Search

We address the challenges of the semi-supervised LiDAR segmentation (SSLS) problem, particularly in low-budget scenarios. The two main issues in low-budget SSLS are the poor-quality pseudo-labels for unlabeled data, and the performance drops due to the significant imbalance between ground-truth and pseudo-labels. This imbalance leads to a vicious training cycle. To overcome these challenges, we leverage the spatio-temporal prior by recognizing the substantial overlap between temporally adjacent LiDAR scans. We propose a proximity-based label estimation, which generates highly accurate pseudo-labels for unlabeled data by utilizing semantic consistency with adjacent labeled data. Additionally, we enhance this method by progressively expanding the pseudo-labels from the nearest unlabeled scans, which helps significantly reduce errors linked to dynamic classes. Additionally, we employ a dual-branch structure to mitigate performance degradation caused by data imbalance. Experimental results demonstrate remarkable performance in low-budget settings (i.e., <= 5%) and meaningful improvements in normal budget settings (i.e., 5 - 50%). Finally, our method has achieved new state-of-the-art results on SemanticKITTI and nuScenes in semi-supervised LiDAR segmentation. With only 5% labeled data, it offers competitive results against fully-supervised counterparts. Moreover, it surpasses the performance of the previous state-of-the-art at 100% labeled data (75.2%) using only 20% of labeled data (76.0%) on nuScenes. The code is available on https://github.com/halbielee/PLE.

This study introduces CUPID, a novel approach to session-based reciprocal recommendation systems designed for a real-time one-on-one social discovery platform. In such platforms, low latency is critical to enhance user experiences. However, conventional session-based approaches struggle with high latency due to the demands of modeling sequential user behavior for each recommendation process. Additionally, given the reciprocal nature of the platform, where users act as items for each other, training recommendation models on large-scale datasets is computationally prohibitive using conventional methods. To address these challenges, CUPID decouples the time-intensive user session modeling from the real-time user matching process to reduce inference time. Furthermore, CUPID employs a two-phase training strategy that separates the training of embedding and prediction layers, significantly reducing the computational burden by decreasing the number of sequential model inferences by several hundredfold. Extensive experiments on large-scale Azar datasets demonstrate CUPID's effectiveness in a real-world production environment. Notably, CUPID reduces response latency by more than 76% compared to non-asynchronous systems, while significantly improving user engagement., Comment: The 2nd International Workshop on User Understanding from Big Data Workshop (DMU2 2024)

Recent advances in diffusion models have introduced a new era of text-guided image manipulation, enabling users to create realistic edited images with simple textual prompts. However, there is significant concern about the potential misuse of these methods, especially in creating misleading or harmful content. Although recent defense strategies, which introduce imperceptible adversarial noise to induce model failure, have shown promise, they remain ineffective against more sophisticated manipulations, such as editing with a mask. In this work, we propose DiffusionGuard, a robust and effective defense method against unauthorized edits by diffusion-based image editing models, even in challenging setups. Through a detailed analysis of these models, we introduce a novel objective that generates adversarial noise targeting the early stage of the diffusion process. This approach significantly improves the efficiency and effectiveness of adversarial noises. We also introduce a mask-augmentation technique to enhance robustness against various masks during test time. Finally, we introduce a comprehensive benchmark designed to evaluate the effectiveness and robustness of methods in protecting against privacy threats in realistic scenarios. Through extensive experiments, we show that our method achieves stronger protection and improved mask robustness with lower computational costs compared to the strongest baseline. Additionally, our method exhibits superior transferability and better resilience to noise removal techniques compared to all baseline methods. Our source code is publicly available at https://github.com/choi403/DiffusionGuard., Comment: Preprint. Under review

Large language models (LLMs), like ChatGPT, have shown that even trained with noisy prior data, they can generalize effectively to new tasks through in-context learning (ICL) and pre-training techniques. Motivated by this, we explore whether a similar approach can be applied to scientific foundation models (SFMs). Our methodology is structured as follows: (i) we collect low-cost physics-informed neural network (PINN)-based approximated prior data in the form of solutions to partial differential equations (PDEs) constructed through an arbitrary linear combination of mathematical dictionaries; (ii) we utilize Transformer architectures with self and cross-attention mechanisms to predict PDE solutions without knowledge of the governing equations in a zero-shot setting; (iii) we provide experimental evidence on the one-dimensional convection-diffusion-reaction equation, which demonstrate that pre-training remains robust even with approximated prior data, with only marginal impacts on test accuracy. Notably, this finding opens the path to pre-training SFMs with realistic, low-cost data instead of (or in conjunction with) numerical high-cost data. These results support the conjecture that SFMs can improve in a manner similar to LLMs, where fully cleaning the vast set of sentences crawled from the Internet is nearly impossible.

Many real-world datasets, such as healthcare, climate, and economics, are often collected as irregular time series, which poses challenges for accurate modeling. In this paper, we propose the Amortized Control of continuous State Space Model (ACSSM) for continuous dynamical modeling of time series for irregular and discrete observations. We first present a multi-marginal Doob's $h$-transform to construct a continuous dynamical system conditioned on these irregular observations. Following this, we introduce a variational inference algorithm with a tight evidence lower bound (ELBO), leveraging stochastic optimal control (SOC) theory to approximate the intractable Doob's $h$-transform and simulate the conditioned dynamics. To improve efficiency and scalability during both training and inference, ACSSM employs amortized inference to decouple representation learning from the latent dynamics. Additionally, it incorporates a simulation-free latent dynamics framework and a transformer-based data assimilation scheme, facilitating parallel inference of the latent states and ELBO computation. Through empirical evaluations across a variety of real-world datasets, ACSSM demonstrates superior performance in tasks such as classification, regression, interpolation, and extrapolation, while maintaining computational efficiency.

