Search

The accurate alignment of 3D woodblock geometrical models with 2D orthographic projection images presents a significant challenge in the digital preservation of Vietnamese cultural heritage. This paper proposes a unified image processing algorithm to address this issue, enhancing the registration quality between 3D woodblock models and their 2D representations. The method includes determining the plane of the 3D character model, establishing a transformation matrix to align this plane with the 2D printed image plane, and creating a parallel-projected depth map for precise alignment. This process minimizes disocclusions and ensures that character shapes and strokes are correctly positioned. Experimental results highlight the importance of structure-based comparisons to optimize alignment for large-scale Han-Nom character datasets. The proposed approach, combining density-based and structure-based methods, demonstrates improved registration performance, offering an effective normalization scheme for digital heritage preservation.

Singing is one of the most cherished forms of human entertainment. However, creating a beautiful song requires an accompaniment that complements the vocals and aligns well with the song instruments and genre. With advancements in deep learning, previous research has focused on generating suitable accompaniments but often lacks precise alignment with the desired instrumentation and genre. To address this, we propose a straightforward method that enables control over the accompaniment through text prompts, allowing the generation of music that complements the vocals and aligns with the song instrumental and genre requirements. Through extensive experiments, we successfully generate 10-second accompaniments using vocal input and text control.

6G wireless networks are expected to provide seamless and data-based connections that cover space-air-ground and underwater networks. As a core partition of future 6G networks, Space-Air-Ground Integrated Networks (SAGIN) have been envisioned to provide countless real-time intelligent applications. To realize this, promoting AI techniques into SAGIN is an inevitable trend. Due to the distributed and heterogeneous architecture of SAGIN, federated learning (FL) and then quantum FL are emerging AI model training techniques for enabling future privacy-enhanced and computation-efficient SAGINs. In this work, we explore the vision of using FL/QFL in SAGINs. We present a few representative applications enabled by the integration of FL and QFL in SAGINs. A case study of QFL over UAV networks is also given, showing the merit of quantum-enabled training approach over the conventional FL benchmark. Research challenges along with standardization for QFL adoption in future SAGINs are also highlighted., Comment: This work has been accepted by IEEE Conference on Standards for Communications and Networking

Consensus is arguably the most studied problem in distributed computing as a whole, and particularly in the distributed message-passing setting. In this latter framework, research on consensus has considered various hypotheses regarding the failure types, the memory constraints, the algorithmic performances (e.g., early stopping and obliviousness), etc. Surprisingly, almost all of this work assumes that messages are passed in a \emph{complete} network, i.e., each process has a direct link to every other process. Set-agreement, a relaxed variant of consensus, has also been heavily studied in the message-passing setting, yet research on it has also been limited to complete networks. A noticeable exception is the recent work of Casta\~neda et al. (Inf. Comput. 2023) who designed a generic oblivious algorithm for consensus running in $\radius(G,t)$ rounds in every graph $G$, when up to $t$ nodes can crash by irrevocably stopping, where $t$ is smaller than the node-connectivity $\kappa$ of $G$. Here, $\radius(G,t)$ denotes a graph parameter called the \emph{radius of $G$ whenever up to $t$ nodes can crash}. For $t=0$, this parameter coincides with $\radius(G)$, the standard radius of a graph, and, for $G=K_n$, the running time $\radius(K_n,t)=t +1$ of the algorithm exactly matches the known round-complexity of consensus in the clique $K_n$. Our main result is a proof that $\radius(G,t)$ rounds are necessary for oblivious algorithms solving consensus in $G$ when up to $t$ nodes can crash, thus validating a conjecture of Casta\~neda et al., and demonstrating that their consensus algorithm is optimal for any graph $G$. Finally, we extend the study of consensus in the $t$-resilient model in arbitrary graphs to the case where the number $t$ of failures is not necessarily smaller than the connectivity $\kappa$ of the considered graph., Comment: 23 pages, 5 figures

Material segmentation is a complex task, particularly when dealing with aerial data in poor lighting and atmospheric conditions. To address this, hyperspectral data from specialized cameras can be very useful in addition to RGB images. However, due to hardware constraints, high spectral data often come with lower spatial resolution. Additionally, incorporating such data into a learning-based segmentation framework is challenging due to the numerous data channels involved. To overcome these difficulties, we propose an innovative Siamese framework that uses time series-based compression to effectively and scalably integrate the additional spectral data into the segmentation task. We demonstrate our model's effectiveness through competitive benchmarks on aerial datasets in various environmental conditions., Comment: Accepted to the International Conference on Neural Information Processing (ICONIP) 2024. To be published in Springer-Nature Communications in Computer and Information Science (CCIS) Series

Empowering resource-limited robots to execute computationally intensive tasks such as locomotion and manipulation is challenging. This project provides a comprehensive design space exploration to determine optimal hardware computation architectures suitable for model-based control algorithms. We profile and optimize representative architectural designs across general-purpose scalar, vector processors, and specialized accelerators. Specifically, we compare CPUs, vector machines, and domain-specialized accelerators with kernel-level benchmarks and end-to-end representative robotic workloads. Our exploration provides a quantitative performance, area, and utilization comparison and analyzes the trade-offs between these representative distinct architectural designs. We demonstrate that architectural modifications, software, and system optimization can alleviate bottlenecks and enhance utilization. Finally, we propose a code generation flow to simplify the engineering work for mapping robotic workloads to specialized architectures., Comment: This submission has been withdrawn following further internal review and discussions with collaborators, as it was determined that the current version does not meet our intended standards, and will not be updated further. This decision aligns with internal changes and agreements that were finalized post-submission

