Search

The increasing complexity of deep learning models necessitates specialized hardware and software optimizations, particularly for deep learning accelerators. Existing autotuning methods often suffer from prolonged tuning times due to profiling invalid configurations, which can cause runtime errors. We introduce ML$^2$Tuner, a multi-level machine learning tuning technique that enhances autotuning efficiency by incorporating a validity prediction model to filter out invalid configurations and an advanced performance prediction model utilizing hidden features from the compilation process. Experimental results on an extended VTA accelerator demonstrate that ML$^2$Tuner achieves equivalent performance improvements using only 12.3% of the samples required with a similar approach as TVM and reduces invalid profiling attempts by an average of 60.8%, Highlighting its potential to enhance autotuning performance by filtering out invalid configurations, Comment: Accepted in NeurIPS 2024 workshop on Machine Learning for Systems, 12 pages, 5 figures

In 2009, Calegari constructed smooth homotopy 4-spheres from monodromies of fibered knots. We prove that all these are diffeomorphic to the standard 4-sphere. Our method uses 5-dimensional handlebody techniques and results on mapping class groups of 3-dimensional handlebodies. As an application, we present potential counterexamples to the smooth 4-dimensional Schoenflies conjecture which are related to the work of Casson and Gordon on fibered ribbon knots., Comment: 9 pages

We carried out a project involving the systematic analysis of microlensing data from the Korea Microlensing Telescope Network survey. The aim of this project is to identify lensing events with complex anomaly features that are difficult to explain using standard binary-lens or binary-source models. Our investigation reveals that the light curves of microlensing events KMT-2021-BLG-0284, KMT-2022-BLG-2480, and KMT-2024-BLG-0412 display highly complex patterns with three or more anomaly features. These features cannot be adequately explained by a binary-lens (2L1S) model alone. However, the 2L1S model can effectively describe certain segments of the light curve. By incorporating an additional source into the modeling, we identified a comprehensive model that accounts for all the observed anomaly features. Bayesian analysis, based on constraints provided by lensing observables, indicates that the lenses of KMT-2021-BLG-0284 and KMT-2024-BLG-0412 are binary systems composed of M dwarfs. For KMT-2022-BLG-2480, the primary lens is an early K-type main-sequence star with an M dwarf companion. The lenses of KMT-2021-BLG-0284 and KMT-2024-BLG-0412 are likely located in the bulge, whereas the lens of KMT-2022-BLG-2480 is more likely situated in the disk. In all events, the binary stars of the sources have similar magnitudes due to a detection bias favoring binary source events with a relatively bright secondary source star, which increases detection efficiency., Comment: 9 pages, 9 figures

The recent discovery of an axial amplitude (Higgs) mode in the long-studied charge density wave (CDW) systems GdTe$_3$ and LaTe$_3$ suggests a heretofore unidentified hidden order. A theoretical study proposed that the axial Higgs results from a hidden ferroaxial component of the CDW, which could arise from non-trivial orbital texture. Here, we report extensive experimental studies on ErTe$_3$ and HoTe$_3$ that possess a high-temperature CDW similar to other RTe$_3$ (R = rare earth), along with an additional low-temperature CDW with an orthogonal ordering vector. Combining Raman spectroscopy with large-angle convergent beam electron diffraction (LACBED), rotational anisotropy second-harmonic generation (RA-SHG), and muon-spin relaxation ($\mu$SR), we provide unambiguous evidence that the high-temperature CDW breaks translation, rotation, and all vertical and diagonal mirror symmetries, but not time-reversal or inversion. In contrast, the low-temperature CDW only additionally breaks translation symmetry. Simultaneously, Raman scattering shows the high-temperature CDW produces an axial Higgs mode while the low-temperature mode is scalar. The weak monoclinic structural distortion and clear axial response in Raman and SHG are consistent with a ferroaxial phase in RTe$_3$ driven by coupled orbital and charge orders. Thus, our study provides a new standard for uncovering unconventional orders and confirms the power of Higgs modes to reveal them., Comment: 28 pages, 5 figures