Neural fields are an emerging paradigm that represent data as continuous functions parameterized by neural networks. Despite many advantages, neural fields often have a high training cost, which prevents a broader adoption. In this paper, we focus on a popular family of neural fields, called sinusoidal neural fields (SNFs), and study how it should be initialized to maximize the training speed. We find that the standard initialization scheme for SNFs -- designed based on the signal propagation principle -- is suboptimal. In particular, we show that by simply multiplying each weight (except for the last layer) by a constant, we can accelerate SNF training by 10$\times$. This method, coined $\textit{weight scaling}$, consistently provides a significant speedup over various data domains, allowing the SNFs to train faster than more recently proposed architectures. To understand why the weight scaling works well, we conduct extensive theoretical and empirical analyses which reveal that the weight scaling not only resolves the spectral bias quite effectively but also enjoys a well-conditioned optimization trajectory.

Traditional network management algorithms have relied on prior knowledge of system models and networking scenarios. In practice, a universal optimization framework is desirable where a sole optimization module can be readily applied to arbitrary network management tasks without any knowledge of the system. To this end, knowledge-free optimization techniques are necessary whose operations are independent of scenario-specific information including objective functions, system parameters, and network setups. The major challenge of this paradigm-shifting approach is the requirement of a hyper-intelligent black-box optimizer that can establish efficient decision-making policies using its internal reasoning capabilities. This article presents a novel knowledge-free network management paradigm with the power of foundation models called large language models (LLMs). Trained on vast amounts of datasets, LLMs can understand important contexts from input prompts containing minimal system information, thereby offering remarkable inference performance even for entirely new tasks. Pretrained LLMs can be potentially leveraged as foundation models for versatile network optimization. By eliminating the dependency on prior knowledge, LLMs can be seamlessly applied for various network management tasks. The viability of this approach is demonstrated for resource management problems using GPT-3.5-Turbo. Numerical results validate that knowledge-free LLM optimizers are able to achieve comparable performance to existing knowledge-based optimization algorithms.

Large language models (LLMs) have achieved significant performance gains using advanced prompting techniques over various tasks. However, the increasing length of prompts leads to high computational costs and often obscures crucial information. Prompt compression has been proposed to alleviate these issues, but it faces challenges in (i) capturing the global context and (ii) training the compressor effectively. To tackle these challenges, we introduce a novel prompt compression method, namely Reading To Compressing (R2C), utilizing the Fusion-in-Decoder (FiD) architecture to identify the important information in the prompt. Specifically, the cross-attention scores of the FiD are used to discern essential chunks and sentences from the prompt. R2C effectively captures the global context without compromising semantic consistency while detouring the necessity of pseudo-labels for training the compressor. Empirical results show that R2C retains key contexts, enhancing the LLM performance by 6% in out-of-domain evaluations while reducing the prompt length by 80%., Comment: Findings of the Association for Computational Linguistics: EMNLP 2024; 21 pages; 10 figures and 7 tables

Hydrogen, while a promising sustainable energy carrier, presents challenges such as the embrittlement of materials due to its ability to penetrate and weaken their crystal structures. Here we investigate Fe4N nitride layers, formed on iron through a cost-effective gas nitriding process, as an effective hydrogen permeation barrier. A combination of screening using advanced characterization, density functional theory calculations, and hydrogen permeation analysis reveals that a nitride layer reduces hydrogen diffusion by a factor of 20 at room temperature. This reduction is achieved by creating energetically unfavorable states due to stronger H-binding at the surface and high energy barriers for diffusion. The findings demonstrate the potential of Fe4N as a cost-efficient and easy-to-process solution to protecting metallic materials exposed to hydrogen, with great advantages for large-scale applications.

This study is the first to explore whether multi-modal large language models (LLMs) can align their behaviors with visual personas, addressing a significant gap in the literature that predominantly focuses on text-based personas. We developed a novel dataset of 5K fictional avatar images for assignment as visual personas to LLMs, and analyzed their negotiation behaviors based on the visual traits depicted in these images, with a particular focus on aggressiveness. The results indicate that LLMs assess the aggressiveness of images in a manner similar to humans and output more aggressive negotiation behaviors when prompted with an aggressive visual persona. Interestingly, the LLM exhibited more aggressive negotiation behaviors when the opponent's image appeared less aggressive than their own, and less aggressive behaviors when the opponents image appeared more aggressive., Comment: EMNLP 2024

Safety guard models that detect malicious queries aimed at large language models (LLMs) are essential for ensuring the secure and responsible deployment of LLMs in real-world applications. However, deploying existing safety guard models with billions of parameters alongside LLMs on mobile devices is impractical due to substantial memory requirements and latency. To reduce this cost, we distill a large teacher safety guard model into a smaller one using a labeled dataset of instruction-response pairs with binary harmfulness labels. Due to the limited diversity of harmful instructions in the existing labeled dataset, naively distilled models tend to underperform compared to larger models. To bridge the gap between small and large models, we propose HarmAug, a simple yet effective data augmentation method that involves jailbreaking an LLM and prompting it to generate harmful instructions. Given a prompt such as, "Make a single harmful instruction prompt that would elicit offensive content", we add an affirmative prefix (e.g., "I have an idea for a prompt:") to the LLM's response. This encourages the LLM to continue generating the rest of the response, leading to sampling harmful instructions. Another LLM generates a response to the harmful instruction, and the teacher model labels the instruction-response pair. We empirically show that our HarmAug outperforms other relevant baselines. Moreover, a 435-million-parameter safety guard model trained with HarmAug achieves an F1 score comparable to larger models with over 7 billion parameters, and even outperforms them in AUPRC, while operating at less than 25% of their computational cost.

In this work, we investigate how a model's tendency to broadly integrate its parametric knowledge evolves throughout pretraining, and how this behavior affects overall performance, particularly in terms of knowledge acquisition and forgetting. We introduce the concept of knowledge entropy, which quantifies the range of memory sources the model engages with; high knowledge entropy indicates that the model utilizes a wide range of memory sources, while low knowledge entropy suggests reliance on specific sources with greater certainty. Our analysis reveals a consistent decline in knowledge entropy as pretraining advances. We also find that the decline is closely associated with a reduction in the model's ability to acquire and retain knowledge, leading us to conclude that diminishing knowledge entropy (smaller number of active memory sources) impairs the model's knowledge acquisition and retention capabilities. We find further support for this by demonstrating that increasing the activity of inactive memory sources enhances the model's capacity for knowledge acquisition and retention.