This paper introduces a novel lossless compression method for compressing geometric attributes of point cloud data with bits-back coding. Our method specializes in using a deep learning-based probabilistic model to estimate the Shannon's entropy of the point cloud information, i.e., geometric attributes of the 3D floating points. Once the entropy of the point cloud dataset is estimated with a convolutional variational autoencoder (CVAE), we use the learned CVAE model to compress the geometric attributes of the point clouds with the bits-back coding technique. The novelty of our method with bits-back coding specializes in utilizing the learned latent variable model of the CVAE to compress the point cloud data. By using bits-back coding, we can capture the potential correlation between the data points, such as similar spatial features like shapes and scattering regions, into the lower-dimensional latent space to further reduce the compression ratio. The main insight of our method is that we can achieve a competitive compression ratio as conventional deep learning-based approaches, while significantly reducing the overhead cost of storage and/or communicating the compression codec, making our approach more applicable in practical scenarios. Throughout comprehensive evaluations, we found that the cost for the overhead is significantly small, compared to the reduction of the compression ratio when compressing large point cloud datasets. Experiment results show that our proposed approach can achieve a compression ratio of 1.56 bit-per-point on average, which is significantly lower than the baseline approach such as Google's Draco with a compression ratio of 1.83 bit-per-point., Comment: This paper is under reviewed in IEEE Robotics and Automation Letters

Federated Learning (FL) has emerged as a powerful paradigm for training machine learning models in a decentralized manner, preserving data privacy by keeping local data on clients. However, evaluating the robustness of these models against data perturbations on clients remains a significant challenge. Previous studies have assessed the effectiveness of models in centralized training based on certified accuracy, which guarantees that a certain percentage of the model's predictions will remain correct even if the input data is perturbed. However, the challenge of extending these evaluations to FL remains unresolved due to the unknown client's local data. To tackle this challenge, this study proposed a method named FedCert to take the first step toward evaluating the robustness of FL systems. The proposed method is designed to approximate the certified accuracy of a global model based on the certified accuracy and class distribution of each client. Additionally, considering the Non-Independent and Identically Distributed (Non-IID) nature of data in real-world scenarios, we introduce the client grouping algorithm to ensure reliable certified accuracy during the aggregation step of the approximation algorithm. Through theoretical analysis, we demonstrate the effectiveness of FedCert in assessing the robustness and reliability of FL systems. Moreover, experimental results on the CIFAR-10 and CIFAR-100 datasets under various scenarios show that FedCert consistently reduces the estimation error compared to baseline methods. This study offers a solution for evaluating the robustness of FL systems and lays the groundwork for future research to enhance the dependability of decentralized learning. The source code is available at https://github.com/thanhhff/FedCert/., Comment: The 22nd International Symposium on Network Computing and Applications (NCA 2024)

In personalized Federated Learning (pFL), high data heterogeneity can cause significant gradient divergence across devices, adversely affecting the learning process. This divergence, especially when gradients from different users form an obtuse angle during aggregation, can negate progress, leading to severe weight and gradient update degradation. To address this issue, we introduce a new approach to pFL design, namely Federated Learning with Layer-wise Aggregation via Gradient Analysis (FedLAG), utilizing the concept of gradient conflict at the layer level. Specifically, when layer-wise gradients of different clients form acute angles, those gradients align in the same direction, enabling updates across different clients toward identifying client-invariant features. Conversely, when layer-wise gradient pairs make create obtuse angles, the layers tend to focus on client-specific tasks. In hindsights, FedLAG assigns layers for personalization based on the extent of layer-wise gradient conflicts. Specifically, layers with gradient conflicts are excluded from the global aggregation process. The theoretical evaluation demonstrates that when integrated into other pFL baselines, FedLAG enhances pFL performance by a certain margin. Therefore, our proposed method achieves superior convergence behavior compared with other baselines. Extensive experiments show that our FedLAG outperforms several state-of-the-art methods and can be easily incorporated with many existing methods to further enhance performance.

Invariant causal prediction (ICP) is a popular technique for finding causal parents (direct causes) of a target via exploiting distribution shifts and invariance testing (Peters et al., 2016). However, since ICP needs to run an exponential number of tests and fails to identify parents when distribution shifts only affect a few variables, applying ICP to practical large scale problems is challenging. We propose MMSE-ICP and fastICP, two approaches which employ an error inequality to address the identifiability problem of ICP. The inequality states that the minimum prediction error of the predictor using causal parents is the smallest among all predictors which do not use descendants. fastICP is an efficient approximation tailored for large problems as it exploits the inequality and a heuristic to run fewer tests. MMSE-ICP and fastICP not only outperform competitive baselines in many simulations but also achieve state-of-the-art result on a large scale real data benchmark., Comment: Accepted at TMLR

Segmentation is a crucial task in the medical imaging field and is often an important primary step or even a prerequisite to the analysis of medical volumes. Yet treatments such as surgery complicate the accurate delineation of regions of interest. The BraTS Post-Treatment 2024 Challenge published the first public dataset for post-surgery glioma segmentation and addresses the aforementioned issue by fostering the development of automated segmentation tools for glioma in MRI data. In this effort, we propose two straightforward approaches to enhance the segmentation performances of deep learning-based methodologies. First, we incorporate an additional input based on a simple linear combination of the available MRI sequences input, which highlights enhancing tumors. Second, we employ various ensembling methods to weigh the contribution of a battery of models. Our results demonstrate that these approaches significantly improve segmentation performance compared to baseline models, underscoring the effectiveness of these simple approaches in improving medical image segmentation tasks., Comment: Invited for an Oral Presentation at the MICCAI BraTS Challenge 2024

