Search

Relying on the representation power of neural networks, most recent works have often neglected several factors involved in haze degradation, such as transmission (the amount of light reaching an observer from a scene over distance) and atmospheric light. These factors are generally unknown, making dehazing problems ill-posed and creating inherent uncertainties. To account for such uncertainties and factors involved in haze degradation, we introduce a variational Bayesian framework for single image dehazing. We propose to take not only a clean image and but also transmission map as latent variables, the posterior distributions of which are parameterized by corresponding neural networks: dehazing and transmission networks, respectively. Based on a physical model for haze degradation, our variational Bayesian framework leads to a new objective function that encourages the cooperation between them, facilitating the joint training of and thereby boosting the performance of each other. In our framework, a dehazing network can estimate a clean image independently of a transmission map estimation during inference, introducing no overhead. Furthermore, our model-agnostic framework can be seamlessly incorporated with other existing dehazing networks, greatly enhancing the performance consistently across datasets and models., Comment: Published in CIKM 2023, 10 pages, 9 figures

Transformer-based architectures have demonstrated remarkable success across various domains, but their deployment on edge devices remains challenging due to high memory and computational demands. In this paper, we introduce a novel Reuse Attention mechanism, tailored for efficient memory access and computational optimization, enabling seamless operation on resource-constrained platforms without compromising performance. Unlike traditional multi-head attention (MHA), which redundantly computes separate attention matrices for each head, Reuse Attention consolidates these computations into a shared attention matrix, significantly reducing memory overhead and computational complexity. Comprehensive experiments on ImageNet-1K and downstream tasks show that the proposed UniForm models leveraging Reuse Attention achieve state-of-the-art imagenet classification accuracy while outperforming existing attention mechanisms, such as Linear Attention and Flash Attention, in inference speed and memory scalability. Notably, UniForm-l achieves a 76.7% Top-1 accuracy on ImageNet-1K with 21.8ms inference time on edge devices like the Jetson AGX Orin, representing up to a 5x speedup over competing benchmark methods. These results demonstrate the versatility of Reuse Attention across high-performance GPUs and edge platforms, paving the way for broader real-time applications, Comment: 13 Pages, 8 Tables, 7 Figures

The needs for sensitively and reliably probing magnetization dynamics have been increasing in various contexts such as studying novel hybrid magnonic systems, in which the spin dynamics strongly and coherently couple to other excitations, including microwave photons, light photons, or phonons. Recent advances in quantum magnonics also highlight the need for employing magnon phase as quantum state variables, which is to be detected and mapped out with high precision in on-chip micro- and nano-scale magnonic devices. Here, we demonstrate a facile optical technique that can directly perform concurrent spectroscopic and imaging functionalities with spatial- and phase-resolutions, using infrared strobe light operating at 1550-nm wavelength. To showcase the methodology, we spectroscopically studied the phase-resolved spin dynamics in a bilayer of Permalloy and Y3Fe5O12 (YIG), and spatially imaged the backward volume spin wave modes of YIG in the dipolar spin wave regime. Using the strobe light probe, the detected precessional phase contrast can be directly used to construct the map of the spin wave wavefront, in the continuous-wave regime of spin-wave propagation and in the stationary state, without needing any optical reference path. By selecting the applied field, frequency, and detection phase, the spin wave images can be made sensitive to the precession amplitude and phase. Our results demonstrate that infrared optical strobe light can serve as a versatile platform for magneto-optical probing of magnetization dynamics, with potential implications in investigating hybrid magnonic systems., Comment: 16 pages, 12 figures

Thanks to unprecedented language understanding and generation capabilities of large language model (LLM), Retrieval-augmented Code Generation (RaCG) has recently been widely utilized among software developers. While this has increased productivity, there are still frequent instances of incorrect codes being provided. In particular, there are cases where plausible yet incorrect codes are generated for queries from users that cannot be answered with the given queries and API descriptions. This study proposes a task for evaluating answerability, which assesses whether valid answers can be generated based on users' queries and retrieved APIs in RaCG. Additionally, we build a benchmark dataset called Retrieval-augmented Code Generability Evaluation (RaCGEval) to evaluate the performance of models performing this task. Experimental results show that this task remains at a very challenging level, with baseline models exhibiting a low performance of 46.7%. Furthermore, this study discusses methods that could significantly improve performance.