Molecules have a number of distinct properties whose importance and application vary. Often, in reality, labels for some properties are hard to achieve despite their practical importance. A common solution to such data scarcity is to use models of good generalization with transfer learning. This involves domain experts for designing source and target tasks whose features are shared. However, this approach has limitations: i). Difficulty in accurate design of source-target task pairs due to the large number of tasks, and ii). corresponding computational burden verifying many trials and errors of transfer learning design, thereby iii). constraining the potential of foundation modeling of multi-task molecular property prediction. We address the limitations of the manual design of transfer learning via data-driven bi-level optimization. The proposed method enables scalable multi-task transfer learning for molecular property prediction by automatically obtaining the optimal transfer ratios. Empirically, the proposed method improved the prediction performance of 40 molecular properties and accelerated training convergence.

Deep neural network architectures often consist of repetitive structural elements. We introduce a new approach that reveals these patterns and can be broadly applied to the study of deep learning. Similar to how a power strip helps untangle and organize complex cable connections, this approach treats neurons as additional degrees of freedom in interactions, simplifying the structure and enhancing the intuitive understanding of interactions within deep neural networks. Furthermore, it reveals the translational symmetry of deep neural networks, which simplifies the application of the renormalization group transformation - a method that effectively analyzes the scaling behavior of the system. By utilizing translational symmetry and renormalization group transformations, we can analyze critical phenomena. This approach may open new avenues for studying deep neural networks using statistical physics., Comment: 11 pages, 6 figures

Recent advances in deep learning-based image reconstruction techniques have led to significant progress in phase retrieval using digital in-line holographic microscopy (DIHM). However, existing deep learning-based phase retrieval methods have technical limitations in generalization performance and three-dimensional (3D) morphology reconstruction from a single-shot hologram of biological cells. In this study, we propose a novel deep learning model, named MorpHoloNet, for single-shot reconstruction of 3D morphology by integrating physics-driven and coordinate-based neural networks. By simulating the optical diffraction of coherent light through a 3D phase shift distribution, the proposed MorpHoloNet is optimized by minimizing the loss between the simulated and input holograms on the sensor plane. Compared to existing DIHM methods that face challenges with twin image and phase retrieval problems, MorpHoloNet enables direct reconstruction of 3D complex light field and 3D morphology of a test sample from its single-shot hologram without requiring multiple phase-shifted holograms or angle scanning. The performance of the proposed MorpHoloNet is validated by reconstructing 3D morphologies and refractive index distributions from synthetic holograms of ellipsoids and experimental holograms of biological cells. The proposed deep learning model is utilized to reconstruct spatiotemporal variations in 3D translational and rotational behaviors and morphological deformations of biological cells from consecutive single-shot holograms captured using DIHM. MorpHoloNet would pave the way for advancing label-free, real-time 3D imaging and dynamic analysis of biological cells under various cellular microenvironments in biomedical and engineering fields., Comment: 35 pages, 7 figures, 1 table

In this work, we share the insights for achieving state-of-the-art quality in our text-to-image anime image generative model, called Illustrious. To achieve high resolution, dynamic color range images, and high restoration ability, we focus on three critical approaches for model improvement. First, we delve into the significance of the batch size and dropout control, which enables faster learning of controllable token based concept activations. Second, we increase the training resolution of images, affecting the accurate depiction of character anatomy in much higher resolution, extending its generation capability over 20MP with proper methods. Finally, we propose the refined multi-level captions, covering all tags and various natural language captions as a critical factor for model development. Through extensive analysis and experiments, Illustrious demonstrates state-of-the-art performance in terms of animation style, outperforming widely-used models in illustration domains, propelling easier customization and personalization with nature of open source. We plan to publicly release updated Illustrious model series sequentially as well as sustainable plans for improvements.

Quadrupedal robots hold promising potential for applications in navigating cluttered environments with resilience akin to their animal counterparts. However, their floating base configuration makes them vulnerable to real-world uncertainties, yielding substantial challenges in their locomotion control. Deep reinforcement learning has become one of the plausible alternatives for realizing a robust locomotion controller. However, the approaches that rely solely on proprioception sacrifice collision-free locomotion because they require front-feet contact to detect the presence of stairs to adapt the locomotion gait. Meanwhile, incorporating exteroception necessitates a precisely modeled map observed by exteroceptive sensors over a period of time. Therefore, this work proposes a novel method to fuse proprioception and exteroception featuring a resilient multi-modal reinforcement learning. The proposed method yields a controller that showcases agile locomotion performance on a quadrupedal robot over a myriad of real-world courses, including rough terrains, steep slopes, and high-rise stairs, while retaining its robustness against out-of-distribution situations., Comment: Under review. Project site is available at https://dreamwaqpp.github.io

A search for proton decay into $e^+/\mu^+$ and a $\eta$ meson has been performed using data from a 0.373 Mton$\cdot$year exposure (6050.3 live days) of Super-Kamiokande. Compared to previous searches this work introduces an improved model of the intranuclear $\eta$ interaction cross section, resulting in a factor of two reduction in uncertainties from this source and $\sim$10\% increase in signal efficiency. No significant data excess was found above the expected number of atmospheric neutrino background events resulting in no indication of proton decay into either mode. Lower limits on the proton partial lifetime of $1.4\times\mathrm{10^{34}~years}$ for $p\rightarrow e^+\eta$ and $7.3\times\mathrm{10^{33}~years}$ for $p\rightarrow \mu^+\eta$ at the 90$\%$ C.L. were set. These limits are around 1.5 times longer than our previous study and are the most stringent to date.