Distribution shifts between sites can seriously degrade model performance since models are prone to exploiting unstable correlations. Thus, many methods try to find features that are stable across sites and discard unstable features. However, unstable features might have complementary information that, if used appropriately, could increase accuracy. More recent methods try to adapt to unstable features at the new sites to achieve higher accuracy. However, they make unrealistic assumptions or fail to scale to multiple confounding features. We propose Generalized Prevalence Adjustment (GPA for short), a flexible method that adjusts model predictions to the shifting correlations between prediction target and confounders to safely exploit unstable features. GPA can infer the interaction between target and confounders in new sites using unlabeled samples from those sites. We evaluate GPA on several real and synthetic datasets, and show that it outperforms competitive baselines., Comment: Accepted at ECCV

Accurate pain assessment is crucial in healthcare for effective diagnosis and treatment; however, traditional methods relying on self-reporting are inadequate for populations unable to communicate their pain. Cutting-edge AI is promising for supporting clinicians in pain recognition using facial video data. In this paper, we enhance pain recognition by employing facial video analysis within a Transformer-based deep learning model. By combining a powerful Masked Autoencoder with a Transformers-based classifier, our model effectively captures pain level indicators through both expressions and micro-expressions. We conducted our experiment on the AI4Pain dataset, which produced promising results that pave the way for innovative healthcare solutions that are both comprehensive and objective.

The creation of listener facial responses aims to simulate interactive communication feedback from a listener during a face-to-face conversation. Our goal is to generate believable videos of listeners' heads that respond authentically to a single speaker by a sequence-to-sequence model with an combination of WaveNet and Long short-term memory network. Our approach focuses on capturing the subtle nuances of listener feedback, ensuring the preservation of individual listener identity while expressing appropriate attitudes and viewpoints. Experiment results show that our method surpasses the baseline models on ViCo benchmark Dataset.

In this paper, we study a model for $S^1$-equivariant monopole Floer homology for rational homology three-spheres via a homological device called $\mathcal{S}$-complex. Using the Chern-Simons-Dirac functional, we define an $\mathbf{R}$-filtration on the (equivariant) complex of monopole Floer homology $HM$. This $\mathbf{R}$-filtration fits $HM$ into a persistent homology theory, from which one can define a numerical quantity called the spectral invariant $\rho$. The spectral invariant $\rho$ is tied with the geometry of the underlying manifold. The main result of the papers shows that $\rho$ provides an obstruction to the existence of positive scalar curvature metric on a ribbon homology cobordism., Comment: Comments are welcome! 54 pages, LaTex; typos corrected in statement of Theorem 1.6, references added for Subsection 1.2

(abridged) Together with gravity, turbulence, and stellar feedback, magnetic fields (B-fields) are thought to play a critical role in the evolution of molecular clouds and star formation processes. We aim to map the morphology and measure the strength of B-fields of the nearby molecular cloud, rho Ophiuchus-A ($\rho$ Oph-A), and then to understand the role of B-fields in regulating star formation and shaping the cloud. We have analyzed the far-infrared (FIR) polarization of thermal dust emission observed by SOFIA/HAWC$+$ at 89 and 154 $\mu$m toward the densest part of $\rho$ Oph-A, which is irradiated by the nearby B3/4 star, Oph-S1. The cloud exhibits well-ordered B-fields with magnetic orientations mainly perpendicular to the ridge of the cloud toward the densest region and B-field strengths are in the range of 0.2-2.5 mG, using the Davis-Chandrasekhar-Fermi method. The B-fields are strongest at the densest part of the cloud, which is associated with the starless core SM1, and decreases toward the outskirts of the cloud. By calculating the map of the mass-to-flux ratio, Alfv\'en Mach number, and plasma $\beta$ parameter in $\rho$ Oph-A, we find that the cloud is predominantly magnetically sub-critical, sub-Alfv\'enic, which implies that the cloud is supported by strong B-fields that dominate over gravity, turbulence, and thermal gas energy. Measured B-field strengths at two densest subregions using other methods that account for the compressible mode are relatively lower than that measured with the DCF method but do not significantly change our conclusions on the roles of B-fields relative to gravity and turbulence on star formation. A virial analysis suggests that the cloud is gravitationally unbound. We find that B-fields are sufficiently strong to support the cloud against radiative feedback and to regulate the shape of the cloud., Comment: Accepted to A&A

Real-time visual feedback from catheterization analysis is crucial for enhancing surgical safety and efficiency during endovascular interventions. However, existing datasets are often limited to specific tasks, small scale, and lack the comprehensive annotations necessary for broader endovascular intervention understanding. To tackle these limitations, we introduce CathAction, a large-scale dataset for catheterization understanding. Our CathAction dataset encompasses approximately 500,000 annotated frames for catheterization action understanding and collision detection, and 25,000 ground truth masks for catheter and guidewire segmentation. For each task, we benchmark recent related works in the field. We further discuss the challenges of endovascular intentions compared to traditional computer vision tasks and point out open research questions. We hope that CathAction will facilitate the development of endovascular intervention understanding methods that can be applied to real-world applications. The dataset is available at https://airvlab.github.io/cathaction/., Comment: 10 pages. Webpage: https://airvlab.github.io/cathaction/

The rapid growth of Large Language Models (LLMs) usage has highlighted the importance of gradient-free in-context learning (ICL). However, interpreting their inner workings remains challenging. This paper introduces a novel multimodal contrastive in-context learning framework to enhance our understanding of ICL in LLMs. First, we present a contrastive learning-based interpretation of ICL in real-world settings, marking the distance of the key-value representation as the differentiator in ICL. Second, we develop an analytical framework to address biases in multimodal input formatting for real-world datasets. We demonstrate the effectiveness of ICL examples where baseline performance is poor, even when they are represented in unseen formats. Lastly, we propose an on-the-fly approach for ICL (Anchored-by-Text ICL) that demonstrates effectiveness in detecting hateful memes, a task where typical ICL struggles due to resource limitations. Extensive experiments on multimodal datasets reveal that our approach significantly improves ICL performance across various scenarios, such as challenging tasks and resource-constrained environments. Moreover, it provides valuable insights into the mechanisms of in-context learning in LLMs. Our findings have important implications for developing more interpretable, efficient, and robust multimodal AI systems, especially in challenging tasks and resource-constrained environments.

