Search

Recent advancements in Large Language Models (LLMs) have the potential to transform financial analytics by integrating numerical and textual data. However, challenges such as insufficient context when fusing multimodal information and the difficulty in measuring the utility of qualitative outputs, which LLMs generate as text, have limited their effectiveness in tasks such as financial forecasting. This study addresses these challenges by leveraging daily reports from securities firms to create high-quality contextual information. The reports are segmented into text-based key factors and combined with numerical data, such as price information, to form context sets. By dynamically updating few-shot examples based on the query time, the sets incorporate the latest information, forming a highly relevant set closely aligned with the query point. Additionally, a crafted prompt is designed to assign scores to the key factors, converting qualitative insights into quantitative results. The derived scores undergo a scaling process, transforming them into real-world values that are used for prediction. Our experiments demonstrate that LLMs outperform time-series models in market forecasting, though challenges such as imperfect reproducibility and limited explainability remain., Comment: 7 pages, 4 figures

LLM-as-a-Judge and reward models are widely used alternatives of multiple-choice questions or human annotators for large language model (LLM) evaluation. Their efficacy shines in evaluating long-form responses, serving a critical role as evaluators of leaderboards and as proxies to align LLMs via reinforcement learning. However, despite their popularity, their effectiveness in diverse contexts, such as non-English prompts, factual verification, or challenging questions, remains unexplored. In this paper, we conduct a comprehensive analysis of automated evaluators, reporting several key findings on their behavior. First, we discover that English evaluation capabilities significantly influence language-specific evaluation capabilities, often more than the language proficiency itself, enabling evaluators trained in English to easily transfer their skills to other languages. Second, we identify critical shortcomings, where LLMs fail to detect and penalize errors, such as factual inaccuracies, cultural misrepresentations, and the presence of unwanted language. Finally, we find that state-of-the-art evaluators struggle with challenging prompts, in either English or Korean, underscoring their limitations in assessing or generating complex reasoning questions. We release the dataset and codes used., Comment: under review

The rapid advancements in deep learning necessitate better training methods for deep neural networks (DNNs). As models grow in complexity, vanishing and exploding gradients impede performance. We propose Z-Score Normalization for Gradient Descent (ZNorm), an innovative technique that adjusts only the gradients to accelerate training and improve model performance. ZNorm normalizes the overall gradients, providing consistent gradient scaling across layers, thereby reducing the risks of vanishing and exploding gradients, having better performances. Our extensive experiments on CIFAR-10 and medical datasets demonstrate that ZNorm enhances performance metrics. ZNorm consistently outperforms existing methods, achieving superior results using the same experimental settings. In medical imaging applications, ZNorm improves tumor prediction and segmentation performances, underscoring its practical utility. These findings highlight ZNorm's potential as a robust and versatile tool for enhancing the training speed and effectiveness of deep neural networks across a wide range of architectures and applications.

A binary decision task, like yes-no questions or answer verification, reflects a significant real-world scenario such as where users look for confirmation about the correctness of their decisions on specific issues. In this work, we observe that language models exhibit a negative bias in the binary decisions of complex reasoning tasks. Based on our observations and the rationale about attention-based model dynamics, we propose a negative attention score (NAS) to systematically and quantitatively formulate negative bias. Based on NAS, we identify attention heads that attend to negative tokens provided in the instructions as answer candidate of binary decisions, regardless of the question in the prompt, and validate their association with the negative bias. Additionally, we propose the negative attention score alignment (NASA) method, which is a parameter-efficient fine-tuning technique to address the extracted negatively biased attention heads. Experimental results from various domains of reasoning tasks and large model search space demonstrate that NASA significantly reduces the gap between precision and recall caused by negative bias while preserving their generalization abilities. Our codes are available at \url{https://github.com/ysw1021/NASA}.

