Search

Causal language modeling (CLM) serves as the foundational framework underpinning remarkable successes of recent large language models (LLMs). Despite its success, the training approach for next word prediction poses a potential risk of causing the model to overly focus on local dependencies within a sentence. While prior studies have been introduced to predict future N words simultaneously, they were primarily applied to tasks such as masked language modeling (MLM) and neural machine translation (NMT). In this study, we introduce a simple N-gram prediction framework for the CLM task. Moreover, we introduce word difference representation (WDR) as a surrogate and contextualized target representation during model training on the basis of N-gram prediction framework. To further enhance the quality of next word prediction, we propose an ensemble method that incorporates the future N words' prediction results. Empirical evaluations across multiple benchmark datasets encompassing CLM and NMT tasks demonstrate the significant advantages of our proposed methods over the conventional CLM.

Temporal Action Detection (TAD) is fundamental yet challenging for real-world video applications. Leveraging the unique benefits of transformers, various DETR-based approaches have been adopted in TAD. However, it has recently been identified that the attention collapse in self-attention causes the performance degradation of DETR for TAD. Building upon previous research, this paper newly addresses the attention collapse problem in cross-attention within DETR-based TAD methods. Moreover, our findings reveal that cross-attention exhibits patterns distinct from predictions, indicating a short-cut phenomenon. To resolve this, we propose a new framework, Prediction-Feedback DETR (Pred-DETR), which utilizes predictions to restore the collapse and align the cross- and self-attention with predictions. Specifically, we devise novel prediction-feedback objectives using guidance from the relations of the predictions. As a result, Pred-DETR significantly alleviates the collapse and achieves state-of-the-art performance among DETR-based methods on various challenging benchmarks including THUMOS14, ActivityNet-v1.3, HACS, and FineAction.

Temporal action detection (TAD) is challenging, yet fundamental for real-world video applications. Recently, DETR-based models for TAD have been prevailing thanks to their unique benefits. However, transformers demand a huge dataset, and unfortunately data scarcity in TAD causes a severe degeneration. In this paper, we identify two crucial problems from data scarcity: attention collapse and imbalanced performance. To this end, we propose a new pre-training strategy, Long-Term Pre-training (LTP), tailored for transformers. LTP has two main components: 1) class-wise synthesis, 2) long-term pretext tasks. Firstly, we synthesize long-form video features by merging video snippets of a target class and non-target classes. They are analogous to untrimmed data used in TAD, despite being created from trimmed data. In addition, we devise two types of long-term pretext tasks to learn long-term dependency. They impose long-term conditions such as finding second-to-fourth or short-duration actions. Our extensive experiments show state-of-the-art performances in DETR-based methods on ActivityNet-v1.3 and THUMOS14 by a large margin. Moreover, we demonstrate that LTP significantly relieves the data scarcity issues in TAD.

Few-shot object counting has garnered significant attention for its practicality as it aims to count target objects in a query image based on given exemplars without the need for additional training. However, there is a shortcoming in the prevailing extract-and-match approach: query and exemplar features lack interaction during feature extraction since they are extracted unaware of each other and later correlated based on similarity. This can lead to insufficient target awareness of the extracted features, resulting in target confusion in precisely identifying the actual target when multiple class objects coexist. To address this limitation, we propose a novel framework, Mutually-Aware FEAture learning(MAFEA), which encodes query and exemplar features mutually aware of each other from the outset. By encouraging interaction between query and exemplar features throughout the entire pipeline, we can obtain target-aware features that are robust to a multi-category scenario. Furthermore, we introduce a background token to effectively associate the target region of query with exemplars and decouple its background region from them. Our extensive experiments demonstrate that our model reaches a new state-of-the-art performance on the two challenging benchmarks, FSCD-LVIS and FSC-147, with a remarkably reduced degree of the target confusion problem., Comment: Submitted to Pattern Recognition

Temporal action detection (TAD) is challenging, yet fundamental for real-world video applications. Large temporal scale variation of actions is one of the most primary difficulties in TAD. Naturally, multi-scale features have potential in localizing actions of diverse lengths as widely used in object detection. Nevertheless, unlike objects in images, actions have more ambiguity in their boundaries. That is, small neighboring objects are not considered as a large one while short adjoining actions can be misunderstood as a long one. In the coarse-to-fine feature pyramid via pooling, these vague action boundaries can fade out, which we call 'vanishing boundary problem'. To this end, we propose Boundary-Recovering Network (BRN) to address the vanishing boundary problem. BRN constructs scale-time features by introducing a new axis called scale dimension by interpolating multi-scale features to the same temporal length. On top of scale-time features, scale-time blocks learn to exchange features across scale levels, which can effectively settle down the issue. Our extensive experiments demonstrate that our model outperforms the state-of-the-art on the two challenging benchmarks, ActivityNet-v1.3 and THUMOS14, with remarkably reduced degree of the vanishing boundary problem., Comment: Submitted to Pattern Recognition Journal