Performance testing in large-scale database systems like SAP HANA is a crucial yet labor-intensive task, involving extensive manual analysis of thousands of measurements, such as CPU time and elapsed time. Manual maintenance of these metrics is time-consuming and susceptible to human error, making early detection of performance regressions challenging. We address these issues by proposing an automated approach to detect performance regressions in such measurements. Our approach integrates Bayesian inference with the Pruned Exact Linear Time (PELT) algorithm, enhancing the detection of change points and performance regressions with high precision and efficiency compared to previous approaches. Our method minimizes false negatives and ensures SAP HANA's system's reliability and performance quality. The proposed solution can accelerate testing and contribute to more sustainable performance management practices in large-scale data management environments.

In recent years, there has been an increasing number of frameworks developed for biomedical entity and relation extraction. This research effort aims to address the accelerating growth in biomedical publications and the intricate nature of biomedical texts, which are written for mainly domain experts. To handle these challenges, we develop a novel framework that utilizes external knowledge to construct a task-independent and reusable background knowledge graph for biomedical entity and relation extraction. The design of our model is inspired by how humans learn domain-specific topics. In particular, humans often first acquire the most basic and common knowledge regarding a field to build the foundational knowledge and then use that as a basis for extending to various specialized topics. Our framework employs such common-knowledge-sharing mechanism to build a general neural-network knowledge graph that is learning transferable to different domain-specific biomedical texts effectively. Experimental evaluations demonstrate that our model, equipped with this generalized and cross-transferable knowledge base, achieves competitive performance benchmarks, including BioRelEx for binding interaction detection and ADE for Adverse Drug Effect identification.

Large Language Models (LLMs) have demonstrated remarkable success across various domains but often lack fairness considerations, potentially leading to discriminatory outcomes against marginalized populations. Unlike fairness in traditional machine learning, fairness in LLMs involves unique backgrounds, taxonomies, and fulfillment techniques. This tutorial provides a systematic overview of recent advances in the literature concerning fair LLMs, beginning with real-world case studies to introduce LLMs, followed by an analysis of bias causes therein. The concept of fairness in LLMs is then explored, summarizing the strategies for evaluating bias and the algorithms designed to promote fairness. Additionally, resources for assessing bias in LLMs, including toolkits and datasets, are compiled, and current research challenges and open questions in the field are discussed. The repository is available at \url{https://github.com/LavinWong/Fairness-in-Large-Language-Models}.

This paper formalises the Canadian Traveller problem as a positional two-player game on graphs. We consider two variants depending on whether an edge is blocked. In the locally-informed variant, the traveller learns if an edge is blocked upon reaching one of its endpoints, while in the uninformed variant, they discover this only when the edge is supposed to appear. We provide a polynomial algorithm for each shortest path variant in the uninformed case. This algorithm also solves the case of directed acyclic non-temporal graphs. In the locally-informed case, we prove that finding a winning strategy is PSPACE-complete. Moreover, we establish that the problem is polynomial-time solvable when $k=1$ but NP-hard for $k\geq 2$. Additionally, we show that the standard (non-temporal) Canadian Traveller Problem is NP-hard when there are $k\geq 4$ blocked edges, which is, to the best of our knowledge, the first hardness result for CTP for a constant number of blocked edges.

Combining different data modalities enables deep neural networks to tackle complex tasks more effectively, making multimodal learning increasingly popular. To harness multimodal data closer to end users, it is essential to integrate multimodal learning with privacy-preserving approaches like federated learning (FL). However, compared to conventional unimodal learning, multimodal setting requires dedicated encoders for each modality, resulting in larger and more complex models. Training these models requires significant resources, presenting a substantial challenge for FL clients operating with limited computation and communication resources. To address these challenges, we introduce LW-FedMML, a layer-wise federated multimodal learning approach which decomposes the training process into multiple stages. Each stage focuses on training only a portion of the model, thereby significantly reducing the memory and computational requirements. Moreover, FL clients only need to exchange the trained model portion with the central server, lowering the resulting communication cost. We conduct extensive experiments across various FL and multimodal learning settings to validate the effectiveness of our proposed method. The results demonstrate that LW-FedMML can compete with conventional end-to-end federated multimodal learning (FedMML) while significantly reducing the resource burden on FL clients. Specifically, LW-FedMML reduces memory usage by up to $2.7\times$, computational operations (FLOPs) by $2.4\times$, and total communication cost by $2.3\times$. We also explore a progressive training approach called Prog-FedMML. While it offers lesser resource efficiency than LW-FedMML, Prog-FedMML has the potential to surpass the performance of end-to-end FedMML, making it a viable option for scenarios with fewer resource constraints.

This paper examines the pricing issue of margin-call stock loans with finite maturities under the Black-Scholes-Merton framework. In particular, using a Fourier Sine transform method, we reduce the partial differential equation governing the price of a margin-call stock loan into an ordinary differential equation, the solution of which can be easily found (in the Fourier Sine space) and analytically inverted into the original space. As a result, we obtain an integral representation of the value of the stock loan in terms of the unknown optimal exit prices, which are, in turn, governed by a Volterra integral equation. We thus can break the pricing problem of margin-call stock loans into two steps: 1) finding the optimal exit prices by solving numerically the governing Volterra integral equation and 2) calculating the values of margin-call stock loans based on the obtained optimal exit prices. By validating and comparing with other available numerical methods, we show that our proposed numerical scheme offers a reliable and efficient way to calculate the service fee of a margin-call stock loan contract, track the contract value over time, and compute the level of stock price above which it is optimal to exit the contract. The effects of the margin-call feature on the loan contract are also examined and quantified.