In this work, we investigate a method for simulation-free training of Neural Ordinary Differential Equations (NODEs) for learning deterministic mappings between paired data. Despite the analogy of NODEs as continuous-depth residual networks, their application in typical supervised learning tasks has not been popular, mainly due to the large number of function evaluations required by ODE solvers and numerical instability in gradient estimation. To alleviate this problem, we employ the flow matching framework for simulation-free training of NODEs, which directly regresses the parameterized dynamics function to a predefined target velocity field. Contrary to generative tasks, however, we show that applying flow matching directly between paired data can often lead to an ill-defined flow that breaks the coupling of the data pairs (e.g., due to crossing trajectories). We propose a simple extension that applies flow matching in the embedding space of data pairs, where the embeddings are learned jointly with the dynamic function to ensure the validity of the flow which is also easier to learn. We demonstrate the effectiveness of our method on both regression and classification tasks, where our method outperforms existing NODEs with a significantly lower number of function evaluations. The code is available at https://github.com/seminkim/simulation-free-node.

The dynamic control of novel states of matter beyond thermodynamic equilibrium is a fundamental pursuit in condensed matter physics. Intense terahertz fields have enabled metal-insulator transitions, superconductivity, quantum paraelectric ferroelectricity, and room-temperature magnetization via circularly polarized terahertz electric fields. These effects hinge on the excitation of infrared-active soft phonon modes by terahertz fields. Expanding this concept, recent theory suggests that ferroelectric polarization may be manipulated through terahertz twisted light, transferring orbital angular momentum to create ferroelectric skyrmions. Our study experimentally demonstrates that such control is possible in quasi-2D ferroelectric CsBiNb2O7 using twisted UV light with orbital angular momentum (OAM). By resonantly exciting both the ferroelectric mode and the octahedral tilting mode, twisted UV light dynamically modulates the ferroelectric polarization. We employ in-situ X-ray Bragg coherent diffractive imaging, twisted optical Raman spectroscopy, and density functional theory to three-dimensionally resolve ionic displacement fields and polarization texture changes. Our observations reveal deterministic, reversible twisted light-induced strain and ionic displacements within the unit cell, causing substantial microscopic polarization changes. This interaction between twisted photons, phonon modes, and induced ionic displacements breaks symmetry and stabilizes a non-equilibrium ferroelectric phase with topological solitons. These findings offer a new path to control ferroelectricity and magnetism, opening avenues for novel optoelectronic devices such as ultrafast non-volatile memory switches by using light to coherently control ferroic states., Comment: 14 pages, 5 figures

Traditional weak-lensing mass reconstruction techniques suffer from various artifacts, including noise amplification and the mass-sheet degeneracy. In Hong et al. (2021), we demonstrated that many of these pitfalls of traditional mass reconstruction can be mitigated using a deep learning approach based on a convolutional neural network (CNN). In this paper, we present our improvements and report on the detailed performance of our CNN algorithm applied to next-generation wide-field observations. Assuming the field of view ($3\deg.5 \times 3\deg.5$) and depth (27 mag at $5\sigma$) of the Vera C. Rubin Observatory, we generated training datasets of mock shear catalogs with a source density of 33 arcmin$^{-2}$ from cosmological simulation ray-tracing data. We find that the current CNN method provides high-fidelity reconstructions consistent with the true convergence field, restoring both small and large-scale structures. In addition, the cluster detection utilizing our CNN reconstruction achieves $\sim75$% completeness down to $\sim 10^{14}M_{\odot}$. We anticipate that this CNN-based mass reconstruction will be a powerful tool in the Rubin era, enabling fast and robust wide-field mass reconstructions on a routine basis., Comment: 11 pages, 8 figures, submitted to ApJ

We study the problem of conditional two-sample testing, which aims to determine whether two populations have the same distribution after accounting for confounding factors. This problem commonly arises in various applications, such as domain adaptation and algorithmic fairness, where comparing two groups is essential while controlling for confounding variables. We begin by establishing a hardness result for conditional two-sample testing, demonstrating that no valid test can have significant power against any single alternative without proper assumptions. We then introduce two general frameworks that implicitly or explicitly target specific classes of distributions for their validity and power. Our first framework allows us to convert any conditional independence test into a conditional two-sample test in a black-box manner, while preserving the asymptotic properties of the original conditional independence test. The second framework transforms the problem into comparing marginal distributions with estimated density ratios, which allows us to leverage existing methods for marginal two-sample testing. We demonstrate this idea in a concrete manner with classification and kernel-based methods. Finally, simulation studies are conducted to illustrate the proposed frameworks in finite-sample scenarios., Comment: 39 pages, 6 figures