Multimodal Dialogue Response Generation (MDRG) is a recently proposed task where the model needs to generate responses in texts, images, or a blend of both based on the dialogue context. Due to the lack of a large-scale dataset specifically for this task and the benefits of leveraging powerful pre-trained models, previous work relies on the text modality as an intermediary step for both the image input and output of the model rather than adopting an end-to-end approach. However, this approach can overlook crucial information about the image, hindering 1) image-grounded text response and 2) consistency of objects in the image response. In this paper, we propose BI-MDRG that bridges the response generation path such that the image history information is utilized for enhanced relevance of text responses to the image content and the consistency of objects in sequential image responses. Through extensive experiments on the multimodal dialogue benchmark dataset, we show that BI-MDRG can effectively increase the quality of multimodal dialogue. Additionally, recognizing the gap in benchmark datasets for evaluating the image consistency in multimodal dialogue, we have created a curated set of 300 dialogues annotated to track object consistency across conversations., Comment: ECCV 2024

Recently, there has been an extensive research effort in building efficient large language model (LLM) inference serving systems. These efforts not only include innovations in the algorithm and software domains but also constitute developments of various hardware acceleration techniques. Nevertheless, there is a lack of simulation infrastructure capable of accurately modeling versatile hardware-software behaviors in LLM serving systems without extensively extending the simulation time. This paper aims to develop an effective simulation tool, called LLMServingSim, to support future research in LLM serving systems. In designing LLMServingSim, we focus on two limitations of existing simulators: (1) they lack consideration of the dynamic workload variations of LLM inference serving due to its autoregressive nature, and (2) they incur repetitive simulations without leveraging algorithmic redundancies in LLMs. To address these limitations, LLMServingSim simulates the LLM serving in the granularity of iterations, leveraging the computation redundancies across decoder blocks and reusing the simulation results from previous iterations. Additionally, LLMServingSim provides a flexible framework that allows users to plug in any accelerator compiler-and-simulation stacks for exploring various system designs with heterogeneous processors. Our experiments demonstrate that LLMServingSim produces simulation results closely following the performance behaviors of real GPU-based LLM serving system with less than 14.7% error rate, while offering 91.5x faster simulation speed compared to existing accelerator simulators., Comment: 15 pages, 11 figures

Active learning (AL) aims to enhance model performance by selectively collecting highly informative data, thereby minimizing annotation costs. However, in practical scenarios, unlabeled data may contain out-of-distribution (OOD) samples, leading to wasted annotation costs if data is incorrectly selected. Recent research has explored methods to apply AL to open-set data, but these methods often require or incur unavoidable cost losses to minimize them. To address these challenges, we propose a novel selection strategy, CLIPN for AL (CLIPNAL), which minimizes cost losses without requiring OOD samples. CLIPNAL sequentially evaluates the purity and informativeness of data. First, it utilizes a pre-trained vision-language model to detect and exclude OOD data by leveraging linguistic and visual information of in-distribution (ID) data without additional training. Second, it selects highly informative data from the remaining ID data, and then the selected samples are annotated by human experts. Experimental results on datasets with various open-set conditions demonstrate that CLIPNAL achieves the lowest cost loss and highest performance across all scenarios. Code is available at https://github.com/DSBA-Lab/OpenAL.

Location-based services offer immense utility, but also pose significant privacy risks. In response, we propose LocPIR, a novel framework using homomorphic encryption (HE), specifically the TFHE scheme, to preserve user location privacy when retrieving data from public clouds. Our system employs TFHE's expertise in non-polynomial evaluations, crucial for comparison operations. LocPIR showcases minimal client-server interaction, reduced memory overhead, and efficient throughput. Performance tests confirm its computational speed, making it a viable solution for practical scenarios, demonstrated via application to a COVID-19 alert model. Thus, LocPIR effectively addresses privacy concerns in location-based services, enabling secure data sharing from the public cloud., Comment: Accepted at the IEEE International Conference on Advanced Video and Signal-Based Surveillance (AVSS) 2024

We have experimentally demonstrated the effectiveness of beta-gallium oxide (beta-Ga2O3) ferroelectric fin field-effect transistors (Fe-FinFETs) for the first time. Atomic layer deposited (ALD) hafnium zirconium oxide (HZO) is used as the ferroelectric layer. The HZO/beta-Ga2O3 Fe-FinFETs have wider counterclockwise hysteresis loops in the transfer characteristics than that of conventional planar FET, achieving record-high memory window (MW) of 13.9 V in a single HZO layer. When normalized to the actual channel width, FinFETs show an improved ION/IOFF ratio of 2.3x10^7 and a subthreshold swing value of 110 mV/dec. The enhanced characteristics are attributed to the low-interface state density (Dit), showing good interface properties between the beta-Ga2O3 and HZO layer. The enhanced polarization due to larger electric fields across the entire ferroelectric layer in FinFETs is validated using Sentaurus TCAD. After 5x10^6 program/erase (PGM/ERS) cycles, the MW was maintained at 9.2 V, and the retention time was measured up to 3x10^4 s with low degradation. Therefore, the ultrawide bandgap (UWBG) Fe-FinFET was shown to be one of the promising candidates for high-density non-volatile memory devices., Comment: 14 pages, 5 figures