Modern reinforcement learning (RL) struggles to capture real-world cause-and-effect dynamics, leading to inefficient exploration due to extensive trial-and-error actions. While recent efforts to improve agent exploration have leveraged causal discovery, they often make unrealistic assumptions of causal variables in the environments. In this paper, we introduce a novel framework, Variable-Agnostic Causal Exploration for Reinforcement Learning (VACERL), incorporating causal relationships to drive exploration in RL without specifying environmental causal variables. Our approach automatically identifies crucial observation-action steps associated with key variables using attention mechanisms. Subsequently, it constructs the causal graph connecting these steps, which guides the agent towards observation-action pairs with greater causal influence on task completion. This can be leveraged to generate intrinsic rewards or establish a hierarchy of subgoals to enhance exploration efficiency. Experimental results showcase a significant improvement in agent performance in grid-world, 2d games and robotic domains, particularly in scenarios with sparse rewards and noisy actions, such as the notorious Noisy-TV environments.

We introduce an approach to identifying speaker names in dialogue transcripts, a crucial task for enhancing content accessibility and searchability in digital media archives. Despite the advancements in speech recognition, the task of text-based speaker identification (SpeakerID) has received limited attention, lacking large-scale, diverse datasets for effective model training. Addressing these gaps, we present a novel, large-scale dataset derived from the MediaSum corpus, encompassing transcripts from a wide range of media sources. We propose novel transformer-based models tailored for SpeakerID, leveraging contextual cues within dialogues to accurately attribute speaker names. Through extensive experiments, our best model achieves a great precision of 80.3\%, setting a new benchmark for SpeakerID. The data and code are publicly available here: \url{https://github.com/adobe-research/speaker-identification}, Comment: accepted to INTERSPEECH 2024

In the Emotion Recognition in Conversation task, recent investigations have utilized attention mechanisms exploring relationships among utterances from intra- and inter-speakers for modeling emotional interaction between them. However, attributes such as speaker personality traits remain unexplored and present challenges in terms of their applicability to other tasks or compatibility with diverse model architectures. Therefore, this work introduces a novel framework named BiosERC, which investigates speaker characteristics in a conversation. By employing Large Language Models (LLMs), we extract the "biographical information" of the speaker within a conversation as supplementary knowledge injected into the model to classify emotional labels for each utterance. Our proposed method achieved state-of-the-art (SOTA) results on three famous benchmark datasets: IEMOCAP, MELD, and EmoryNLP, demonstrating the effectiveness and generalization of our model and showcasing its potential for adaptation to various conversation analysis tasks. Our source code is available at https://github.com/yingjie7/BiosERC., Comment: Accepted in the 33rd International Conference on Artificial Neural Networks (ICANN 2024)

Large Language Models (LLMs) generate text by sampling the next token from a probability distribution over the vocabulary at each decoding step. However, popular sampling methods like top-p (nucleus sampling) often struggle to balance quality and diversity, especially at higher temperatures, leading to incoherent or repetitive outputs. To address this challenge, we propose min-p sampling, a dynamic truncation method that adjusts the sampling threshold based on the model's confidence by scaling according to the top token's probability. We conduct extensive experiments on benchmarks including GPQA, GSM8K, and AlpacaEval Creative Writing, demonstrating that min-p sampling improves both the quality and diversity of generated text, particularly at high temperatures. Moreover, human evaluations reveal a clear preference for min-p sampling in terms of both text quality and diversity. Min-p sampling has been adopted by multiple open-source LLM implementations, highlighting its practical utility and potential impact., Comment: 20 Pages, revised from 8 pages initially. Main additions include: General full rewrite/reformatting, more comparisons with other sampling methods (eta, epsilon, top-k) on 7B parameter models, more benchmarks for >70B parameter models, human evaluation, theoretical explanations, ethics statement, reproducibility and acknowledgements

Clifford Taubes showed that the moduli space of the variational equation of the Yang-Mills-Higgs functional on the plane is non-empty, and its elements correspond to "vortices". Inspired by this result, in this paper, we show that the moduli space of the Hitchin-type dimensional reduction of the Seiberg-Witten equations on the plane contains both exponentially decayed solutions and polynomial growth solutions. Furthermore, we show that there is correspondence from the moduli space of exponentially decayed and polynomial growth solutions to the symmetric products of complex numbers. The correspondence restricted to the latter is a surjective map., Comment: 32 pages, comments are welcome!

Software agents have emerged as promising tools for addressing complex software engineering tasks. Existing works, on the other hand, frequently oversimplify software development workflows, despite the fact that such workflows are typically more complex in the real world. Thus, we propose AgileCoder, a multi agent system that integrates Agile Methodology (AM) into the framework. This system assigns specific AM roles - such as Product Manager, Developer, and Tester to different agents, who then collaboratively develop software based on user inputs. AgileCoder enhances development efficiency by organizing work into sprints, focusing on incrementally developing software through sprints. Additionally, we introduce Dynamic Code Graph Generator, a module that creates a Code Dependency Graph dynamically as updates are made to the codebase. This allows agents to better comprehend the codebase, leading to more precise code generation and modifications throughout the software development process. AgileCoder surpasses existing benchmarks, like ChatDev and MetaGPT, establishing a new standard and showcasing the capabilities of multi agent systems in advanced software engineering environments., Comment: Work in progress