Transformers often struggle with length generalization, meaning they fail to generalize to sequences longer than those encountered during training. While arithmetic tasks are commonly used to study length generalization, certain tasks are considered notoriously difficult, e.g., multi-operand addition (requiring generalization over both the number of operands and their lengths) and multiplication (requiring generalization over both operand lengths). In this work, we achieve approximately 2-3x length generalization on both tasks, which is the first such achievement in arithmetic Transformers. We design task-specific scratchpads enabling the model to focus on a fixed number of tokens per each next-token prediction step, and apply multi-level versions of Position Coupling (Cho et al., 2024; McLeish et al., 2024) to let Transformers know the right position to attend to. On the theory side, we prove that a 1-layer Transformer using our method can solve multi-operand addition, up to operand length and operand count that are exponential in embedding dimension., Comment: 38 pages, 16 figures

Two-dimensional (2D) kagome lattice metals are interesting because they display flat electronic bands, Dirac points, Van Hove singularities, and can have interplay between charge density wave (CDW), magnetic order, and superconductivity. In kagome lattice antiferromagnet FeGe, a short-range CDW order was found deep within an antiferromagnetically ordered state, interacting with the magnetic order. Surprisingly, post-growth annealing of FeGe at 560$^{\circ}$C can suppress the CDW order while annealing at 320$^{\circ}$C induces a long-range CDW order, with the ability to cycle between the states repeatedly by annealing. Here we perform transport, neutron scattering, scanning transmission electron microscopy (STEM), and muon spin rotation ($\mu$SR) experiments to unveil the microscopic mechanism of the annealing process and its impact on magneto-transport, CDW, and magnetic properties of FeGe. We find that 560$^{\circ}$C annealing creates germanium vacancies uniformly distributed throughout the FeGe kagome lattice, which prevent the formation of Ge-Ge dimers necessary for the CDW order. Upon annealing at 320$^{\circ}$C, the system segregates into stoichiometric FeGe regions with long-range CDW order and regions with stacking faults that act as nucleation sites for the CDW. The presence or absence of CDW order greatly affects the anomalous Hall effect, incommensurate magnetic order, and spin-lattice coupling in FeGe, thus placing FeGe as the only known kagome lattice material with a tunable CDW and magnetic order, potentially useful for sensing and information transmission.

Mongolia is among the countries undergoing rapid urbanization, and its temporary nomadic dwellings-known as Ger-have expanded into urban areas. Ger settlements in cities are increasingly recognized as slums by their socio-economic deprivation. The distinctive circular, tent-like shape of gers enables their detection through very-high-resolution satellite imagery. We develop a computer vision algorithm to detect gers in Ulaanbaatar, the capital of Mongolia, utilizing satellite images collected from 2015 to 2023. Results reveal that ger settlements have been displaced towards the capital's peripheral areas. The predicted slum ratio based on our results exhibits a significant correlation (r = 0.84) with the World Bank's district-level poverty data. Our nationwide extrapolation suggests that slums may continue to take up one-fifth of the population after the COVID-19 pandemic, contrary to other official predictions that anticipated a decline. We discuss the potential of machine learning on satellite imagery in providing insights into urbanization patterns and monitoring the Sustainable Development Goals., Comment: 20 pages

Despite advancements in Large Language Model (LLM) alignment, understanding the reasons behind LLM preferences remains crucial for bridging the gap between desired and actual behavior. LLMs often exhibit biases or tendencies that diverge from human preferences, such as favoring certain writing styles or producing overly verbose outputs. However, current methods for evaluating preference alignment often lack explainability, relying on coarse-grained comparisons. To address this, we introduce PROFILE (PRObing Factors of InfLuence for Explainability), a novel framework that uncovers and quantifies the influence of specific factors driving preferences. PROFILE's factor level analysis explains the 'why' behind human-model alignment and misalignment, offering insights into the direction of model improvement. We apply PROFILE to analyze human and LLM preferences across three tasks: summarization, helpful response generation, and document-based question-answering. Our factor level analysis reveals a substantial discrepancy between human and LLM preferences in generation tasks, whereas LLMs show strong alignment with human preferences in evaluation tasks. We demonstrate how leveraging factor level insights, including addressing misaligned factors or exploiting the generation-evaluation gap, can improve alignment with human preferences. This work underscores the importance of explainable preference analysis and highlights PROFILE's potential to provide valuable training signals, driving further improvements in human-model alignment.