The notion of structural heterogeneity is pervasive in real networks, and their community organization is no exception. Still, a vast majority of community detection methods assume neatly hierarchically organized communities of a characteristic scale for a given hierarchical level. In this work, we demonstrate that the reality of scale-dependent community reorganization is convoluted with simultaneous processes of community splitting and merging, challenging the conventional understanding of community-scale adjustment. We provide the mathematical argument on the modularity function, the results from the real-network analysis, and a simple network model for a comprehensive understanding of the nontrivial community reorganization process characterized by a local dip in the number of communities as the resolution parameter varies. This study suggests a need for a paradigm shift in the study of network communities, which emphasizes the importance of considering scale-dependent reorganization to better understand the genuine structural organization of networks., Comment: 6 pages, 5 figures

Recently, computer-aided design models and electromagnetic simulations have been used to augment synthetic aperture radar (SAR) data for deep learning. However, an automatic target recognition (ATR) model struggles with domain shift when using synthetic data because the model learns specific clutter patterns present in such data, which disturbs performance when applied to measured data with different clutter distributions. This study proposes a framework particularly designed for domain-generalized SAR-ATR called IRASNet, enabling effective feature-level clutter reduction and domain-invariant feature learning. First, we propose a clutter reduction module (CRM) that maximizes the signal-to-clutter ratio on feature maps. The module reduces the impact of clutter at the feature level while preserving target and shadow information, thereby improving ATR performance. Second, we integrate adversarial learning with CRM to extract clutter-reduced domain-invariant features. The integration bridges the gap between synthetic and measured datasets without requiring measured data during training. Third, we improve feature extraction from target and shadow regions by implementing a positional supervision task using mask ground truth encoding. The improvement enhances the ability of the model to discriminate between classes. Our proposed IRASNet presents new state-of-the-art public SAR datasets utilizing target and shadow information to achieve superior performance across various test conditions. IRASNet not only enhances generalization performance but also significantly improves feature-level clutter reduction, making it a valuable advancement in the field of radar image pattern recognition., Comment: 16 pages, 11 figures

Ultrasound curve angle (UCA) measurement provides a radiation-free and reliable evaluation for scoliosis based on ultrasound imaging. However, degraded image quality, especially in difficult-to-image patients, can prevent clinical experts from making confident measurements, even leading to misdiagnosis. In this paper, we propose a multi-stage image enhancement framework that models high-quality image distribution via a diffusion-based model. Specifically, we integrate the underlying morphological information from images taken at different depths of the 3D volume to calibrate the reverse process toward high-quality and high-fidelity image generation. This is achieved through a fusion operation with a learnable tuner module that learns the multi-to-one mapping from multi-depth to high-quality images. Moreover, the separate learning of the high-quality image distribution and the spinal features guarantees the preservation of consistent spinal pose descriptions in the generated images, which is crucial in evaluating spinal deformities. Remarkably, our proposed enhancement algorithm significantly outperforms other enhancement-based methods on ultrasound images in terms of image quality. Ultimately, we conduct the intra-rater and inter-rater measurements of UCA and higher ICC (0.91 and 0.89 for thoracic and lumbar angles) on enhanced images, indicating our method facilitates the measurement of ultrasound curve angles and offers promising prospects for automated scoliosis diagnosis.

Training deep learning models on limited data while maintaining generalization is one of the fundamental challenges in molecular property prediction. One effective solution is transferring knowledge extracted from abundant datasets to those with scarce data. Recently, a novel algorithm called Geometrically Aligned Transfer Encoder (GATE) has been introduced, which uses soft parameter sharing by aligning the geometrical shapes of task-specific latent spaces. However, GATE faces limitations in scaling to multiple tasks due to computational costs. In this study, we propose a task addition approach for GATE to improve performance on target tasks with limited data while minimizing computational complexity. It is achieved through supervised multi-task pre-training on a large dataset, followed by the addition and training of task-specific modules for each target task. Our experiments demonstrate the superior performance of the task addition strategy for GATE over conventional multi-task methods, with comparable computational costs., Comment: 11 pages, 5 figures, Accepted at AI for Science Workshop at 41st International Conference on Machine Learning

Photoinduced ultrafast phenomena in materials exhibiting nonequilibrium behavior can lead to the emergence of exotic phases beyond the limits of thermodynamics, presenting opportunities for femtosecond photoexcitation. Despite extensive research, the ability to actively control quantum materials remains elusive owing to the lack of clear evidence demonstrating the explicit control of phase-changing kinetics through light-matter interactions. To address this drawback, we leveraged single-pulse time-resolved X-ray imaging of Au nanorods undergoing photoinduced melting to showcase control over the solid-to-liquid transition process through the use of localized surface plasmons. Our study uncovers transverse or longitudinal melting processes accompanied by characteristic oscillatory distortions at different laser intensities. Numerical simulations confirm that the localized surface plasmons, excited by polarized laser fields, dictate the melting modes through anharmonic lattice deformations. These results provide direct evidence of photoinduced surface plasmon-mediated ultrafast control of matter, establishing a foundation for the customization of material kinetics using femtosecond laser fields., Comment: 17 pages, 3 figures

An upgrade of the COSINE-100 experiment, COSINE-100U, has been prepared for installation at Yemilab, a new underground laboratory in Korea, following 6.4 years of operation at the Yangyang Underground Laboratory. The COSINE-100 experiment aimed to investigate the annual modulation signals reported by the DAMA/LIBRA but observed a null result, revealing a more than 3$\sigma$ discrepancy. COSINE-100U seeks to explore new parameter spaces for dark matter detection using NaI(Tl) detectors. All eight NaI(Tl) crystals, with a total mass of 99.1 kg, have been upgraded to improve light collection efficiency, significantly enhancing dark matter detection sensitivity. This paper describes the detector upgrades, performance improvements, and the enhanced sensitivity to low-mass dark matter detection in the COSINE-100U experiment., Comment: 14 pages, 17 figures