We present MV2Cyl, a novel method for reconstructing 3D from 2D multi-view images, not merely as a field or raw geometry but as a sketch-extrude CAD model. Extracting extrusion cylinders from raw 3D geometry has been extensively researched in computer vision, while the processing of 3D data through neural networks has remained a bottleneck. Since 3D scans are generally accompanied by multi-view images, leveraging 2D convolutional neural networks allows these images to be exploited as a rich source for extracting extrusion cylinder information. However, we observe that extracting only the surface information of the extrudes and utilizing it results in suboptimal outcomes due to the challenges in the occlusion and surface segmentation. By synergizing with the extracted base curve information, we achieve the optimal reconstruction result with the best accuracy in 2D sketch and extrude parameter estimation. Our experiments, comparing our method with previous work that takes a raw 3D point cloud as input, demonstrate the effectiveness of our approach by taking advantage of multi-view images., Comment: NeurIPS 2024

We study the question of how best to assign an encouragement in a randomized encouragement study. In our setting, units arrive with covariates, receive a nudge toward treatment or control, acquire one of those statuses in a way that need not align with the nudge, and finally have a response observed. The nudge can be seen as a binary instrument that affects the response only via the treatment status. Our goal is to assign the nudge as a function of covariates in a way that best estimates the local average treatment effect (LATE). We assume a partially linear model, wherein the baseline model is non-parametric and the treatment term is linear in the covariates. Under this model, we outline a two-stage procedure to consistently estimate the LATE. Though the variance of the LATE is intractable, we derive a finite sample approximation and thus a design criterion to minimize. This criterion is convex, allowing for constraints that might arise for budgetary or ethical reasons. We prove conditions under which our solution asymptotically recovers the lowest true variance among all possible nudge propensities. We apply our method to a semi-synthetic example involving triage in an emergency department and find significant gains relative to a regression discontinuity design., Comment: 31 pages, 6 figures

Inspired by the renaissance of optical computing recently, this poster presents a disruptive outlook on the possibility of seamless integration between optical communications and optical computing infrastructures, paving the way for achieving optical-layer intelligence and consequently boosting the capacity efficiency. This entails a paradigm shift in optical node architecture from the currently used optical-bypass to a novel one, entitled, optical-computing-enabled mode, where in addition to the traditional add-drop and cross-connect functionalities, optical nodes are upgraded to account for optical-computing capabilities between the lightpath entities directly at the optical layer. A preliminary study focusing on the optical aggregation operation is examined and early simulation results indicate a promising spectral saving enabled by the optical-computing-enabled mode compared with the optical-bypass one., Comment: 2-page poster, to be appeared in Proceedings of the 8th Asia-Pacific Workshop on Networking (APNet 2024)

Deep learning models can extract predictive and actionable information from complex inputs. The richer the inputs, the better these models usually perform. However, models that leverage rich inputs (e.g., multi-modality) can be difficult to deploy widely, because some inputs may be missing at inference. Current popular solutions to this problem include marginalization, imputation, and training multiple models. Marginalization can obtain calibrated predictions but it is computationally costly and therefore only feasible for low dimensional inputs. Imputation may result in inaccurate predictions because it employs point estimates for missing variables and does not work well for high dimensional inputs (e.g., images). Training multiple models whereby each model takes different subsets of inputs can work well but requires knowing missing input patterns in advance. Furthermore, training and retaining multiple models can be costly. We propose an efficient way to learn both the conditional distribution using full inputs and the marginal distributions. Our method, Knockout, randomly replaces input features with appropriate placeholder values during training. We provide a theoretical justification of Knockout and show that it can be viewed as an implicit marginalization strategy. We evaluate Knockout in a wide range of simulations and real-world datasets and show that it can offer strong empirical performance.

The success of Artificial Intelligence (AI) in multiple disciplines and vertical domains in recent years has promoted the evolution of mobile networking and the future Internet toward an AI-integrated Internet-of-Things (IoT) era. Nevertheless, most AI techniques rely on data generated by physical devices (e.g., mobile devices and network nodes) or specific applications (e.g., fitness trackers and mobile gaming). Therefore, Generative AI (GAI), a.k.a. AI-generated content (AIGC), has emerged as a powerful AI paradigm; thanks to its ability to efficiently learn complex data distributions and generate synthetic data to represent the original data in various forms. This impressive feature is projected to transform the management of mobile networking and diversify the current services and applications provided. On this basis, this work presents a concise tutorial on the role of GAIs in mobile and wireless networking. In particular, this survey first provides the fundamentals of GAI and representative GAI models, serving as an essential preliminary to the understanding of GAI's applications in mobile and wireless networking. Then, this work provides a comprehensive review of state-of-the-art studies and GAI applications in network management, wireless security, semantic communication, and lessons learned from the open literature. Finally, this work summarizes the current research on GAI for mobile and wireless networking by outlining important challenges that need to be resolved to facilitate the development and applicability of GAI in this edge-cutting area., Comment: This work has been accepted for publication in the IEEE Internet of Things Journal under ID number IoT-37996-2024

Recent advancements in Large Language Models (LLMs) have shown significant potential in enhancing recommender systems. However, addressing the cold-start recommendation problem, where users lack historical data, remains a considerable challenge. In this paper, we introduce KALM4Rec (Keyword-driven Retrieval-Augmented Large Language Models for Cold-start User Recommendations), a novel framework specifically designed to tackle this problem by requiring only a few input keywords from users in a practical scenario of cold-start user restaurant recommendations. KALM4Rec operates in two main stages: candidates retrieval and LLM-based candidates re-ranking. In the first stage, keyword-driven retrieval models are used to identify potential candidates, addressing LLMs' limitations in processing extensive tokens and reducing the risk of generating misleading information. In the second stage, we employ LLMs with various prompting strategies, including zero-shot and few-shot techniques, to re-rank these candidates by integrating multiple examples directly into the LLM prompts. Our evaluation, using a Yelp restaurant dataset with user reviews from three English-speaking cities, shows that our proposed framework significantly improves recommendation quality. Specifically, the integration of in-context instructions with LLMs for re-ranking markedly enhances the performance of the cold-start user recommender system., Comment: 10 pages, 10 figures, 4 tables