The labor-intensive labeling for semantic segmentation has spurred the emergence of Unsupervised Semantic Segmentation. Recent studies utilize patch-wise contrastive learning based on features from image-level self-supervised pretrained models. However, relying solely on similarity-based supervision from image-level pretrained models often leads to unreliable guidance due to insufficient patch-level semantic representations. To address this, we propose a Progressive Proxy Anchor Propagation (PPAP) strategy. This method gradually identifies more trustworthy positives for each anchor by relocating its proxy to regions densely populated with semantically similar samples. Specifically, we initially establish a tight boundary to gather a few reliable positive samples around each anchor. Then, considering the distribution of positive samples, we relocate the proxy anchor towards areas with a higher concentration of positives and adjust the positiveness boundary based on the propagation degree of the proxy anchor. Moreover, to account for ambiguous regions where positive and negative samples may coexist near the positiveness boundary, we introduce an instance-wise ambiguous zone. Samples within these zones are excluded from the negative set, further enhancing the reliability of the negative set. Our state-of-the-art performances on various datasets validate the effectiveness of the proposed method for Unsupervised Semantic Segmentation., Comment: Accepted to ECCV 2024

Class-Incremental Semantic Segmentation(CISS) aims to learn new classes without forgetting the old ones, using only the labels of the new classes. To achieve this, two popular strategies are employed: 1) pseudo-labeling and knowledge distillation to preserve prior knowledge; and 2) background weight transfer, which leverages the broad coverage of background in learning new classes by transferring background weight to the new class classifier. However, the first strategy heavily relies on the old model in detecting old classes while undetected pixels are regarded as the background, thereby leading to the background shift towards the old classes(i.e., misclassification of old class as background). Additionally, in the case of the second approach, initializing the new class classifier with background knowledge triggers a similar background shift issue, but towards the new classes. To address these issues, we propose a background-class separation framework for CISS. To begin with, selective pseudo-labeling and adaptive feature distillation are to distill only trustworthy past knowledge. On the other hand, we encourage the separation between the background and new classes with a novel orthogonal objective along with label-guided output distillation. Our state-of-the-art results validate the effectiveness of these proposed methods., Comment: Accepted to ECCV 2024. Code is available at http://github.com/RoadoneP/ECCV2024_MBS

We present an inverse image-formation module that can enhance the robustness of existing visual SLAM pipelines for casually captured scenarios. Casual video captures often suffer from motion blur and varying appearances, which degrade the final quality of coherent 3D visual representation. We propose integrating the physical imaging into the SLAM system, which employs linear HDR radiance maps to collect measurements. Specifically, individual frames aggregate images of multiple poses along the camera trajectory to explain prevalent motion blur in hand-held videos. Additionally, we accommodate per-frame appearance variation by dedicating explicit variables for image formation steps, namely white balance, exposure time, and camera response function. Through joint optimization of additional variables, the SLAM pipeline produces high-quality images with more accurate trajectories. Extensive experiments demonstrate that our approach can be incorporated into recent visual SLAM pipelines using various scene representations, such as neural radiance fields or Gaussian splatting., Comment: ECCV 2024

The flatfish is a major farmed species consumed globally in large quantities. However, due to the densely populated farming environment, flatfish are susceptible to injuries and diseases, making early disease detection crucial. Traditionally, diseases were detected through visual inspection, but observing large numbers of fish is challenging. Automated approaches based on deep learning technologies have been widely used, to address this problem, but accurate detection remains difficult due to the diversity of the fish and the lack of the fish disease dataset. In this study, augments fish disease images using generative adversarial networks and image harmonization methods. Next, disease detectors are trained separately for three body parts (head, fins, and body) to address individual diseases properly. In addition, a flatfish disease image dataset called \texttt{FlatIMG} is created and verified on the dataset using the proposed methods. A flash salmon disease dataset is also tested to validate the generalizability of the proposed methods. The results achieved 12\% higher performance than the baseline framework. This study is the first attempt to create a large-scale flatfish disease image dataset and propose an effective disease detection framework. Automatic disease monitoring could be achieved in farming environments based on the proposed methods and dataset., Comment: 16 page, 13 figures, 4 tables

With high equilibrium temperatures and tidally locked rotation, ultra-hot Jupiters (UHJs) are unique laboratories within which to probe extreme atmospheric physics and chemistry. In this paper, we present high-resolution dayside spectroscopy of the UHJ WASP-189b obtained with the new Gemini High-resolution Optical SpecTrograph (GHOST) at the Gemini South Observatory. The observations, which cover three hours of post-eclipse orbital phases, were obtained during the instrument's System Verification run. We detect the planet's atmosphere via the Doppler cross-correlation technique, and recover a detection of neutral iron in the planet's dayside atmosphere at a significance of 7.5$\sigma$ in the red-arm of the data, verifying the presence of a thermal inversion. We also investigate the presence of other species in the atmosphere and discuss the implications of model injection/recovery tests. These results represent the first atmospheric characterization of an exoplanet with GHOST's high-resolution mode, and demonstrate the potential of this new instrument in detecting and studying ultra-hot exoplanet atmospheres., Comment: 21 pages, 12 figures, 3 tables. Accepted for publication in The Astronomical Journal

Large Language Models (LLMs) have demonstrated impressive problem-solving capabilities in mathematics through step-by-step reasoning chains. However, they are susceptible to reasoning errors that impact the quality of subsequent reasoning chains and the final answer due to language models' autoregressive token-by-token generating nature. Recent works have proposed adopting external verifiers to guide the generation of reasoning paths, but existing works utilize models that have been trained with step-by-step labels to assess the correctness of token-by-token reasoning chains. Consequently, they struggle to recognize discriminative details of tokens within a reasoning path and lack the ability to evaluate whether an intermediate reasoning path is on a promising track toward the correct final answer. To amend the lack of sound and token-grained math-verification signals, we devise a novel training scheme for verifiers that apply token-level supervision with the expected cumulative reward (i.e., value). Furthermore, we propose a practical formulation of the cumulative reward by reducing it to finding the probability of future correctness of the final answer and thereby enabling the empirical estimation of the value. Experimental results on mathematical reasoning benchmarks show that Token-Supervised Value Model (TVM) can outperform step-by-step verifiers on GSM8K and MATH with Mistral and Llama.