Device-to-device variations in ferroelectric (FE) hafnium oxide-based devices pose a crucial challenge that limits the otherwise promising capabilities of this technology. Earlier simulation-based studies have identified polarization (P) domain nucleation and polycrystallinity as key contributors to these variations. In this work, we experimentally investigate the effect of these two factors on remanent polarization (PR) variation in Hf0.5Zr0.5O2 (HZO) based metal-ferroelectric-insulator-metal (MFIM) capacitors for different set voltages (VSET) and FE thicknesses (TFE). Our measurements reveal a non-monotonic behavior of PR variations with VSET, which is consistent with previous simulation-based predictions. For low and high-VSET regions, we find that PR variations are dictated primarily by saturation polarization (PS) variations and are associated with the polycrystallinity in HZO. Our measurements also reveal that PR variations peak near the coercive voltage (VC), defined as the mid-VSET region. We attribute the increase of PR variation around VC to the random nature and sharp P switching associated with domain nucleation, which is dominant near VC. Further, we observe a reduction in the peak PR variation as HZO thickness (TFE) is scaled. We validate our arguments by establishing the correlation between the measured values of PR with VC and PS. Our results display that a strong correlation exists between PR and VC in the mid-VSET region and between PR and PS in the low and high-VSET regions across various TFE., Comment: 6 pages, 8 figures

We propose a novel framework based on neural network that reformulates classical mechanics as an operator learning problem. A machine directly maps a potential function to its corresponding trajectory in phase space without solving the Hamilton equations. Most notably, while conventional methods tend to accumulate errors over time through iterative time integration, our approach prevents error propagation. Two newly developed neural network architectures, namely VaRONet and MambONet, are introduced to adapt the Variational LSTM sequence-to-sequence model and leverage the Mamba model for efficient temporal dynamics processing. We tested our approach with various 1D physics problems: harmonic oscillation, double-well potentials, Morse potential, and other potential models outside the training data. Compared to traditional numerical methods based on the fourth-order Runge-Kutta (RK4) algorithm, our model demonstrates improved computational efficiency and accuracy. Code is available at: https://github.com/Axect/Neural_Hamilton, Comment: 33 pages, 8 figures, 9 tables

Super-resolution methods are increasingly becoming popular for both real-world and face-specific tasks. Many existing approaches, however, rely on simplistic degradation models, which limits their ability to handle complex and unknown degradation patterns effectively. While diffusion-based super-resolution techniques have recently shown impressive results, they are still constrained by the need for numerous inference steps. To address this, we propose TDDSR, an efficient single-step diffusion-based super-resolution method. Our method, distilled from a pre-trained teacher model and based on a diffusion network, performs super-resolution in a single step. It integrates a learnable diffusion-based downsampler to capture diverse degradation patterns and employs two discriminators, one for high-resolution and one for low-resolution images, to enhance the overall performance. Experimental results demonstrate its effectiveness across real-world and face-specific SR tasks, achieving performance beyond other state-of-the-art models and comparable to previous diffusion methods with multiple sampling steps.

3D human shape reconstruction under severe occlusion due to human-object or human-human interaction is a challenging problem. Parametric models i.e., SMPL(-X), which are based on the statistics across human shapes, can represent whole human body shapes but are limited to minimally-clothed human shapes. Implicit-function-based methods extract features from the parametric models to employ prior knowledge of human bodies and can capture geometric details such as clothing and hair. However, they often struggle to handle misaligned parametric models and inpaint occluded regions given a single RGB image. In this work, we propose a novel pipeline, MHCDIFF, Multi-hypotheses Conditioned Point Cloud Diffusion, composed of point cloud diffusion conditioned on probabilistic distributions for pixel-aligned detailed 3D human reconstruction under occlusion. Compared to previous implicit-function-based methods, the point cloud diffusion model can capture the global consistent features to generate the occluded regions, and the denoising process corrects the misaligned SMPL meshes. The core of MHCDIFF is extracting local features from multiple hypothesized SMPL(-X) meshes and aggregating the set of features to condition the diffusion model. In the experiments on CAPE and MultiHuman datasets, the proposed method outperforms various SOTA methods based on SMPL, implicit functions, point cloud diffusion, and their combined, under synthetic and real occlusions. Our code is publicly available at https://donghwankim0101.github.io/projects/mhcdiff/ ., Comment: 17 pages, 7 figures, accepted NeurIPS 2024

Recent advancements in machine learning (ML) are transforming the field of structural biology. For example, AlphaFold, a groundbreaking neural network for protein structure prediction, has been widely adopted by researchers. The availability of easy-to-use interfaces and interpretable outcomes from the neural network architecture, such as the confidence scores used to color the predicted structures, have made AlphaFold accessible even to non-ML experts. In this paper, we present various methods for representing protein 3D structures from low- to high-resolution, and show how interpretable ML methods can support tasks such as predicting protein structures, protein function, and protein-protein interactions. This survey also emphasizes the significance of interpreting and visualizing ML-based inference for structure-based protein representations that enhance interpretability and knowledge discovery. Developing such interpretable approaches promises to further accelerate fields including drug development and protein design.