When developing Computer Aided Detection (CAD) systems for Digital Breast Tomosynthesis (DBT), the complexity arising from the volumetric nature of the modality poses significant technical challenges for obtaining large-scale accurate annotations. Without access to large-scale annotations, the resulting model may not generalize to different domains. Given the costly nature of obtaining DBT annotations, how to effectively increase the amount of data used for training DBT CAD systems remains an open challenge. In this paper, we present SelectiveKD, a semi-supervised learning framework for building cancer detection models for DBT, which only requires a limited number of annotated slices to reach high performance. We achieve this by utilizing unlabeled slices available in a DBT stack through a knowledge distillation framework in which the teacher model provides a supervisory signal to the student model for all slices in the DBT volume. Our framework mitigates the potential noise in the supervisory signal from a sub-optimal teacher by implementing a selective dataset expansion strategy using pseudo labels. We evaluate our approach with a large-scale real-world dataset of over 10,000 DBT exams collected from multiple device manufacturers and locations. The resulting SelectiveKD process effectively utilizes unannotated slices from a DBT stack, leading to significantly improved cancer classification performance (AUC) and generalization performance., Comment: 10 pages, 2 figures, 1 table

Accurately detecting objects at long distances remains a critical challenge in 3D object detection when relying solely on LiDAR sensors due to the inherent limitations of data sparsity. To address this issue, we propose the LiDAR-Camera Augmentation Network (LCANet), a novel framework that reconstructs LiDAR point cloud data by fusing 2D image features, which contain rich semantic information, generating additional points to improve detection accuracy. LCANet fuses data from LiDAR sensors and cameras by projecting image features into the 3D space, integrating semantic information into the point cloud data. This fused data is then encoded to produce 3D features that contain both semantic and spatial information, which are further refined to reconstruct final points before bounding box prediction. This fusion effectively compensates for LiDAR's weakness in detecting objects at long distances, which are often represented by sparse points. Additionally, due to the sparsity of many objects in the original dataset, which makes effective supervision for point generation challenging, we employ a point cloud completion network to create a complete point cloud dataset that supervises the generation of dense point clouds in our network. Extensive experiments on the KITTI and Waymo datasets demonstrate that LCANet significantly outperforms existing models, particularly in detecting sparse and distant objects., Comment: 7 pages

The use of pre-trained language models fine-tuned to address specific downstream tasks is a common approach in natural language processing (NLP). However, acquiring domain-specific knowledge via fine-tuning is challenging. Traditional methods involve pretraining language models using vast amounts of domain-specific data before fine-tuning for particular tasks. This study investigates emergency/non-emergency classification tasks based on electronic medical record (EMR) data obtained from pediatric emergency departments (PEDs) in Korea. Our findings reveal that existing domain-specific pre-trained language models underperform compared to general language models in handling N-lingual free-text data characteristics of non-English-speaking regions. To address these limitations, we propose a domain knowledge transfer methodology that leverages knowledge distillation to infuse general language models with domain-specific knowledge via fine-tuning. This study demonstrates the effective transfer of specialized knowledge between models by defining a general language model as the student model and a domain-specific pre-trained model as the teacher model. In particular, we address the complexities of EMR data obtained from PEDs in non-English-speaking regions, such as Korea, and demonstrate that the proposed method enhances classification performance in such contexts. The proposed methodology not only outperforms baseline models on Korean PED EMR data, but also promises broader applicability in various professional and technical domains. In future works, we intend to extend this methodology to include diverse non-English-speaking regions and address additional downstream tasks, with the aim of developing advanced model architectures using state-of-the-art KD techniques. The code is available in https://github.com/JoSangYeon/DSG-KD., Comment: IEEE ACCESS 2024

In cloud environments, GPU-based deep neural network (DNN) inference servers are required to meet the Service Level Objective (SLO) latency for each workload under a specified request rate, while also minimizing GPU resource consumption. However, previous studies have not fully achieved this objective. In this paper, we propose ParvaGPU, a technology that facilitates spatial GPU sharing for large-scale DNN inference in cloud computing. ParvaGPU integrates NVIDIA's Multi-Instance GPU (MIG) and Multi-Process Service (MPS) technologies to enhance GPU utilization, with the goal of meeting the diverse SLOs of each workload and reducing overall GPU usage. Specifically, ParvaGPU addresses the challenges of minimizing underutilization within allocated GPU space partitions and external fragmentation in combined MIG and MPS environments. We conducted our assessment on multiple A100 GPUs, evaluating 11 diverse DNN workloads with varying SLOs. Our evaluation revealed no SLO violations and a significant reduction in GPU usage compared to state-of-the-art frameworks., Comment: To appear at the International Conference for High Performance Computing, Networking, Storage, and Analysis (SC24)

HOPS 87 is a Class 0 protostellar core known to harbor an extremely young bipolar outflow and a hot corino. We report the discovery of localized, chemically rich regions near the bases of the two-lobe bipolar molecular outflow in HOPS 87 containing molecules such as H$_2$CO, $^{13}$CS, H$_2$S, OCS, and CH$_3$OH, the simplest complex organic molecule (COM). The locations and kinematics suggest that these localized features are due to jet-driven shocks rather than being part of the hot corino region encasing the protostar. The COM compositions of the molecular gas in these jet-localized regions are relatively simpler than those in the hot corino zone. We speculate that this simplicity is due to either the liberation of ice with a less complex chemical history or the effects of shock chemistry. Our study highlights the dynamic interplay between the protostellar bipolar outflow, disk, inner core environment, and the surrounding medium, contributing to our understanding of molecular complexity in solar-like young stellar objects., Comment: 16 pages, 6+2 figures, accepted by ApJ

We study the code generation behavior of instruction-tuned models built on top of code pre-trained language models when they could access an auxiliary function to implement a function. We design several ways to provide auxiliary functions to the models by adding them to the query or providing a response prefix to incorporate the ability to utilize auxiliary functions with the instruction-following capability. Our experimental results show the effectiveness of combining the base models' auxiliary function utilization ability with the instruction following ability. In particular, the performance of adopting our approaches with the open-sourced language models surpasses that of the recent powerful proprietary language models, i.e., gpt-4o., Comment: EMNLP 2024 Findings Short

For over 25 years, the DAMA/LIBRA collaboration has claimed to observe an annual modulation signal, suggesting the existence of dark matter interactions. However, no other experiments have replicated their result using different detector materials. To address this puzzle, the COSINE-100 collaboration conducted a model-independent test using 106 kg of sodium iodide as detectors, the same target material as DAMA/LIBRA. Analyzing data collected over 6.4 years, with improved energy calibration and time-dependent background description, we found no evidence of an annual modulation signal, challenging the DAMA/LIBRA result with a confidence level greater than 3$\sigma$. This finding represents a significant step toward resolving the long-standing debate surrounding DAMA/LIBRA's dark matter claim, indicating that the observed modulation is unlikely to be caused by dark matter interactions.