In multi-session dialog system, it is essential to continuously update the memory as the session progresses. Simply accumulating memory can make it difficult to focus on the content of the conversation for inference due to the limited input sentence size. Therefore, efficient and accurate conversation model that is capable of managing memory to reflect the conversation history continuously is necessary. This paper presents a conversation model that efficiently manages memory as sessions progress and incorporates this into the model to reflect the conversation history accurately with 3 methodologies: SFT, DPO and DPO with SFT model. Our model using DPO algorithm shows an improvement about 0.0591 of BERTScore in memory accuracy, and the rate of responses reflecting the memory increased as well. Also, response generation performance enhanced about 4.292 in fluency, 3.935 in coherence, and 2.896 in consistency. This paper describes a training method that yields better performance than models with more than twice the parameter size, even when the model size is smaller. Thus, our model demonstrates efficiency not only in terms of accuracy but also in resource utilization.

We introduce HyperCLOVA X, a family of large language models (LLMs) tailored to the Korean language and culture, along with competitive capabilities in English, math, and coding. HyperCLOVA X was trained on a balanced mix of Korean, English, and code data, followed by instruction-tuning with high-quality human-annotated datasets while abiding by strict safety guidelines reflecting our commitment to responsible AI. The model is evaluated across various benchmarks, including comprehensive reasoning, knowledge, commonsense, factuality, coding, math, chatting, instruction-following, and harmlessness, in both Korean and English. HyperCLOVA X exhibits strong reasoning capabilities in Korean backed by a deep understanding of the language and cultural nuances. Further analysis of the inherent bilingual nature and its extension to multilingualism highlights the model's cross-lingual proficiency and strong generalization ability to untargeted languages, including machine translation between several language pairs and cross-lingual inference tasks. We believe that HyperCLOVA X can provide helpful guidance for regions or countries in developing their sovereign LLMs., Comment: 44 pages; updated authors list and fixed author names

Most reinforcement learning (RL) methods focus on learning optimal policies over low-level action spaces. While these methods can perform well in their training environments, they lack the flexibility to transfer to new tasks. Instead, RL agents that can act over useful, temporally extended skills rather than low-level actions can learn new tasks more easily. Prior work in skill-based RL either requires expert supervision to define useful skills, which is hard to scale, or learns a skill-space from offline data with heuristics that limit the adaptability of the skills, making them difficult to transfer during downstream RL. Our approach, EXTRACT, instead utilizes pre-trained vision language models to extract a discrete set of semantically meaningful skills from offline data, each of which is parameterized by continuous arguments, without human supervision. This skill parameterization allows robots to learn new tasks by only needing to learn when to select a specific skill and how to modify its arguments for the specific task. We demonstrate through experiments in sparse-reward, image-based, robot manipulation environments that EXTRACT can more quickly learn new tasks than prior works, with major gains in sample efficiency and performance over prior skill-based RL. Website at https://www.jessezhang.net/projects/extract/., Comment: 22 pages, 13 figures

Positive thinking is thought to be an important component of self-motivation in various practical fields such as education and the workplace. Previous work, including sentiment transfer and positive reframing, has focused on the positive side of language. However, self-motivation that drives people to reach their goals has not yet been studied from a computational perspective. Moreover, negative feedback has not yet been explored, even though positive and negative feedback are both necessary to grow self-motivation. To facilitate self-motivation, we propose CArrot and STICk (CASTIC) dataset, consisting of 12,590 sentences with 5 different strategies for enhancing self-motivation. Our data and code are publicly available at here., Comment: 10 pages, 8 figures

To create culturally inclusive vision-language models (VLMs), the foremost requirement is developing a test benchmark that can diagnose the models' ability to respond to questions reflecting cultural elements. This paper addresses the necessity for such benchmarks, noting that existing research has relied on human annotators' manual efforts, which impedes diversity and efficiency. We propose a semi-automated pipeline for constructing cultural VLM benchmarks to enhance diversity and efficiency. This pipeline leverages human-VLM collaboration, where VLMs generate questions based on guidelines, human-annotated examples, and image-wise relevant knowledge, which are then reviewed by native speakers for quality and cultural relevance. The effectiveness of our adaptable pipeline is demonstrated through a specific application: creating a dataset tailored to Korean culture, dubbed K-Viscuit. The resulting benchmark features two types of questions: Type 1 questions measure visual recognition abilities, while Type 2 assess fine-grained visual reasoning skills. This ensures a thorough diagnosis of VLM models across various aspects. Our evaluation using K-Viscuit revealed that open-source models notably lag behind proprietary models in understanding Korean culture, highlighting areas for improvement. We provided diverse analyses of VLM performance across different cultural aspects. Besides, we explored the potential of incorporating external knowledge retrieval to enhance the generation process, suggesting future directions for improving cultural interpretation ability of VLMs. Our dataset and code will be made publicly available.