Machine learning algorithms have become indispensable in today's world. They support and accelerate the way we make decisions based on the data at hand. This acceleration means that data structures that were valid at one moment could no longer be valid in the future. With these changing data structures, it is necessary to adapt machine learning (ML) systems incrementally to the new data. This is done with the use of online learning or continuous ML technologies. While deep learning technologies have shown exceptional performance on predefined datasets, they have not been widely applied to online, streaming, and continuous learning. In this retrospective of our tutorial titled Opportunities and Challenges of Online Deep Learning held at ECML PKDD 2023, we provide a brief overview of the opportunities but also the potential pitfalls for the application of neural networks in online learning environments using the frameworks River and Deep-River., Comment: Accepted for publication on ECML-PKDD 2023 joint Post-Workshop Proceeding

When performing manipulation-based activities such as picking objects, a mobile robot needs to position its base at a location that supports successful execution. To address this problem, prominent approaches typically rely on costly grasp planners to provide grasp poses for a target object, which are then are then analysed to identify the best robot placements for achieving each grasp pose. In this paper, we propose instead to first find robot placements that would not result in collision with the environment and from where picking up the object is feasible, then evaluate them to find the best placement candidate. Our approach takes into account the robot's reachability, as well as RGB-D images and occupancy grid maps of the environment for identifying suitable robot poses. The proposed algorithm is embedded in a service robotic workflow, in which a person points to select the target object for grasping. We evaluate our approach with a series of grasping experiments, against an existing baseline implementation that sends the robot to a fixed navigation goal. The experimental results show how the approach allows the robot to grasp the target object from locations that are very challenging to the baseline implementation.

We show the non-compactness of moduli space of solutions of the monopole equations for $3/2$-spinors on a closed 3-manifold is equivalent to the existence of `3/2-Fueter sections' that are solutions of an overdetermined non-linear elliptic differential equation. These are sections of a fiber bundle whose fiber is a special 4-dimensional submanifold of the hyperk\"ahler manifold of center-framed charged one $SU(2)$-instantons on $\mathbf{R}^4$. This fiber bundle does not inherit a hyperk\"ahler structure., Comment: Comments are welcome

A low-cost approach for stochastically sampling static exchange during TDHF-type propagation is presented. This enables the use of an excellent hybrid DFT starting point for stochastic GW quasiparticle energy calculations. Generalized Kohn-Sham molecular orbitals and energies, rather than those of a local-DFT calculation, are used for building the Green's function and effective Coulomb interaction. The use of an optimally tuned hybrid diminishes the starting point dependency in one-shot stochastic GW, effectively avoiding the need for self-consistent GW iterations., Comment: 18 pages, 1 figure

Named Entity Recognition and Relation Extraction are two crucial and challenging subtasks in the field of Information Extraction. Despite the successes achieved by the traditional approaches, fundamental research questions remain open. First, most recent studies use parameter sharing for a single subtask or shared features for both two subtasks, ignoring their semantic differences. Second, information interaction mainly focuses on the two subtasks, leaving the fine-grained informtion interaction among the subtask-specific features of encoding subjects, relations, and objects unexplored. Motivated by the aforementioned limitations, we propose a novel model to jointly extract entities and relations. The main novelties are as follows: (1) We propose to decouple the feature encoding process into three parts, namely encoding subjects, encoding objects, and encoding relations. Thanks to this, we are able to use fine-grained subtask-specific features. (2) We propose novel inter-aggregation and intra-aggregation strategies to enhance the information interaction and construct individual fine-grained subtask-specific features, respectively. The experimental results demonstrate that our model outperforms several previous state-of-the-art models. Extensive additional experiments further confirm the effectiveness of our model.

The emergence of multimodal data on social media platforms presents new opportunities to better understand user sentiments toward a given aspect. However, existing multimodal datasets for Aspect-Category Sentiment Analysis (ACSA) often focus on textual annotations, neglecting fine-grained information in images. Consequently, these datasets fail to fully exploit the richness inherent in multimodal. To address this, we introduce a new Vietnamese multimodal dataset, named ViMACSA, which consists of 4,876 text-image pairs with 14,618 fine-grained annotations for both text and image in the hotel domain. Additionally, we propose a Fine-Grained Cross-Modal Fusion Framework (FCMF) that effectively learns both intra- and inter-modality interactions and then fuses these information to produce a unified multimodal representation. Experimental results show that our framework outperforms SOTA models on the ViMACSA dataset, achieving the highest F1 score of 79.73%. We also explore characteristics and challenges in Vietnamese multimodal sentiment analysis, including misspellings, abbreviations, and the complexities of the Vietnamese language. This work contributes both a benchmark dataset and a new framework that leverages fine-grained multimodal information to improve multimodal aspect-category sentiment analysis. Our dataset is available for research purposes: https://github.com/hoangquy18/Multimodal-Aspect-Category-Sentiment-Analysis.