Estimating the poses of both a hand and an object has become an important area of research due to the growing need for advanced vision computing. The primary challenge involves understanding and reconstructing how hands and objects interact, such as contact and physical plausibility. Existing approaches often adopt a graph neural network to incorporate spatial information of hand and object meshes. However, these approaches have not fully exploited the potential of graphs without modification of edges within and between hand- and object-graphs. We propose a graph-based refinement method that incorporates an interaction-aware graph-attention mechanism to account for hand-object interactions. Using edges, we establish connections among closely correlated nodes, both within individual graphs and across different graphs. Experiments demonstrate the effectiveness of our proposed method with notable improvements in the realm of physical plausibility., Comment: 7 pages, Accepted by ICIP 2024

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

Studies on quantum algorithms for ground state energy estimation often assume perfect ground state preparation; however, in reality the initial state will have imperfect overlap with the true ground state. Here we address that problem in two ways: by faster preparation of matrix product state (MPS) approximations, and more efficient filtering of the prepared state to find the ground state energy. We show how to achieve unitary synthesis with a Toffoli complexity about $7 \times$ lower than that in prior work, and use that to derive a more efficient MPS preparation method. For filtering we present two different approaches: sampling and binary search. For both we use the theory of window functions to avoid large phase errors and minimise the complexity. We find that the binary search approach provides better scaling with the overlap at the cost of a larger constant factor, such that it will be preferred for overlaps less than about $0.003$. Finally, we estimate the total resources to perform ground state energy estimation of Fe-S cluster systems, including the FeMo cofactor by estimating the overlap of different MPS initial states with potential ground-states of the FeMo cofactor using an extrapolation procedure. {With a modest MPS bond dimension of 4000, our procedure produces an estimate of $\sim 0.9$ overlap squared with a candidate ground-state of the FeMo cofactor, producing a total resource estimate of $7.3 \times 10^{10}$ Toffoli gates; neglecting the search over candidates and assuming the accuracy of the extrapolation, this validates prior estimates that used perfect ground state overlap. This presents an example of a practical path to prepare states of high overlap in a challenging-to-compute chemical system., Comment: 47 pages, 20 figures

Accurate 3D object detection is crucial for autonomous vehicles and robots to navigate and interact with the environment safely and effectively. Meanwhile, the performance of 3D detector relies on the data size and annotation which is expensive. Consequently, the demand of training with limited labeled data is growing. We explore a novel teacher-student framework employing channel augmentation for 3D semi-supervised object detection. The teacher-student SSL typically adopts a weak augmentation and strong augmentation to teacher and student, respectively. In this work, we apply multiple channel augmentations to both networks using the transformation equivariance detector (TED). The TED allows us to explore different combinations of augmentation on point clouds and efficiently aggregates multi-channel transformation equivariance features. In principle, by adopting fixed channel augmentations for the teacher network, the student can train stably on reliable pseudo-labels. Adopting strong channel augmentations can enrich the diversity of data, fostering robustness to transformations and enhancing generalization performance of the student network. We use SOTA hierarchical supervision as a baseline and adapt its dual-threshold to TED, which is called channel IoU consistency. We evaluate our method with KITTI dataset, and achieved a significant performance leap, surpassing SOTA 3D semi-supervised object detection models., Comment: Accepted to 2024 IEEE International Conference on Image Processing (ICIP)