This work presents a framework based on feature disentanglement to learn speaker embeddings that are robust to environmental variations. Our framework utilises an auto-encoder as a disentangler, dividing the input speaker embedding into components related to the speaker and other residual information. We employ a group of objective functions to ensure that the auto-encoder's code representation - used as the refined embedding - condenses only the speaker characteristics. We show the versatility of our framework through its compatibility with any existing speaker embedding extractor, requiring no structural modifications or adaptations for integration. We validate the effectiveness of our framework by incorporating it into two popularly used embedding extractors and conducting experiments across various benchmarks. The results show a performance improvement of up to 16%. We release our code for this work to be available https://github.com/kaistmm/voxceleb-disentangler, Comment: Interspeech 2024. The official webpage can be found at https://mm.kaist.ac.kr/projects/voxceleb-disentangler/

Single-source domain generalization (SDG) in medical image segmentation (MIS) aims to generalize a model using data from only one source domain to segment data from an unseen target domain. Despite substantial advances in SDG with data augmentation, existing methods often fail to fully consider the details and uncertain areas prevalent in MIS, leading to mis-segmentation. This paper proposes a Fourier-based semantic augmentation method called FIESTA using uncertainty guidance to enhance the fundamental goals of MIS in an SDG context by manipulating the amplitude and phase components in the frequency domain. The proposed Fourier augmentative transformer addresses semantic amplitude modulation based on meaningful angular points to induce pertinent variations and harnesses the phase spectrum to ensure structural coherence. Moreover, FIESTA employs epistemic uncertainty to fine-tune the augmentation process, improving the ability of the model to adapt to diverse augmented data and concentrate on areas with higher ambiguity. Extensive experiments across three cross-domain scenarios demonstrate that FIESTA surpasses recent state-of-the-art SDG approaches in segmentation performance and significantly contributes to boosting the applicability of the model in medical imaging modalities., Comment: 40 pages, 7 figures, 5 tables

Homomorphic encryption (HE) is pivotal for secure computation on encrypted data, crucial in privacy-preserving data analysis. However, efficiently processing high-dimensional data in HE, especially for machine learning and statistical (ML/STAT) algorithms, poses a challenge. In this paper, we present an effective acceleration method using the kernel method for HE schemes, enhancing time performance in ML/STAT algorithms within encrypted domains. This technique, independent of underlying HE mechanisms and complementing existing optimizations, notably reduces costly HE multiplications, offering near constant time complexity relative to data dimension. Aimed at accessibility, this method is tailored for data scientists and developers with limited cryptography background, facilitating advanced data analysis in secure environments., Comment: Submitted as a preprint

As DNNs are widely adopted in various application domains while demanding increasingly higher compute and memory requirements, designing efficient and performant NPUs (Neural Processing Units) is becoming more important. However, existing architectural NPU simulators lack support for high-speed simulation, multi-core modeling, multi-tenant scenarios, detailed DRAM/NoC modeling, and/or different deep learning frameworks. To address these limitations, this work proposes ONNXim, a fast cycle-level simulator for multi-core NPUs in DNN serving systems. It takes DNN models represented in the ONNX graph format generated from various deep learning frameworks for ease of simulation. In addition, based on the observation that typical NPU cores process tensor tiles from on-chip scratchpad memory with deterministic compute latency, we forgo a detailed modeling for the computation while still preserving simulation accuracy. ONNXim also preserves dependencies between compute and tile DMAs. Meanwhile, the DRAM and NoC are modeled in cycle-level to properly model contention among multiple cores that can execute different DNN models for multi-tenancy. Consequently, ONNXim is significantly faster than existing simulators (e.g., by up to 384x over Accel-sim) and enables various case studies, such as multi-tenant NPUs, that were previously impractical due to slow speed and/or lack of functionalities. ONNXim is publicly available at https://github.com/PSAL-POSTECH/ONNXim.

Electromagnetic (EM) simulation plays a crucial role in analyzing and designing devices with sub-wavelength scale structures such as solar cells, semiconductor devices, image sensors, future displays and integrated photonic devices. Specifically, optics problems such as estimating semiconductor device structures and designing nanophotonic devices provide intriguing research topics with far-reaching real world impact. Traditional algorithms for such tasks require iteratively refining parameters through simulations, which often yield sub-optimal results due to the high computational cost of both the algorithms and EM simulations. Machine learning (ML) emerged as a promising candidate to mitigate these challenges, and optics research community has increasingly adopted ML algorithms to obtain results surpassing classical methods across various tasks. To foster a synergistic collaboration between the optics and ML communities, it is essential to have an EM simulation software that is user-friendly for both research communities. To this end, we present Meent, an EM simulation software that employs rigorous coupled-wave analysis (RCWA). Developed in Python and equipped with automatic differentiation (AD) capabilities, Meent serves as a versatile platform for integrating ML into optics research and vice versa. To demonstrate its utility as a research platform, we present three applications of Meent: 1) generating a dataset for training neural operator, 2) serving as an environment for the reinforcement learning of nanophotonic device optimization, and 3) providing a solution for inverse problems with gradient-based optimizers. These applications highlight Meent's potential to advance both EM simulation and ML methodologies. The code is available at https://github.com/kc-ml2/meent with the MIT license to promote the cross-polinations of ideas among academic researchers and industry practitioners., Comment: under review