In order to solve problems of practical importance, quantum computers will likely need to incorporate quantum error correction, where a logical qubit is redundantly encoded in many noisy physical qubits. The large physical-qubit overhead typically associated with error correction motivates the search for more hardware-efficient approaches. Here, using a microfabricated superconducting quantum circuit, we realize a logical qubit memory formed from the concatenation of encoded bosonic cat qubits with an outer repetition code of distance $d=5$. The bosonic cat qubits are passively protected against bit flips using a stabilizing circuit. Cat-qubit phase-flip errors are corrected by the repetition code which uses ancilla transmons for syndrome measurement. We realize a noise-biased CX gate which ensures bit-flip error suppression is maintained during error correction. We study the performance and scaling of the logical qubit memory, finding that the phase-flip correcting repetition code operates below threshold, with logical phase-flip error decreasing with code distance from $d=3$ to $d=5$. Concurrently, the logical bit-flip error is suppressed with increasing cat-qubit mean photon number. The minimum measured logical error per cycle is on average $1.75(2)\%$ for the distance-3 code sections, and $1.65(3)\%$ for the longer distance-5 code, demonstrating the effectiveness of bit-flip error suppression throughout the error correction cycle. These results, where the intrinsic error suppression of the bosonic encodings allows us to use a hardware-efficient outer error correcting code, indicate that concatenated bosonic codes are a compelling paradigm for reaching fault-tolerant quantum computation., Comment: Comments on the manuscript welcome!

We report the first measurement of the azimuthal anisotropy of J$/\psi$ at forward rapidity ($1.2<|\eta|<2.2$) in Au$+$Au collisions at $\sqrt{s_{_{NN}}}=200$ GeV at the Relativistic Heavy Ion Collider. The data were collected by the PHENIX experiment in 2014 and 2016 with integrated luminosity of 14.5~nb$^{-1}$. The second Fourier coefficient ($v_2$) of the azimuthal distribution of $J/\psi$ is determined as a function of the transverse momentum ($p_T$) using the event-plane method. The measurements were performed for several selections of collision centrality: 0\%--50\%, 10\%--60\%, and 10\%-40\%. We find that in all cases the values of $v_2(p_T)$, which quantify the elliptic flow of J$/\psi$, are consistent with zero. The results are consistent with measurements at midrapidity, indicating no significant elliptic flow of the J$/\psi$ within the quark-gluon-plasma medium at collision energies of $\sqrt{s_{_{NN}}}=200$ GeV., Comment: 369 authors from 72 institutions, 12 pages, 7 figures, 5 tables. v1 is version submitted to Physical Review C. HEPdata tables for the points plotted in figures for this and previous PHENIX publications are (or will be) publicly available at http://www.phenix.bnl.gov/papers.html

We present the first forward-rapidity measurements of elliptic anisotropy of open-heavy-flavor muons at the BNL Relativistic Heavy Ion Collider. The measurements are based on data samples of Au$+$Au collisions at $\sqrt{s_{_{NN}}}=200$ GeV collected by the PHENIX experiment in 2014 and 2016 with integrated luminosity of 14.5~nb$^{-1}$. The measurements are performed in the pseudorapidity range $1.2<|\eta|<2$ and cover transverse momenta $1

Recently, significant improvements in rate-distortion performance of image compression have been achieved with deep-learning techniques. A key factor in this success is the use of additional bits to predict an approximation of the latent vector, which is the output of the encoder, through another neural network. Then, only the difference between the prediction and the latent vector is coded into the bitstream, along with its estimated probability distribution. We introduce a new predictive structure consisting of the auxiliary coarse network and the main network, inspired by neural video compression. The auxiliary coarse network encodes the auxiliary information and predicts the approximation of the original image as multi-scale features. The main network encodes the residual between the predicted feature from the auxiliary coarse network and the feature of the original image. To further leverage our new structure, we propose Auxiliary info-guided Feature Prediction (AFP) module that uses global correlation to predict more accurate predicted features. Moreover, we present Context Junction module that refines the auxiliary feature from AFP module and produces the residuals between the refined features and the original image features. Finally, we introduce Auxiliary info-guided Parameter Estimation (APE) module, which predicts the approximation of the latent vector and estimates the probability distribution of these residuals. We demonstrate the effectiveness of the proposed modules by various ablation studies. Under extensive experiments, our model outperforms other neural image compression models and achieves a 19.49\% higher rate-distortion performance than VVC on Tecnick dataset.

We reconsider studies of Toeplitz operators on function spaces (the weighted Bergman space, the generalized derivative Hardy space) and the H-Toeplitz operators on the Bergman space. Past studies have considered the presence or absence of hyponormality or questions of contractivity or expansivity; we provide structure theorems for these operators that allow us to recapture, and often considerably improve, these results. In some cases these operators or their adjoints are actually in more restrictive classes, such as subnormal or moment infinitely divisible ($\mathcal{MID}$).