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

Given an edge-incomplete graph, how can we accurately find the missing links? The link prediction in edge-incomplete graphs aims to discover the missing relations between entities when their relationships are represented as a graph. Edge-incomplete graphs are prevalent in real-world due to practical limitations, such as not checking all users when adding friends in a social network. Addressing the problem is crucial for various tasks, including recommending friends in social networks and finding references in citation networks. However, previous approaches rely heavily on the given edge-incomplete (observed) graph, making it challenging to consider the missing (unobserved) links during training. In this paper, we propose PULL (PU-Learning-based Link predictor), an accurate link prediction method based on the positive-unlabeled (PU) learning. PULL treats the observed edges in the training graph as positive examples, and the unconnected node pairs as unlabeled ones. PULL effectively prevents the link predictor from overfitting to the observed graph by proposing latent variables for every edge, and leveraging the expected graph structure with respect to the variables. Extensive experiments on five real-world datasets show that PULL consistently outperforms the baselines for predicting links in edge-incomplete graphs., Comment: 11 pages

Materials potentially hosting Kitaev spin-liquid states are considered crucial for realizing topological quantum computing. However, the intricate nature of spin interactions within these materials complicates the precise measurement of low-energy spin excitations indicative of fractionalized excitations. Using Na$_{2}$Co$_2$TeO$_{6}$ as an example, we study these low-energy spin excitations using the time-resolved resonant elastic x-ray scattering (tr-REXS). Our observations unveil remarkably slow spin dynamics at the magnetic peak, whose recovery timescale is several nanoseconds. This timescale aligns with the extrapolated spin gap of $\sim$ 1 $\mu$eV, obtained by density matrix renormalization group (DMRG) simulations in the thermodynamic limit. The consistency demonstrates the efficacy of tr-REXS in discerning low-energy spin gaps inaccessible to conventional spectroscopic techniques., Comment: 9 pages, 6 figures

Training and validating models for semantic segmentation require datasets with pixel-wise annotations, which are notoriously labor-intensive. Although useful priors such as foundation models or crowdsourced datasets are available, they are error-prone. We hence propose an effective framework of active label correction (ALC) based on a design of correction query to rectify pseudo labels of pixels, which in turn is more annotator-friendly than the standard one inquiring to classify a pixel directly according to our theoretical analysis and user study. Specifically, leveraging foundation models providing useful zero-shot predictions on pseudo labels and superpixels, our method comprises two key techniques: (i) an annotator-friendly design of correction query with the pseudo labels, and (ii) an acquisition function looking ahead label expansions based on the superpixels. Experimental results on PASCAL, Cityscapes, and Kvasir-SEG datasets demonstrate the effectiveness of our ALC framework, outperforming prior methods for active semantic segmentation and label correction. Notably, utilizing our method, we obtained a revised dataset of PASCAL by rectifying errors in 2.6 million pixels in PASCAL dataset.

Defects in wide bandgap semiconductors have recently emerged as promising candidates for solid-state quantum optical technologies. Electrical excitation of emitters may pave the way to scalable on-chip devices, and therefore is highly sought after. However, most wide band gap materials are not amenable to efficient doping, which in turn poses challenges on efficient electrical excitation and on-chip integration. Here, we demonstrate for the first time room temperature electroluminescence from isolated colour centres in hexagonal boron nitride (hBN). We harness the van der Waals (vdW) structure of two-dimensional materials, and engineer nanoscale devices comprised of graphene - hBN - graphene tunnel junctions. Under an applied bias, charge carriers are injected into hBN, and result in a localised light emission from the hBN colour centres. Remarkably, our devices operate at room temperature and produce robust, narrowband emission spanning a wide spectral range - from the visible to the near infrared. Our work marks an important milestone in van der Waals materials and their promising attributes for integrated quantum technologies and on-chip photonic circuits., Comment: 16 pages, 4 figures

This paper proposes a new active learning method for semantic segmentation. The core of our method lies in a new annotation query design. It samples informative local image regions (e.g., superpixels), and for each of such regions, asks an oracle for a multi-hot vector indicating all classes existing in the region. This multi-class labeling strategy is substantially more efficient than existing ones like segmentation, polygon, and even dominant class labeling in terms of annotation time per click. However, it introduces the class ambiguity issue in training as it assigns partial labels (i.e., a set of candidate classes) to individual pixels. We thus propose a new algorithm for learning semantic segmentation while disambiguating the partial labels in two stages. In the first stage, it trains a segmentation model directly with the partial labels through two new loss functions motivated by partial label learning and multiple instance learning. In the second stage, it disambiguates the partial labels by generating pixel-wise pseudo labels, which are used for supervised learning of the model. Equipped with a new acquisition function dedicated to the multi-class labeling, our method outperforms previous work on Cityscapes and PASCAL VOC 2012 while spending less annotation cost. Our code and results are available at https://github.com/sehyun03/MulActSeg., Comment: NeurIPS 2023 accepted