3D object detection with omnidirectional views enables safety-critical applications such as mobile robot navigation. Such applications increasingly operate on resource-constrained edge devices, facilitating reliable processing without privacy concerns or network delays. To enable cost-effective deployment, cameras have been widely adopted as a low-cost alternative to LiDAR sensors. However, the compute-intensive workload to achieve high performance of camera-based solutions remains challenging due to the computational limitations of edge devices. In this paper, we present Panopticus, a carefully designed system for omnidirectional and camera-based 3D detection on edge devices. Panopticus employs an adaptive multi-branch detection scheme that accounts for spatial complexities. To optimize the accuracy within latency limits, Panopticus dynamically adjusts the model's architecture and operations based on available edge resources and spatial characteristics. We implemented Panopticus on three edge devices and conducted experiments across real-world environments based on the public self-driving dataset and our mobile 360{\deg} camera dataset. Experiment results showed that Panopticus improves accuracy by 62% on average given the strict latency objective of 33ms. Also, Panopticus achieves a 2.1{\times} latency reduction on average compared to baselines., Comment: Published at MobiCom 2024

Reconstructing past events requires reasoning across long time horizons. To figure out what happened, we need to use our prior knowledge about the world and human behavior and draw inferences from various sources of evidence including visual, language, and auditory cues. We introduce MARPLE, a benchmark for evaluating long-horizon inference capabilities using multi-modal evidence. Our benchmark features agents interacting with simulated households, supporting vision, language, and auditory stimuli, as well as procedurally generated environments and agent behaviors. Inspired by classic ``whodunit'' stories, we ask AI models and human participants to infer which agent caused a change in the environment based on a step-by-step replay of what actually happened. The goal is to correctly identify the culprit as early as possible. Our findings show that human participants outperform both traditional Monte Carlo simulation methods and an LLM baseline (GPT-4) on this task. Compared to humans, traditional inference models are less robust and performant, while GPT-4 has difficulty comprehending environmental changes. We analyze what factors influence inference performance and ablate different modes of evidence, finding that all modes are valuable for performance. Overall, our experiments demonstrate that the long-horizon, multimodal inference tasks in our benchmark present a challenge to current models., Comment: NeurIPS 2024. First two authors contributed equally. Project page: https://marple-benchmark.github.io/

This report describes our 1st place solution to the 8th HANDS workshop challenge (ARCTIC track) in conjunction with ECCV 2024. In this challenge, we address the task of bimanual category-agnostic hand-object interaction reconstruction, which aims to generate 3D reconstructions of both hands and the object from a monocular video, without relying on predefined templates. This task is particularly challenging due to the significant occlusion and dynamic contact between the hands and the object during bimanual manipulation. We worked to resolve these issues by introducing a mask loss and a 3D contact loss, respectively. Moreover, we applied 3D Gaussian Splatting (3DGS) to this task. As a result, our method achieved a value of 38.69 in the main metric, CD$_h$, on the ARCTIC test set.

The Josephson diode effect (JDE), characterized by a unidirectional supercurrent across a Josephson junction, arises from non-reciprocal critical currents typically controlled by magnetic fields. In this study, we demonstrate JDE controlled by local electric fields, achieving complete polarity reversal through gate voltages on epitaxial Al-InAs Josephson junctions. Our observations reveal intricate effects of in-plane magnetic fields and gate voltages on the JDE. We develop a theoretical model that considers the coherent interplay between finite Cooper-pair momentum (fCPM) and anisotropic spin-orbit coupling (SOC), identifying that fCPM dominates JDE at low in-plane magnetic fields, while SOC governs its polarity reversal at high fields. This model aligns well with experimental data, illustrating precise electric control of JDE polarity through anisotropic SOC. These findings introduce a novel approach to controlling superconducting circuits, paving a route toward advanced applications in superconducting quantum devices., Comment: 42 pages, 19 figures, 1 table

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.