Wireless information and energy transfer (WIET) represents an emerging paradigm which employs controllable transmission of radio-frequency signals for the dual purpose of data communication and wireless charging. As such, WIET is widely regarded as an enabler of envisioned 6G use cases that rely on energy-sustainable Internet-of-Things (IoT) networks, such as smart cities and smart grids. Meeting the quality-of-service demands of WIET, in terms of both data transfer and power delivery, requires effective co-design of the information and energy signals. In this article, we present the main principles and design aspects of WIET, focusing on its integration in 6G networks. First, we discuss how conventional communication notions such as resource allocation and waveform design need to be revisited in the context of WIET. Next, we consider various candidate 6G technologies that can boost WIET efficiency, namely, holographic multiple-input multiple-output, near-field beamforming, terahertz communication, intelligent reflecting surfaces (IRSs), and reconfigurable (fluid) antenna arrays. We introduce respective WIET design methods, analyze the promising performance gains of these WIET systems, and discuss challenges, open issues, and future research directions. Finally, a near-field energy beamforming scheme and a power-based IRS beamforming algorithm are experimentally validated using a wireless energy transfer testbed. The vision of WIET in communication systems has been gaining momentum in recent years, with constant progress with respect to theoretical but also practical aspects. The comprehensive overview of the state of the art of WIET presented in this paper highlights the potentials of WIET systems as well as their overall benefits in 6G networks., Comment: Proceedings of the IEEE, 36 pages, 33 figures

Reinforcement learning (RL) with continuous state and action spaces remains one of the most challenging problems within the field. Most current learning methods focus on integral identities such as value functions to derive an optimal strategy for the learning agent. In this paper, we instead study the dual form of the original RL formulation to propose the first differential RL framework that can handle settings with limited training samples and short-length episodes. Our approach introduces Differential Policy Optimization (DPO), a pointwise and stage-wise iteration method that optimizes policies encoded by local-movement operators. We prove a pointwise convergence estimate for DPO and provide a regret bound comparable with the best current theoretical derivation. Such pointwise estimate ensures that the learned policy matches the optimal path uniformly across different steps. We then apply DPO to a class of practical RL problems with continuous state and action spaces, and which search for optimal configurations with Lagrangian rewards. DPO is easy to implement, scalable, and shows competitive results on benchmarking experiments against several popular RL methods.

Large Language Models (LLMs) can perform various natural language processing tasks with suitable instruction prompts. However, designing effective prompts manually is challenging and time-consuming. Existing methods for automatic prompt optimization either lack flexibility or efficiency. In this paper, we propose an effective approach to automatically select the optimal prompt for a given input from a finite set of synthetic candidate prompts. Our approach consists of three steps: (1) clustering the training data and generating candidate prompts for each cluster using an LLM-based prompt generator; (2) synthesizing a dataset of input-prompt-output tuples for training a prompt evaluator to rank the prompts based on their relevance to the input; (3) using the prompt evaluator to select the best prompt for a new input at test time. Our approach balances prompt generality-specificity and eliminates the need for resource-intensive training and inference. It demonstrates competitive performance on zero-shot question-answering datasets: GSM8K, MultiArith, and AQuA., Comment: preprint

Autonomous ground vehicle (UGV) navigation has the potential to revolutionize the transportation system by increasing accessibility to disabled people, ensure safety and convenience of use. However, UGV requires extensive and efficient testing and evaluation to ensure its acceptance for public use. This testing are mostly done in a simulator which result to sim2real transfer gap. In this paper, we propose a digital twin perception awareness approach for the control of robot navigation without prior creation of the virtual environment (VT) environment state. To achieve this, we develop a twin delayed deep deterministic policy gradient (TD3) algorithm that ensures collision avoidance and goal-based path planning. We demonstrate the performance of our approach on different environment dynamics. We show that our approach is capable of efficiently avoiding collision with obstacles and navigating to its desired destination, while at the same time safely avoids obstacles using the information received from the LIDAR sensor mounted on the robot. Our approach bridges the gap between sim-to-real transfer and contributes to the adoption of UGVs in real world. We validate our approach in simulation and a real-world application in an office space., Comment: 8 pages, 7 figures

The evolution and growing automation of collaborative robots introduce more complexity and unpredictability to systems, highlighting the crucial need for robot's adaptability and flexibility to address the increasing complexities of their environment. In typical industrial production scenarios, robots are often required to be re-programmed when facing a more demanding task or even a few changes in workspace conditions. To increase productivity, efficiency and reduce human effort in the design process, this paper explores the potential of using digital twin combined with Reinforcement Learning (RL) to enable robots to generate self-improving collision-free trajectories in real time. The digital twin, acting as a virtual counterpart of the physical system, serves as a 'forward run' for monitoring, controlling, and optimizing the physical system in a safe and cost-effective manner. The physical system sends data to synchronize the digital system through the video feeds from cameras, which allows the virtual robot to update its observation and policy based on real scenarios. The bidirectional communication between digital and physical systems provides a promising platform for hardware-in-the-loop RL training through trial and error until the robot successfully adapts to its new environment. The proposed online training framework is demonstrated on the Unfactory Xarm5 collaborative robot, where the robot end-effector aims to reach the target position while avoiding obstacles. The experiment suggest that proposed framework is capable of performing policy online training, and that there remains significant room for improvement., Comment: 7 pages

Charts, figures, and text derived from data play an important role in decision making, from data-driven policy development to day-to-day choices informed by online articles. Making sense of, or fact-checking, outputs means understanding how they relate to the underlying data. Even for domain experts with access to the source code and data sets, this poses a significant challenge. In this paper we introduce a new program analysis framework which supports interactive exploration of fine-grained I/O relationships directly through computed outputs, making use of dynamic dependence graphs. Our main contribution is a novel notion in data provenance which we call related inputs, a relation of mutual relevance or "cognacy" which arises between inputs when they contribute to common features of the output. Queries of this form allow readers to ask questions like "What outputs use this data element, and what other data elements are used along with it?". We show how Jonsson and Tarski's concept of conjugate operators on Boolean algebras appropriately characterises the notion of cognacy in a dependence graph, and give a procedure for computing related inputs over such a graph.

In this new era of rapid AI development, especially in language processing, the demand for AI in the legal domain is increasingly critical. In the context where research in other languages such as English, Japanese, and Chinese has been well-established, we introduce the first fundamental research for the Vietnamese language in the legal domain: legal textual entailment recognition through the Vietnamese Language and Speech Processing workshop. In analyzing participants' results, we discuss certain linguistic aspects critical in the legal domain that pose challenges that need to be addressed.