The baryon masses on CLS ensembles are used to determine the LEC that characterize QCD in the flavor-SU(3) limit with vanishing up, down, and strange quark masses. Here we reevaluate some of the baryon masses on flavor-symmetric ensembles with much-improved statistical precision, in particular for the decuplet states. These additional results then lead to a more significant chiral extrapolation of the Lattice data set to its chiral SU(3) limit. Our results are based on the chiral Lagrangian with baryon octet and decuplet fields considered at the one-loop level. Finite-box and discretization effects of the Lattice data are considered systematically. While in our global fit of the data we insist on large-Nc sum rules for the LEC that enter at N3LO, all other LEC are unconstrained. In particular, we obtain values for the chiral limit of the pion decay constant and the isospin-limit of the quark-mass ratio compatible with the FLAG report., Comment: 26 pages, 4 figures and 9 tables - minor update. arXiv admin note: text overlap with arXiv:2301.06837

In speaker verification systems, the utilization of short utterances presents a persistent challenge, leading to performance degradation primarily due to insufficient phonetic information to characterize the speakers. To overcome this obstacle, we propose a novel structure, MR-RawNet, designed to enhance the robustness of speaker verification systems against variable duration utterances using raw waveforms. The MR-RawNet extracts time-frequency representations from raw waveforms via a multi-resolution feature extractor that optimally adjusts both temporal and spectral resolutions simultaneously. Furthermore, we apply a multi-resolution attention block that focuses on diverse and extensive temporal contexts, ensuring robustness against changes in utterance length. The experimental results, conducted on VoxCeleb1 dataset, demonstrate that the MR-RawNet exhibits superior performance in handling utterances of variable duration compared to other raw waveform-based systems., Comment: 5 pages, accepted by Interspeech 2024

Crystals with unique ionic arrangements and strong electronic correlations serve as a fertile ground for the emergence of exotic phases, as evidenced by the coexistence of charge density wave (CDW) and superconductivity in vanadium Kagome metals, specifically AV3Sb5 (where A represents K, Rb, or Cs). The formation of a star of David CDW superstructure, resulting from the coordinated displacements of vanadium ions on a corner sharing triangular lattice, has garnered significant attention in efforts to comprehend the influence of electron phonon interaction within this geometrically intricate lattice. However, understanding of the underlying mechanism behind CDW formation, coupled with symmetry protected lattice vibrations, remains elusive. In this study, we employed time resolved X ray scattering experiments utilising an X ray free electron laser. Our findings reveal that the phonon mode associated with the out of plane motion of Cs ions becomes frustrated in the CDW phase. Furthermore, we observed the photoinduced emergence of a metastable CDW phase, facilitated by the alleviation of frustration through nonadiabatic changes in free energy. By elucidating the longstanding puzzle surrounding the intervention of phonons in CDW ordering, this research offers fresh insights into the competition between phonons and periodic lattice distortions, a phenomenon widespread in other correlated quantum materials including layered high Tc superconductors., Comment: Manuscript: 20 pages, 4 figures, SI: 14 pages, 8 figures

In this paper, the solution of HYU MLLAB KT Team to the Multimodal Algorithmic Reasoning Task: SMART-101 CVPR 2024 Challenge is presented. Beyond conventional visual question-answering problems, the SMART-101 challenge aims to achieve human-level multimodal understanding by tackling complex visio-linguistic puzzles designed for children in the 6-8 age group. To solve this problem, we suggest two main ideas. First, to utilize the reasoning ability of a large-scale language model (LLM), the given visual cues (images) are grounded in the text modality. For this purpose, we generate highly detailed text captions that describe the context of the image and use these captions as input for the LLM. Second, due to the nature of puzzle images, which often contain various geometric visual patterns, we utilize an object detection algorithm to ensure these patterns are not overlooked in the captioning process. We employed the SAM algorithm, which can detect various-size objects, to capture the visual features of these geometric patterns and used this information as input for the LLM. Under the puzzle split configuration, we achieved an option selection accuracy Oacc of 29.5 on the test set and a weighted option selection accuracy (WOSA) of 27.1 on the challenge set.

Most advances in 3D Generative Adversarial Networks (3D GANs) largely depend on ray casting-based volume rendering, which incurs demanding rendering costs. One promising alternative is rasterization-based 3D Gaussian Splatting (3D-GS), providing a much faster rendering speed and explicit 3D representation. In this paper, we exploit Gaussian as a 3D representation for 3D GANs by leveraging its efficient and explicit characteristics. However, in an adversarial framework, we observe that a na\"ive generator architecture suffers from training instability and lacks the capability to adjust the scale of Gaussians. This leads to model divergence and visual artifacts due to the absence of proper guidance for initialized positions of Gaussians and densification to manage their scales adaptively. To address these issues, we introduce a generator architecture with a hierarchical multi-scale Gaussian representation that effectively regularizes the position and scale of generated Gaussians. Specifically, we design a hierarchy of Gaussians where finer-level Gaussians are parameterized by their coarser-level counterparts; the position of finer-level Gaussians would be located near their coarser-level counterparts, and the scale would monotonically decrease as the level becomes finer, modeling both coarse and fine details of the 3D scene. Experimental results demonstrate that ours achieves a significantly faster rendering speed (x100) compared to state-of-the-art 3D consistent GANs with comparable 3D generation capability. Project page: https://hse1032.github.io/gsgan., Comment: Project page: https://hse1032.github.io/gsgan

