveraging semantic segmentation information to navigate around texture-less and problematic areas like lakes, oceans, and high-rise buildings using a monocular camera. We introduce a real-time semantic segmentation architecture and a novel keyframe decision pipeline to optimize image inputs based on pixel distribution, reducing processing time. A hierarchical planner based on the Dynamic Window Approach (DWA) algorithm, integrated with a cost map, is designed to facilitate efficient path planning. The system is implemented in a photo-realistic simulation environment using Unity, aligning with segmentation model parameters. Comprehensive qualitative and quantitative evaluations validate the effectiveness of our approach, showing significant improvements in the reliability and efficiency of UAV localization in challenging environments., Comment: In The 24th International Conference on Control, Automation, and Systems (ICCAS 2024), Jeju, Korea

The best arm identification problem requires identifying the best alternative (i.e., arm) in active experimentation using the smallest number of experiments (i.e., arm pulls), which is crucial for cost-efficient and timely decision-making processes. In the fixed confidence setting, an algorithm must stop data-dependently and return the estimated best arm with a correctness guarantee. Since this stopping time is random, we desire its distribution to have light tails. Unfortunately, many existing studies focus on high probability or in expectation bounds on the stopping time, which allow heavy tails and, for high probability bounds, even not stopping at all. We first prove that this never-stopping event can indeed happen for some popular algorithms. Motivated by this, we propose algorithms that provably enjoy an exponential-tailed stopping time, which improves upon the polynomial tail bound reported by Kalyanakrishnan et al. (2012). The first algorithm is based on a fixed budget algorithm called Sequential Halving along with a doubling trick. The second algorithm is a meta algorithm that takes in any fixed confidence algorithm with a high probability stopping guarantee and turns it into one that enjoys an exponential-tailed stopping time. Our results imply that there is much more to be desired for contemporary fixed confidence algorithms.

We investigate an internet-of-things system where energy-harvesting devices send status updates to a common receiver using the irregular repetition slotted ALOHA (IRSA) protocol. Energy shortages in these devices may lead to transmission failures that are unknown to the receiver, disrupting the decoding process. To address this issue, we propose a method for the receiver to perfectly identify such failures. Furthermore, we optimize the degree distribution of the protocol to enhance the freshness of the status updates. Our optimized degree distribution mitigates the adverse effects of potential transmission failures. Numerical results demonstrate that, despite energy-harvesting constraints, IRSA can achieve a level of information freshness comparable to systems with unlimited energy., Comment: accepted to IEEE WCNC 2025

Deep Neural Networks (DNNs) suffer from significant retraining costs when adapting to evolving requirements. Modularizing DNNs offers the promise of improving their reusability. Previous work has proposed techniques to decompose DNN models into modules both during and after training. However, these strategies yield several shortcomings, including significant weight overlaps and accuracy losses across modules, restricted focus on convolutional layers only, and added complexity and training time by introducing auxiliary masks to control modularity. In this work, we propose MODA, an activation-driven modular training approach. MODA promotes inherent modularity within a DNN model by directly regulating the activation outputs of its layers based on three modular objectives: intra-class affinity, inter-class dispersion, and compactness. MODA is evaluated using three well-known DNN models and three datasets with varying sizes. This evaluation indicates that, compared to the existing state-of-the-art, using MODA yields several advantages: (1) MODA accomplishes modularization with 29% less training time; (2) the resultant modules generated by MODA comprise 2.4x fewer weights and 3.5x less weight overlap while (3) preserving the original model's accuracy without additional fine-tuning; in module replacement scenarios, (4) MODA improves the accuracy of a target class by 12% on average while ensuring minimal impact on the accuracy of other classes.

We study the problem of estimating the \emph{value} of the largest mean among $K$ distributions via samples from them (rather than estimating \emph{which} distribution has the largest mean), which arises from various machine learning tasks including Q-learning and Monte Carlo tree search. While there have been a few proposed algorithms, their performance analyses have been limited to their biases rather than a precise error metric. In this paper, we propose a novel algorithm called HAVER (Head AVERaging) and analyze its mean squared error. Our analysis reveals that HAVER has a compelling performance in two respects. First, HAVER estimates the maximum mean as well as the oracle who knows the identity of the best distribution and reports its sample mean. Second, perhaps surprisingly, HAVER exhibits even better rates than this oracle when there are many distributions near the best one. Both of these improvements are the first of their kind in the literature, and we also prove that the naive algorithm that reports the largest empirical mean does not achieve these bounds. Finally, we confirm our theoretical findings via numerical experiments including bandits and Q-learning scenarios where HAVER outperforms baseline methods.