Existing datasets for 3D hand-object interaction are limited either in the data cardinality, data variations in interaction scenarios, or the quality of annotations. In this work, we present a comprehensive new training dataset for hand-object interaction called HOGraspNet. It is the only real dataset that captures full grasp taxonomies, providing grasp annotation and wide intraclass variations. Using grasp taxonomies as atomic actions, their space and time combinatorial can represent complex hand activities around objects. We select 22 rigid objects from the YCB dataset and 8 other compound objects using shape and size taxonomies, ensuring coverage of all hand grasp configurations. The dataset includes diverse hand shapes from 99 participants aged 10 to 74, continuous video frames, and a 1.5M RGB-Depth of sparse frames with annotations. It offers labels for 3D hand and object meshes, 3D keypoints, contact maps, and \emph{grasp labels}. Accurate hand and object 3D meshes are obtained by fitting the hand parametric model (MANO) and the hand implicit function (HALO) to multi-view RGBD frames, with the MoCap system only for objects. Note that HALO fitting does not require any parameter tuning, enabling scalability to the dataset's size with comparable accuracy to MANO. We evaluate HOGraspNet on relevant tasks: grasp classification and 3D hand pose estimation. The result shows performance variations based on grasp type and object class, indicating the potential importance of the interaction space captured by our dataset. The provided data aims at learning universal shape priors or foundation models for 3D hand-object interaction. Our dataset and code are available at https://hograspnet2024.github.io/., Comment: 14 pages except for references. It will be published at European Conference on Computer Vision(ECCV) 2024

Quantification of tissue parameters using MRI is emerging as a powerful tool in clinical diagnosis and research studies. The need for multiple long scans with different acquisition parameters prohibits quantitative MRI from reaching widespread adoption in routine clinical and research exams. Accelerated parameter mapping techniques leverage parallel imaging, signal modelling and deep learning to offer more practical quantitative MRI acquisitions. However, the achievable acceleration and the quality of maps are often limited. Joint MAPLE is a recent state-of-the-art multi-parametric and scan-specific parameter mapping technique with promising performance at high acceleration rates. It synergistically combines parallel imaging, model-based and machine learning approaches for joint mapping of T1, T2*, proton density and the field inhomogeneity. However, Joint MAPLE suffers from prohibitively long reconstruction time to estimate the maps from a multi-echo, multi-flip angle (MEMFA) dataset at high resolution in a scan-specific manner. In this work, we propose a faster version of Joint MAPLE which retains the mapping performance of the original version. Coil compression, random slice selection, parameter-specific learning rates and transfer learning are synergistically combined in the proposed framework. It speeds-up the reconstruction time up to 700 times than the original version and processes a whole-brain MEMFA dataset in 21 minutes on average, which originally requires ~260 hours for Joint MAPLE. The mapping performance of the proposed framework is ~2-fold better than the standard and the state-of-the-art evaluated reconstruction techniques on average in terms of the root mean squared error.

This paper aims to adapt the source model to the target environment, leveraging small user feedback (i.e., labeled target data) readily available in real-world applications. We find that existing semi-supervised domain adaptation (SemiSDA) methods often suffer from poorly improved adaptation performance when directly utilizing such feedback data, as shown in Figure 1. We analyze this phenomenon via a novel concept called Negatively Biased Feedback (NBF), which stems from the observation that user feedback is more likely for data points where the model produces incorrect predictions. To leverage this feedback while avoiding the issue, we propose a scalable adapting approach, Retrieval Latent Defending. This approach helps existing SemiSDA methods to adapt the model with a balanced supervised signal by utilizing latent defending samples throughout the adaptation process. We demonstrate the problem caused by NBF and the efficacy of our approach across various benchmarks, including image classification, semantic segmentation, and a real-world medical imaging application. Our extensive experiments reveal that integrating our approach with multiple state-of-the-art SemiSDA methods leads to significant performance improvements., Comment: Accepted to ECCV 2024, Project page: https://sites.google.com/view/junha/nbf-rld

This study proposes two novel learning rate schedulers: the Hyperbolic Learning Rate Scheduler (HyperbolicLR) and the Exponential Hyperbolic Learning Rate Scheduler (ExpHyperbolicLR). These schedulers attempt to address the inconsistent learning curves often observed in conventional schedulers when adjusting the number of epochs. By leveraging the asymptotic behavior of hyperbolic curves, the proposed schedulers maintain more consistent learning curves across varying epoch settings. The HyperbolicLR algorithm directly applies this property to the epoch-learning rate space, while the ExpHyperbolicLR maps this concept onto the exponential space of epochs and learning rates. To evaluate the performance of these schedulers, first we found the optimal hyperparameters for each scheduler on a small number of epochs, fixed these values, and compared their performance as the number of epochs increased. Our experimental results on various deep learning tasks and architectures demonstrate that both HyperbolicLR and ExpHyperbolicLR maintain more consistent performance improvements compared to conventional schedulers as the number of epochs increases. These findings suggest that our hyperbolic-based learning rate schedulers offer a more robust and efficient approach to training deep neural networks, especially in scenarios where computational resources or time constraints limit extensive hyperparameter searches., Comment: 30 pages, 12 figures