Building a reliable visual question answering~(VQA) system across different languages is a challenging problem, primarily due to the lack of abundant samples for training. To address this challenge, recent studies have employed machine translation systems for the cross-lingual VQA task. This involves translating the evaluation samples into a source language (usually English) and using monolingual models (i.e., translate-test). However, our analysis reveals that translated texts contain unique characteristics distinct from human-written ones, referred to as translation artifacts. We find that these artifacts can significantly affect the models, confirmed by extensive experiments across diverse models, languages, and translation processes. In light of this, we present a simple data augmentation strategy that can alleviate the adverse impacts of translation artifacts., Comment: ACL 2024 Findings Accepted

Soft labels can improve the generalization of a neural network classifier in many domains, such as image classification. Despite its success, the current literature has overlooked the efficiency of label smoothing in node classification with graph-structured data. In this work, we propose a simple yet effective label smoothing for the transductive node classification task. We design the soft label to encapsulate the local context of the target node through the neighborhood label distribution. We apply the smoothing method for seven baseline models to show its effectiveness. The label smoothing methods improve the classification accuracy in 10 node classification datasets in most cases. In the following analysis, we find that incorporating global label statistics in posterior computation is the key to the success of label smoothing. Further investigation reveals that the soft labels mitigate overfitting during training, leading to better generalization performance.

Recent studies have actively employed persistent homology (PH), a topological data analysis technique, to analyze the topological information in time series data. Many successful studies have utilized graph representations of time series data for PH calculation. Given the diverse nature of time series data, it is crucial to have mechanisms that can adjust the PH calculations by incorporating domain-specific knowledge. In this context, we introduce a methodology that allows the adjustment of PH calculations by reflecting relevant domain knowledge in specific fields. We introduce the concept of featured time series, which is the pair of a time series augmented with specific features such as domain knowledge, and an influence vector that assigns a value to each feature to fine-tune the results of the PH. We then prove the stability theorem of the proposed method, which states that adjusting the influence vectors grants stability to the PH calculations. The proposed approach enables the tailored analysis of a time series based on the graph representation methodology, which makes it applicable to real-world domains. We consider two examples to verify the proposed method's advantages: anomaly detection of stock data and topological analysis of music data.

Automated docking technologies of marine boats have been enlightened by an increasing number of literature. This paper contributes to the literature by proposing a mathematical framework that automates "trailer loading" in the presence of wind disturbances, which is unexplored despite its importance to boat owners. The comprehensive pipeline of localization, system identification, and trajectory optimization is structured, followed by several techniques to improve performance reliability. The performance of the proposed method was demonstrated with a commercial pontoon boat in Michigan, in 2023, securing a success rate of 80\% in the presence of perception errors and wind disturbance. This result indicates the strong potential of the proposed pipeline, effectively accommodating the wind effect., Comment: To be presented at IEEE Intelligent Vehicles Symposium (IV 2024)

Image segmentation is one of the major computer vision tasks, which is applicable in a variety of domains, such as autonomous navigation of an unmanned aerial vehicle. However, image segmentation cannot easily materialize on tiny embedded systems because image segmentation models generally have high peak memory usage due to their architectural characteristics. This work finds that image segmentation models unnecessarily require large memory space with an existing tiny machine learning framework. That is, the existing framework cannot effectively manage the memory space for the image segmentation models. This work proposes TinySeg, a new model optimizing framework that enables memory-efficient image segmentation for tiny embedded systems. TinySeg analyzes the lifetimes of tensors in the target model and identifies long-living tensors. Then, TinySeg optimizes the memory usage of the target model mainly with two methods: (i) tensor spilling into local or remote storage and (ii) fused fetching of spilled tensors. This work implements TinySeg on top of the existing tiny machine learning framework and demonstrates that TinySeg can reduce the peak memory usage of an image segmentation model by 39.3% for tiny embedded systems., Comment: LCTES 2024

We present the results from the first two years of the Planet Hunters NGTS citizen science project, which searches for transiting planet candidates in data from the Next Generation Transit Survey (NGTS) by enlisting the help of members of the general public. Over 8,000 registered volunteers reviewed 138,198 light curves from the NGTS Public Data Releases 1 and 2. We utilize a user weighting scheme to combine the classifications of multiple users to identify the most promising planet candidates not initially discovered by the NGTS team. We highlight the five most interesting planet candidates detected through this search, which are all candidate short-period giant planets. This includes the TIC-165227846 system that, if confirmed, would be the lowest-mass star to host a close-in giant planet. We assess the detection efficiency of the project by determining the number of confirmed planets from the NASA Exoplanet Archive and TESS Objects of Interest (TOIs) successfully recovered by this search and find that 74% of confirmed planets and 63% of TOIs detected by NGTS are recovered by the Planet Hunters NGTS project. The identification of new planet candidates shows that the citizen science approach can provide a complementary method to the detection of exoplanets with ground-based surveys such as NGTS., Comment: 42 pages, 20 figures, 17 tables. To be published in AJ

Link prediction (LP), inferring the connectivity between nodes, is a significant research area in graph data, where a link represents essential information on relationships between nodes. Although graph neural network (GNN)-based models have achieved high performance in LP, understanding why they perform well is challenging because most comprise complex neural networks. We employ persistent homology (PH), a topological data analysis method that helps analyze the topological information of graphs, to explain the reasons for the high performance. We propose a novel method that employs PH for LP (PHLP) focusing on how the presence or absence of target links influences the overall topology. The PHLP utilizes the angle hop subgraph and new node labeling called degree double radius node labeling (Degree DRNL), distinguishing the information of graphs better than DRNL. Using only a classifier, PHLP performs similarly to state-of-the-art (SOTA) models on most benchmark datasets. Incorporating the outputs calculated using PHLP into the existing GNN-based SOTA models improves performance across all benchmark datasets. To the best of our knowledge, PHLP is the first method of applying PH to LP without GNNs. The proposed approach, employing PH while not relying on neural networks, enables the identification of crucial factors for improving performance.