We define the mulati-parameter maximal function $\mathcal{M}$ as $$ \mathcal{M} f(x)=\sup _{0

We propose a self-supervised learning method for long text documents based on contrastive learning. A key to our method is Shuffle and Divide (SaD), a simple text augmentation algorithm that sets up a pretext task required for contrastive updates to BERT-based document embedding. SaD splits a document into two sub-documents containing randomly shuffled words in the entire documents. The sub-documents are considered positive examples, leaving all other documents in the corpus as negatives. After SaD, we repeat the contrastive update and clustering phases until convergence. It is naturally a time-consuming, cumbersome task to label text documents, and our method can help alleviate human efforts, which are most expensive resources in AI. We have empirically evaluated our method by performing unsupervised text classification on the 20 Newsgroups, Reuters-21578, BBC, and BBCSport datasets. In particular, our method pushes the current state-of-the-art, SS-SB-MT, on 20 Newsgroups by 20.94% in accuracy. We also achieve the state-of-the-art performance on Reuters-21578 and exceptionally-high accuracy performances (over 95%) for unsupervised classification on the BBC and BBCSport datasets., Comment: Accepted at ICPR 2022

The recent advances in representation learning inspire us to take on the challenging problem of unsupervised image classification tasks in a principled way. We propose ContraCluster, an unsupervised image classification method that combines clustering with the power of contrastive self-supervised learning. ContraCluster consists of three stages: (1) contrastive self-supervised pre-training (CPT), (2) contrastive prototype sampling (CPS), and (3) prototype-based semi-supervised fine-tuning (PB-SFT). CPS can select highly accurate, categorically prototypical images in an embedding space learned by contrastive learning. We use sampled prototypes as noisy labeled data to perform semi-supervised fine-tuning (PB-SFT), leveraging small prototypes and large unlabeled data to further enhance the accuracy. We demonstrate empirically that ContraCluster achieves new state-of-the-art results for standard benchmark datasets including CIFAR-10, STL-10, and ImageNet-10. For example, ContraCluster achieves about 90.8% accuracy for CIFAR-10, which outperforms DAC (52.2%), IIC (61.7%), and SCAN (87.6%) by a large margin. Without any labels, ContraCluster can achieve a 90.8% accuracy that is comparable to 95.8% by the best supervised counterpart., Comment: Accepted at ICPR 2022

If S is a smooth compact surface in $\mathbb{R}^{3}$ with strictly positive second fundamental form, and $E_S$ is the corresponding extension operator, then we prove that for all $p > 3$, $\left\|E_S f\right\|_{L^p\left(\mathbb{R}^3\right)} \leq C(p, S)\|f\|_{L^{\infty}(S)}.$ The proof of restriction conjecture in $\mathbb{R}^{3}$ implies that Kakeya set conjecture is true when n=3., Comment: There is an error for Lemma 3.1. There should be more condition so I think I should withdraw this article and my paper. It is famous problem, so withdrawing is necessary

Learning semantic segmentation requires pixel-wise annotations, which can be time-consuming and expensive. To reduce the annotation cost, we propose a superpixel-based active learning (AL) framework, which collects a dominant label per superpixel instead. To be specific, it consists of adaptive superpixel and sieving mechanisms, fully dedicated to AL. At each round of AL, we adaptively merge neighboring pixels of similar learned features into superpixels. We then query a selected subset of these superpixels using an acquisition function assuming no uniform superpixel size. This approach is more efficient than existing methods, which rely only on innate features such as RGB color and assume uniform superpixel sizes. Obtaining a dominant label per superpixel drastically reduces annotators' burden as it requires fewer clicks. However, it inevitably introduces noisy annotations due to mismatches between superpixel and ground truth segmentation. To address this issue, we further devise a sieving mechanism that identifies and excludes potentially noisy annotations from learning. Our experiments on both Cityscapes and PASCAL VOC datasets demonstrate the efficacy of adaptive superpixel and sieving mechanisms.