Chain-of-Thought (CoT) reasoning has enabled Large Language Model (LLM) to achieve remarkable performance in various NLP tasks, including arithmetic problem-solving. However, this success does not generalize to small language model (sLM) like T5, due to their limited capacity and absence of emergent abilities associated with larger models. Recent works to enhance sLM through knowledge distillation have yielded some improvements but still face significant limitations, particularly high ambiguity from the variability in natural language expressions and substantial computational costs. In this paper, we investigate why sLM perform poorly on arithmetic reasoning tasks and hypothesize that natural language format variability introduces high ambiguity for these smaller models. Based on this hypothesis, we conduct experiments with equation-only format, which is a reasoning format that unifies arithmetic reasoning previously expressed in natural language formats into mathematical equations. Experiment results demonstrate that equation-only format effectively boosts the arithmetic reasoning abilities of sLM, especially in very small models like T5-Tiny., Comment: 6 pages, 2 figures

Interferometric observations of gravitational microlensing events offer an opportunity for precise, efficient, and direct mass and distance measurements of lensing objects, especially those of isolated neutron stars and black holes. However, such observations were previously possible for only a handful of extremely bright events. The recent development of a dual-field interferometer, GRAVITY Wide, has made it possible to reach out to significantly fainter objects, and increase the pool of microlensing events amenable to interferometric observations by two orders of magnitude. Here, we present the first successful observation of a microlensing event with GRAVITY Wide and the resolution of microlensed images in the event OGLE-2023-BLG-0061/KMT-2023-BLG-0496. We measure the angular Einstein radius of the lens with a sub-percent precision, $\theta_{\rm E} = 1.280 \pm 0.009$ mas. Combined with the microlensing parallax detected from the event light curve, the mass and distance to the lens are found to be $0.472 \pm 0.012 M_{\odot}$ and $1.81 \pm 0.05$ kpc, respectively. We present the procedure for the selection of targets for interferometric observations, and discuss possible systematic effects affecting GRAVITY Wide data. This detection demonstrates the capabilities of the new instrument and it opens up completely new possibilities for the follow-up of microlensing events, and future routine discoveries of isolated neutron stars and black holes., Comment: submitted to AAS Journals

In this study, we present a novel method for enhancing the computational efficiency of whole-body control for humanoid robots, a challenge accentuated by their high degrees of freedom. The reduced-dimension rigid body dynamics of a floating base robot is constructed by segmenting its kinematic chain into constrained and unconstrained chains, simplifying the dynamics of the unconstrained chain through the centroidal dynamics. The proposed dynamics model is possible to be applied to whole-body control methods, allowing the problem to be divided into two parts for more efficient computation. The efficiency of the framework is demonstrated by comparative experiments in simulations. The calculation results demonstrate a significant reduction in processing time, highlighting an improvement over the times reported in current methodologies. Additionally, the results also shows the computational efficiency increases as the degrees of freedom of robot model increases., Comment: submitted to RA-L, under review

The SoccerNet 2024 challenges represent the fourth annual video understanding challenges organized by the SoccerNet team. These challenges aim to advance research across multiple themes in football, including broadcast video understanding, field understanding, and player understanding. This year, the challenges encompass four vision-based tasks. (1) Ball Action Spotting, focusing on precisely localizing when and which soccer actions related to the ball occur, (2) Dense Video Captioning, focusing on describing the broadcast with natural language and anchored timestamps, (3) Multi-View Foul Recognition, a novel task focusing on analyzing multiple viewpoints of a potential foul incident to classify whether a foul occurred and assess its severity, (4) Game State Reconstruction, another novel task focusing on reconstructing the game state from broadcast videos onto a 2D top-view map of the field. Detailed information about the tasks, challenges, and leaderboards can be found at https://www.soccer-net.org, with baselines and development kits available at https://github.com/SoccerNet., Comment: 7 pages, 1 figure

This paper introduces ES-KT-24, a novel multimodal Knowledge Tracing (KT) dataset for intelligent tutoring systems in educational game contexts. Although KT is crucial in adaptive learning, existing datasets often lack game-based and multimodal elements. ES-KT-24 addresses these limitations by incorporating educational game-playing videos, synthetically generated question text, and detailed game logs. The dataset covers Mathematics, English, Indonesian, and Malaysian subjects, emphasizing diversity and including non-English content. The synthetic text component, generated using a large language model, encompasses 28 distinct knowledge concepts and 182 questions, featuring 15,032 users and 7,782,928 interactions. Our benchmark experiments demonstrate the dataset's utility for KT research by comparing Deep learning-based KT models with Language Model-based Knowledge Tracing (LKT) approaches. Notably, LKT models showed slightly higher performance than traditional DKT models, highlighting the potential of language model-based approaches in this field. Furthermore, ES-KT-24 has the potential to significantly advance research in multimodal KT models and learning analytics. By integrating game-playing videos and detailed game logs, this dataset offers a unique approach to dissecting student learning patterns through advanced data analysis and machine-learning techniques. It has the potential to unearth new insights into the learning process and inspire further exploration in the field., Comment: 11 pages, 5 figures

Wireless-powered communications (WPCs) are increasingly crucial for extending the lifespan of low-power Internet of Things (IoT) devices. Furthermore, reconfigurable intelligent surfaces (RISs) can create favorable electromagnetic environments by providing alternative signal paths to counteract blockages. The strategic integration of WPC and RIS technologies can significantly enhance energy transfer and data transmission efficiency. However, passive RISs suffer from double-fading attenuation over RIS-aided cascaded links. In this article, we propose the application of an active RIS within WPC-enabled IoT networks. The enhanced flexibility of the active RIS in terms of energy transfer and information transmission is investigated using adjustable parameters. We derive novel closed-form expressions for the ergodic rate and outage probability by incorporating key parameters, including signal amplification, active noise, power consumption, and phase quantization errors. Additionally, we explore the optimization of WPC scenarios, focusing on the time-switching factor and power consumption of the active RIS. The results validate our analysis, demonstrating that an active RIS significantly enhances WPC performance compared to a passive RIS., Comment: Accepted for IEEE Internet of Things Journal

Markowitz laid the foundation of portfolio theory through the mean-variance optimization (MVO) framework. However, the effectiveness of MVO is contingent on the precise estimation of expected returns, variances, and covariances of asset returns, which are typically uncertain. Machine learning models are becoming useful in estimating uncertain parameters, and such models are trained to minimize prediction errors, such as mean squared errors (MSE), which treat prediction errors uniformly across assets. Recent studies have pointed out that this approach would lead to suboptimal decisions and proposed Decision-Focused Learning (DFL) as a solution, integrating prediction and optimization to improve decision-making outcomes. While studies have shown DFL's potential to enhance portfolio performance, the detailed mechanisms of how DFL modifies prediction models for MVO remain unexplored. This study aims to investigate how DFL adjusts stock return prediction models to optimize decisions in MVO, addressing the question: "MSE treats the errors of all assets equally, but how does DFL reduce errors of different assets differently?" Answering this will provide crucial insights into optimal stock return prediction for constructing efficient portfolios., Comment: 7 pages, 3 figures, 3 tables