Large language models (LLMs) have enabled the development of numerous specialized, task-specific variants. However, the maintenance and deployment of these individual models present substantial challenges in terms of resource utilization and operational efficiency. In this work, we propose the \textit{Mixture of Distributions (MoD)} framework, a novel approach for merging LLMs that operates directly on their output probability distributions, rather than on model weights. Unlike traditional weight-averaging methods, MoD effectively preserves the specialized capabilities of individual models while enabling efficient knowledge sharing across tasks. Through extensive experimentation on mathematical reasoning benchmarks using Qwen2.5 models, we demonstrate that MoD significantly outperforms existing model merging techniques across multiple benchmarks. All code, data, and experimental materials are published at https://github.com/knovel-eng/mod.

As telecommunications systems progress to support diverse use cases with heterogeneous and dynamic Quality of Service (QoS) requirements, it becomes an increasingly complex task to automatically manage various resources involved -- from radio, compute, to X-haul network, which are distributed from the edge to the cloud. Intent-driven network automation can play an important role in NextG networks to meet this need. Towards this, we have developed INA-Infra, an open, extensible, and end-to-end 5G/beyond 5G network infrastructure with intent-driven network automation and end-to-end network slicing capability. INA-Infra is designed using open-source components and is based on O-RAN architecture. INA-Infra manages the network infrastructure, various resources, and (virtualized / containerized) network functions using Nephio -- a cloud-native intent automation solution. It also incorporates intent-driven intelligent control using a Resource Management rApp and a Network Slicing xApp. We demonstrate that INA-Infra can manage the 5G network in a highly automatic and optimized manner, allowing the mobile network operators to focus on specifying the intents of different traffic classes., Comment: Preprint version, published at workshop OpenRIT-6G, part of IEEE GLOBECOM 2024

Open Radio Access Networks (O-RAN) are expected to revolutionize the telecommunications industry with benefits like cost reduction, vendor diversity, and improved network performance through AI optimization. Supporting the O-RAN ALLIANCE's mission to achieve more intelligent, open, virtualized and fully interoperable mobile networks, O-RAN Open Testing and Integration Centers (OTICs) play a key role in accelerating the adoption of O-RAN specifications based on rigorous testing and validation. One theme in the recent O-RAN Global PlugFest Spring 2024 focused on demonstrating consistent and repeatable Open Fronthaul testing in multiple labs. To respond to this topic, in this paper, we present a detailed analysis of the testing methodologies and results for O-RAN Distributed Unit (O-DU) in O-RAN across two OTICs. We identify key differences in testing setups, share challenges encountered, and propose best practices for achieving repeatable and consistent testing results. Our findings highlight the impact of different deployment technologies and testing environments on performance and conformance testing outcomes, providing valuable insights for future O-RAN implementations., Comment: Published version at RitiRAN Workshop - co-located with IEEE VTC Fall 2024

Tracking dense 3D motion from monocular videos remains challenging, particularly when aiming for pixel-level precision over long sequences. We introduce DELTA, a novel method that efficiently tracks every pixel in 3D space, enabling accurate motion estimation across entire videos. Our approach leverages a joint global-local attention mechanism for reduced-resolution tracking, followed by a transformer-based upsampler to achieve high-resolution predictions. Unlike existing methods, which are limited by computational inefficiency or sparse tracking, DELTA delivers dense 3D tracking at scale, running over 8x faster than previous methods while achieving state-of-the-art accuracy. Furthermore, we explore the impact of depth representation on tracking performance and identify log-depth as the optimal choice. Extensive experiments demonstrate the superiority of DELTA on multiple benchmarks, achieving new state-of-the-art results in both 2D and 3D dense tracking tasks. Our method provides a robust solution for applications requiring fine-grained, long-term motion tracking in 3D space., Comment: Project Page: https://snap-research.github.io/DELTA/