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

Metasurfaces have become one of the most prominent research topics in the field of optics owing to their unprecedented properties and novel applications on an ultrathin platform. By combining graphene with metasurfaces, electrical tunable functions can be achieved with fast tuning speed, large modulation depth and broad tuning range. However, the tuning efficiency of hybrid graphene metasurfaces within the short-wavelength infrared (SWIR) spectrum is typically low because of the small resonance wavelength shift in this wavelength range. In this work, through the integration of graphene and silicon metasurfaces that support quasi-bound states in the continuum (quasi-BIC), we experimentally demonstrate significant transmittance tuning even with less than 30 nm resonance wavelength shift thanks to the high quality-factor of quasi-BIC metasurfaces. The tunable transmittance spectrum was measured using Fourier Transform Infrared Spectroscopy (FTIR) with a modified reflective lens to improve the accuracy, and the electrical tuning was realized utilizing the cut-and-stick method of ion gel. At the wavelength of 3.0 um, the measured change of transmittance T_max-T_min and modulation depth (T_max-T_min)/T_max can reach 22.2% and 28.9%, respectively, under a small bias voltage ranging from -2 V to +2 V. To the best of our knowledge, this work is the first experimental demonstration of tunable graphene/quasi-BIC metasurfaces, which have potential applications in optical modulation, reconfigurable photonic devices, and optical communications., Comment: 14 pages, 5 figures

The dynamics of human-AI communication have been reshaped by language models such as ChatGPT. However, extant research has primarily focused on dyadic communication, leaving much to be explored regarding the dynamics of human-AI communication in group settings. The availability of multiple language model chatbots presents a unique opportunity for scholars to better understand the interaction between humans and multiple chatbots. This study examines the impact of multi-chatbot communication in a specific persuasion setting: promoting charitable donations. We developed an online environment that enables multi-chatbot communication and conducted a pilot experiment utilizing two GPT-based chatbots, Save the Children and UNICEF chatbots, to promote charitable donations. In this study, we present our development process of the multi-chatbot interface and present preliminary findings from a pilot experiment. Analysis of qualitative and quantitative feedback are presented, and limitations are addressed.

Traffic accidents are recognized as a major social issue worldwide, causing numerous injuries and significant costs annually. Consequently, methods for predicting and preventing traffic accidents have been researched for many years. With advancements in the field of artificial intelligence, various studies have applied Machine Learning and Deep Learning techniques to traffic accident prediction. Modern traffic conditions change rapidly by the minute, and these changes vary significantly across different roads. In other words, the risk of traffic accidents changes minute by minute in various patterns for each road. Therefore, it is desirable to predict traffic accident risk at the Minute-Level and Road-Level. However, because roads have close and complex relationships with adjacent roads, research on predicting traffic accidents at the Minute-Level and Road-Level is challenging. Thus, it is essential to build a model that can reflect the spatial and temporal characteristics of roads for traffic accident prediction. Consequently, recent attempts have been made to use Graph Convolutional Networks to capture the spatial characteristics of roads and Recurrent Neural Networks to capture their temporal characteristics for predicting traffic accident risk. This paper proposes the Sequential based Spatio-Temporal Graph Convolutional Networks (SST-GCN), which combines GCN and LSTM, to predict traffic accidents at the Minute-Level and Road-Level using a road dataset constructed in Seoul, the capital of South Korea. Experiments have demonstrated that SST-GCN outperforms other state-of-the-art models in Minute-Level predictions.

By comparing constructions of block encoding given by [1-4], we propose a way to extract dequantizability from advancements in dequantization techniques that have been led by Tang, as in [5]. Then we apply this notion to the sparse-access input model that is known to be BQP-complete in general, thereby conceived to be un-dequantizable. Our goal is to break down this belief by examining the sparse-access input model's instances, particularly their input matrices. In conclusion, this paper forms a dequantizability-verifying scheme that can be applied whenever an input is given.