This technical report introduces Pegasus-1, a multimodal language model specialized in video content understanding and interaction through natural language. Pegasus-1 is designed to address the unique challenges posed by video data, such as interpreting spatiotemporal information, to offer nuanced video content comprehension across various lengths. This technical report overviews Pegasus-1's architecture, training strategies, and its performance in benchmarks on video conversation, zero-shot video question answering, and video summarization. We also explore qualitative characteristics of Pegasus-1 , demonstrating its capabilities as well as its limitations, in order to provide readers a balanced view of its current state and its future direction.

Vision-based ego-lane inference using High-Definition (HD) maps is essential in autonomous driving and advanced driver assistance systems. The traditional approach necessitates well-calibrated cameras, which confines variation of camera configuration, as the algorithm relies on intrinsic and extrinsic calibration. In this paper, we propose a learning-based ego-lane inference by directly estimating the ego-lane index from a single image. To enhance robust performance, our model incorporates the two-head structure inferring ego-lane in two perspectives simultaneously. Furthermore, we utilize an attention mechanism guided by vanishing point-and-line to adapt to changes in viewpoint without requiring accurate calibration. The high adaptability of our model was validated in diverse environments, devices, and camera mounting points and orientations.

Quantum computer is extensively used in solving financial problems. Quantum amplitude estimation, an algorithm that aims to estimate the amplitude of a given quantum state, can be utilized to determine the expectation value of bonds as the logic introduced in quantum risk analysis. As the number of the evaluation qubit increases, the more accurate the precise the outcome expectation value is. This augmentation in qubits, however, also leads to a varied escalation in circuit complexity, contingent upon the type of quantum computing device. By analyzing the number of two-qubit gates in the superconducting circuit and ion-trap quantum system, this study examines that the native gates and connectivity nature of the ion-trap system lead to less complicated quantum circuits. Across a range of experiments conducted with one to nineteen qubits, the examination reveals that the ion-trap system exhibits a two to three factor reduction in the number of required two-qubit gates when compared to the superconducting circuit system., Comment: 19 pages, 10 figures

A geometric figure is a reptile if it can be dissected into at least two similar copies congruent to each other. We prove that if a trapezoid is a reptile and not a parallelogram, then the length of each base is a linear combination of the lengths of its legs with rational coefficients. We then rule out isosceles trapezoids and right trapezoids which are not reptile. In particular, we prove that, up to similarity, there are at most six reptile right trapezoids, not a parallelogram, whose acute internal angle is a rational multiple of $\pi$. Finally, we present a rep-25 right trapezoid that is not a parallelogram and is not similar to any of the known reptile trapezoids., Comment: 42 pages, 20 figures, sections 1 and 3 improved, references added for section 3, author's affiliation added

Large-scale contrastive vision-language pre-trained models provide the zero-shot model achieving competitive performance across a range of image classification tasks without requiring training on downstream data. Recent works have confirmed that while additional fine-tuning of the zero-shot model on the reference data results in enhanced downstream performance, it compromises the model's robustness against distribution shifts. Our investigation begins by examining the conditions required to achieve the goals of robust fine-tuning, employing descriptions based on feature distortion theory and joint energy-based models. Subsequently, we propose a novel robust fine-tuning algorithm, Lipsum-FT, that effectively utilizes the language modeling aspect of the vision-language pre-trained models. Extensive experiments conducted on distribution shift scenarios in DomainNet and ImageNet confirm the superiority of our proposed Lipsum-FT approach over existing robust fine-tuning methods., Comment: ICLR 2024

This paper revives Densely Connected Convolutional Networks (DenseNets) and reveals the underrated effectiveness over predominant ResNet-style architectures. We believe DenseNets' potential was overlooked due to untouched training methods and traditional design elements not fully revealing their capabilities. Our pilot study shows dense connections through concatenation are strong, demonstrating that DenseNets can be revitalized to compete with modern architectures. We methodically refine suboptimal components - architectural adjustments, block redesign, and improved training recipes towards widening DenseNets and boosting memory efficiency while keeping concatenation shortcuts. Our models, employing simple architectural elements, ultimately surpass Swin Transformer, ConvNeXt, and DeiT-III - key architectures in the residual learning lineage. Furthermore, our models exhibit near state-of-the-art performance on ImageNet-1K, competing with the very recent models and downstream tasks, ADE20k semantic segmentation, and COCO object detection/instance segmentation. Finally, we provide empirical analyses that uncover the merits of the concatenation over additive shortcuts, steering a renewed preference towards DenseNet-style designs. Our code is available at https://github.com/naver-ai/rdnet., Comment: ECCV 2024. Code at https://github.com/naver-ai/rdnet