Linear discriminant analysis (LDA) is a typical method for classification problems with large dimensions and small samples. There are various types of LDA methods that are based on the different types of estimators for the covariance matrices and mean vectors. In this paper, we consider shrinkage methods based on a non-parametric approach. For the precision matrix, methods based on the sparsity structure or data splitting are examined. Regarding the estimation of mean vectors, Non-parametric Empirical Bayes (NPEB) methods and Non-parametric Maximum Likelihood Estimation (NPMLE) methods, also known as f-modeling and g-modeling, respectively, are adopted. The performance of linear discriminant rules based on combined estimation strategies of the covariance matrix and mean vectors are analyzed in this study. Particularly, the study presents a theoretical result on the performance of the NPEB method and compares it with previous studies. Simulation studies with various covariance matrices and mean vector structures are conducted to evaluate the methods discussed in this paper. Furthermore, real data examples such as gene expressions and EEG data are also presented, Comment: 43 pages, 2 figures

Understanding the interplay between charge, nematic, and structural ordering tendencies in cuprate superconductors is critical to unraveling their complex phase diagram. Using pump-probe time-resolved resonant x-ray scattering on the (0 0 1) Bragg peak at the Cu $L_3$ and O $K$ resonances, we investigate non-equilibrium dynamics of $Q_a = Q_b = 0$ nematic order and its association with both charge density wave (CDW) order and lattice dynamics in La$_{1.65}$Eu$_{0.2}$Sr$_{0.15}$CuO$_4$. The orbital selectivity of the resonant x-ray scattering cross-section allows nematicity dynamics associated with the planar O 2$p$ and Cu 3$d$ states to be distinguished from the response of anisotropic lattice distortions. A direct time-domain comparison of CDW translational-symmetry breaking and nematic rotational-symmetry breaking reveals that these broken symmetries remain closely linked in the photoexcited state, consistent with the stability of CDW topological defects in the investigated pump fluence regime., Comment: 19 pages, 5 figures

We obtain a necessary and sufficient condition on a polynomial $P(t_1,t_2)$ for the $\ell^{p}$ boundedness of the discrete double Hilbert transforms associated with $P(t)$ for $1 < p < \infty$. The proof is based on the multi-parameter circle method treating the cases of $|t_1|\not\approx |t_2|$ arising from $1/t_1$ and $1/t_2$.

How can we accurately recommend actions for users to control their devices at home? Action recommendation for smart home has attracted increasing attention due to its potential impact on the markets of virtual assistants and Internet of Things (IoT). However, designing an effective action recommender system for smart home is challenging because it requires handling context correlations, considering both queried contexts and previous histories of users, and dealing with capricious intentions in history. In this work, we propose SmartSense, an accurate action recommendation method for smart home. For individual action, SmartSense summarizes its device control and its temporal contexts in a self-attentive manner, to reflect the importance of the correlation between them. SmartSense then summarizes sequences of users considering queried contexts in a query-attentive manner to extract the query-related patterns from the sequential actions. SmartSense also transfers the commonsense knowledge from routine data to better handle intentions in action sequences. As a result, SmartSense addresses all three main challenges of action recommendation for smart home, and achieves the state-of-the-art performance giving up to 9.8% higher mAP@1 than the best competitor., Comment: 10 pages, 8 figures, Accepted to CIKM 2022

Advances in neuroimaging techniques have provided us novel insights into understanding how the human mind works. Functional magnetic resonance imaging (fMRI) is the most popular and widely used neuroimaging technique, and there is growing interest in fMRI-based markers of individual differences. However, its utility is often limited due to its high cost and difficulty acquiring from specific populations, including children and infants. Surrogate markers, or neural correlates of fMRI markers, would have important practical implications, but we have few stand-alone predictors for the fMRI markers. Here, using machine learning (ML) models and data augmentation, we predicted well-validated fMRI markers of human cognition from multivariate patterns of functional near-infrared spectroscopy (fNIRS), a portable and relatively inexpensive optical neuroimaging technique. We recruited 50 human participants who performed two cognitive tasks (stop signal task and probabilistic reversal learning task), while neural activation was measured with either fNIRS or fMRI at each of the total two visits. Using ML models and data augmentation, we could predict the well-established fMRI markers of response inhibition or prediction error signals from 48-channel fNIRS activation in the prefrontal cortex. These results suggest that fNIRS might offer a surrogate marker of fMRI activation, which would broaden our understanding of various populations, including infants., Comment: NeurIPS 2020 Workshop on BabyMind