As Large Language Models (LLMs) are nondeterministic, the same input can generate different outputs, some of which may be incorrect or hallucinated. If run again, the LLM may correct itself and produce the correct answer. Unfortunately, most LLM-powered systems resort to single results which, correct or not, users accept. Having the LLM produce multiple outputs may help identify disagreements or alternatives. However, it is not obvious how the user will interpret conflicts or inconsistencies. To this end, we investigate how users perceive the AI model and comprehend the generated information when they receive multiple, potentially inconsistent, outputs. Through a preliminary study, we identified five types of output inconsistencies. Based on these categories, we conducted a study (N=252) in which participants were given one or more LLM-generated passages to an information-seeking question. We found that inconsistency within multiple LLM-generated outputs lowered the participants' perceived AI capacity, while also increasing their comprehension of the given information. Specifically, we observed that this positive effect of inconsistencies was most significant for participants who read two passages, compared to those who read three. Based on these findings, we present design implications that, instead of regarding LLM output inconsistencies as a drawback, we can reveal the potential inconsistencies to transparently indicate the limitations of these models and promote critical LLM usage., Comment: Accepted to FAccT 2024

With the advancement of Large-Language Models (LLMs) and Large Vision-Language Models (LVMs), agents have shown significant capabilities in various tasks, such as data analysis, gaming, or code generation. Recently, there has been a surge in research on web agents, capable of performing tasks within the web environment. However, the web poses unforeseeable scenarios, challenging the generalizability of these agents. This study investigates the disparities between human and web agents' performance in web tasks (e.g., information search) by concentrating on planning, action, and reflection aspects during task execution. We conducted a web task study with a think-aloud protocol, revealing distinct cognitive actions and operations on websites employed by humans. Comparative examination of existing agent structures and human behavior with thought processes highlighted differences in knowledge updating and ambiguity handling when performing the task. Humans demonstrated a propensity for exploring and modifying plans based on additional information and investigating reasons for failure. These findings offer insights into designing planning, reflection, and information discovery modules for web agents and designing the capturing method for implicit human knowledge in a web task.

The intensive computational burden of Stable Diffusion (SD) for text-to-image generation poses a significant hurdle for its practical application. To tackle this challenge, recent research focuses on methods to reduce sampling steps, such as Latent Consistency Model (LCM), and on employing architectural optimizations, including pruning and knowledge distillation. Diverging from existing approaches, we uniquely start with a compact SD variant, BK-SDM. We observe that directly applying LCM to BK-SDM with commonly used crawled datasets yields unsatisfactory results. It leads us to develop two strategies: (1) leveraging high-quality image-text pairs from leading generative models and (2) designing an advanced distillation process tailored for LCM. Through our thorough exploration of quantization, profiling, and on-device deployment, we achieve rapid generation of photo-realistic, text-aligned images in just two steps, with latency under one second on resource-limited edge devices., Comment: 4 pages, accepted to CVPR24 First Workshop on Efficient and On-Device Generation (EDGE)

Cardiologists use electrocardiograms (ECG) for the detection of arrhythmias. However, continuous monitoring of ECG signals to detect cardiac abnormal-ities requires significant time and human resources. As a result, several deep learning studies have been conducted in advance for the automatic detection of arrhythmia. These models show relatively high performance in supervised learning, but are not applicable in cases with few training examples. This is because abnormal ECG data is scarce compared to normal data in most real-world clinical settings. Therefore, in this study, GAN-based anomaly detec-tion, i.e., unsupervised learning, was employed to address the issue of data imbalance. This paper focuses on detecting abnormal signals in electrocardi-ograms (ECGs) using only labels from normal signals as training data. In-spired by self-supervised vision transformers, which learn by dividing images into patches, and masked auto-encoders, known for their effectiveness in patch reconstruction and solving information redundancy, we introduce the ECG Heartbeat Anomaly Detection model, EB-GAME. EB-GAME was trained and validated on the MIT-BIH Arrhythmia Dataset, where it achieved state-of-the-art performance on this benchmark.

Antiferromagnets have attracted significant attention in the field of magnonics, as promising candidates for ultralow-energy carriers for information transfer for future computing. The role of crystalline orientation distribution on magnon transport has received very little attention. In multiferroics such as BiFeO$_3$ the coupling between antiferromagnetic and polar order imposes yet another boundary condition on spin transport. Thus, understanding the fundamentals of spin transport in such systems requires a single domain, a single crystal. We show that through Lanthanum(La) substitution, a single ferroelectric domain can be engineered with a stable, single-variant spin cycloid, controllable by an electric field. The spin transport in such a single domain displays a strong anisotropy, arising from the underlying spin cycloid lattice. Our work shows a pathway to understand the fundamental origins of spin transport in such a single domain multiferroic., Comment: 15 pages, 9 figure