LaTeX is suitable for creating specially formatted documents in science, technology, mathematics, and computer science. Although the use of mathematical expressions in LaTeX format along with language models is increasing, there are no proper evaluation matrices to evaluate them. In this study, we propose TeXBLEU, a metric for evaluating mathematical expressions in the LaTeX format built on the n-gram-based BLEU metric widely used in translation tasks. The proposed TeXBLEU consists of a predefined tokenizer trained on the arXiv paper dataset and a fine-tuned embedding model with positional encoding. The TeXBLEU score was calculated by replacing BLUE's modified precision score with the similarity of n-gram-based tokens. TeXBLEU showed improvements of 86\%, 121\%, and 610\% over traditional evaluation metrics, such as BLEU, sacreBLEU, and Rouge, respectively, on the MathBridge dataset with 1,000 data points. The code is available at https://github.com/KyuDan1/TeXBLEU., Comment: 5 pages, 4 figures

Dialogue State Tracking (DST) is a key part of task-oriented dialogue systems, identifying important information in conversations. However, its accuracy drops significantly in spoken dialogue environments due to named entity errors from Automatic Speech Recognition (ASR) systems. We introduce a simple yet effective data augmentation method that targets those entities to improve the robustness of DST model. Our novel method can control the placement of errors using keyword-highlighted prompts while introducing phonetically similar errors. As a result, our method generated sufficient error patterns on keywords, leading to improved accuracy in noised and low-accuracy ASR environments.

Traditional dialogue state tracking approaches heavily rely on extensive training data and handcrafted features, limiting their scalability and adaptability to new domains. In this paper, we propose a novel method that leverages inference and in-context learning with ChatGPT for domain transfer in dialogue state tracking, without any parameter updates. By guiding ChatGPT's chain of thought, we enable it to retrieve relevant examples and generalize knowledge to accurately infer dialogue states, solely through inference. Experimental results on the MultiWOZ dataset demonstrate competitive performance and promising generalization across domains. Our parameter-free approach offers a scalable and adaptable solution, opening new research directions in domain transfer learning.

In this paper, we introduce and study the Dirichlet series enumerating (proper) equivalence classes of full rank subforms/sublattices of a given quadratic form/lattice, focusing on the positive definite binary case. We obtain formulas linking this Dirichlet series with Dirichlet series counting ideal classes of the imaginary quadratic field associated with the quadratic form. Utilizing the result, we provide explicit formulas of the Dirichlet series for several lattices, including square lattice and hexagonal lattice. Moreover, we investigate some analytic properties of this Dirichlet series., Comment: 37 pages

We address the problem of person re-identification (reID), that is, retrieving person images from a large dataset, given a query image of the person of interest. A key challenge is to learn person representations robust to intra-class variations, as different persons could have the same attribute, and persons' appearances look different, e.g., with viewpoint changes. Recent reID methods focus on learning person features discriminative only for a particular factor of variations (e.g., human pose), which also requires corresponding supervisory signals (e.g., pose annotations). To tackle this problem, we propose to factorize person images into identity-related and unrelated features. Identity-related features contain information useful for specifying a particular person (e.g., clothing), while identity-unrelated ones hold other factors (e.g., human pose). To this end, we propose a new generative adversarial network, dubbed identity shuffle GAN (IS-GAN). It disentangles identity-related and unrelated features from person images through an identity-shuffling technique that exploits identification labels alone without any auxiliary supervisory signals. We restrict the distribution of identity-unrelated features or encourage the identity-related and unrelated features to be uncorrelated, facilitating the disentanglement process. Experimental results validate the effectiveness of IS-GAN, showing state-of-the-art performance on standard reID benchmarks, including Market-1501, CUHK03, and DukeMTMC-reID. We further demonstrate the advantages of disentangling person representations on a long-term reID task, setting a new state of the art on a Celeb-reID dataset., Comment: arXiv admin note: substantial text overlap with arXiv:1910.12003

Given a video with $T$ frames, frame sampling is a task to select $N \ll T$ frames, so as to maximize the performance of a fixed video classifier. Not just brute-force search, but most existing methods suffer from its vast search space of $\binom{T}{N}$, especially when $N$ gets large. To address this challenge, we introduce a novel perspective of reducing the search space from $O(T^N)$ to $O(T)$. Instead of exploring the entire $O(T^N)$ space, our proposed semi-optimal policy selects the top $N$ frames based on the independently estimated value of each frame using per-frame confidence, significantly reducing the computational complexity. We verify that our semi-optimal policy can efficiently approximate the optimal policy, particularly under practical settings. Additionally, through extensive experiments on various datasets and model architectures, we demonstrate that learning our semi-optimal policy ensures stable and high performance regardless of the size of $N$ and $T$.

This study investigates the design, development, and evaluation of a Large Language Model (LLM)-based chatbot for teaching English conversations in an English as a Foreign Language (EFL) context. Employing the Design and Development Research (DDR), we analyzed needs, established design principles, and iteratively refined a chatbot through experimenting various LLMs and alignment methods. Through both quantitative and qualitative evaluations, we identified the most effective LLM and its prompt combination to generate high-quality, contextually appropriate responses. Interviews with teachers provided insights into desirable system features, potential educational applications, and ethical considerations in the development and deployment of the chatbots. The design iterations yielded the importance of feedback mechanisms and customizable AI personas. Future research should explore adaptive feedback strategies, collaborative approaches with various stakeholders, and the integration of insights from human-computer interaction (HCI) and user experience (UX) design. This study contributes to the growing body of research on applying LLMs in language education, providing insights and recommendations for the design, development, and evaluation of LLM-based chatbots for EFL conversation practice. As the field evolves, ongoing research and collaboration among educators, AI engineers, and other stakeholders will be essential to harness the potential of these technologies to enhance language learning experiences., Comment: 56 pages