In this work, we show the pre-trained language models return distinguishable generation probability and uncertainty distribution to unfaithfully hallucinated texts, regardless of their size and structure. By examining 24 models on 6 data sets, we find out that 88-98% of cases return statistically significantly distinguishable generation probability and uncertainty distributions. Using this general phenomenon, we showcase a hallucination-reducing training algorithm. Our algorithm outperforms other baselines by achieving higher faithfulness metrics while maintaining sound general text quality measures., Comment: 10 pages, EMNLP 2024 Findings

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

The prominence of generalized foundation models in vision-language integration has witnessed a surge, given their multifarious applications. Within the natural domain, the procurement of vision-language datasets to construct these foundation models is facilitated by their abundant availability and the ease of web crawling. Conversely, in the remote sensing domain, although vision-language datasets exist, their volume is suboptimal for constructing robust foundation models. This study introduces an approach to curate vision-language datasets by employing an image decoding machine learning model, negating the need for human-annotated labels. Utilizing this methodology, we amassed approximately 9.6 million vision-language paired datasets in VHR imagery. The resultant model outperformed counterparts that did not leverage publicly available vision-language datasets, particularly in downstream tasks such as zero-shot classification, semantic localization, and image-text retrieval. Moreover, in tasks exclusively employing vision encoders, such as linear probing and k-NN classification, our model demonstrated superior efficacy compared to those relying on domain-specific vision-language datasets., Comment: This study was primarily conducted during the latter half of 2023

Drawing parallels between human cognition and artificial intelligence, we explored how large language models (LLMs) internalize identities imposed by targeted prompts. Informed by Social Identity Theory, these identity assignments lead LLMs to distinguish between "we" (the ingroup) and "they" (the outgroup). This self-categorization generates both ingroup favoritism and outgroup bias. Nonetheless, existing literature has predominantly focused on ingroup favoritism, often overlooking outgroup bias, which is a fundamental source of intergroup prejudice and discrimination. Our experiment addresses this gap by demonstrating that outgroup bias manifests as strongly as ingroup favoritism. Furthermore, we successfully mitigated the inherent pro-liberal, anti-conservative bias in LLMs by guiding them to adopt the perspectives of the initially disfavored group. These results were replicated in the context of gender bias. Our findings highlight the potential to develop more equitable and balanced language models., Comment: 23 pages, 5 figures

Older adults are increasingly acquiring smartphones. But acquiring smartphones can be difficult, and little is known about the particular challenges of older adults who are additionally blind or losing their vision. We shed light on the social and technical aspects of acquiring smartphones with vision loss, based on deep qualitative interviews with 22 blind or low vision (BLV) older adults aged 60 and over. Through our grounded theory analysis, we found that BLV older adults experience liminality as they acquire smartphones and transition through re-acquiring smartphones as they become blind, and they can transition through liminality by participating in mutual aid within the blind community. We contribute the notion of "Intersecting Liminality," which explains the marginalizing experience of simultaneously transitioning through vision loss, aging, and technology acquisition. We contend that Intersecting Liminality can serve as a framework that centers the dynamic nature of disability to help our community generate a more nuanced understanding of technology acquisition and more effective assistive interventions., Comment: 14 pages, 2 figures, 2 tables, conference paper accepted to The 26th International ACM SIGACCESS Conference on Computers and Accessibility (ASSETS 2024)

Social problems stemming from the shortage of radiologists are intensifying, and artificial intelligence is being highlighted as a potential solution. Recently emerging large-scale generative AI has expanded from large language models (LLMs) to multi-modal models, showing potential to revolutionize the entire process of medical imaging. However, comprehensive reviews on their development status and future challenges are currently lacking. This scoping review systematically organizes existing literature on the clinical value of large-scale generative AI applications by following PCC guidelines. A systematic search was conducted across four databases: PubMed, EMbase, IEEE-Xplore, and Google Scholar, and 15 studies meeting the inclusion/exclusion criteria set by the researchers were reviewed. Most of these studies focused on improving the efficiency of report generation in specific parts of the interpretation process or on translating reports to aid patient understanding, with the latest studies extending to AI applications performing direct interpretations. All studies were quantitatively evaluated by clinicians, with most utilizing LLMs and only three employing multi-modal models. Both LLMs and multi-modal models showed excellent results in specific areas, but none yet outperformed radiologists in diagnostic performance. Most studies utilized GPT, with few using models specialized for the medical imaging domain. This study provides insights into the current state and limitations of large-scale generative AI-based applications in the medical imaging field, offering foundational data and suggesting that the era of medical imaging foundation models is on the horizon, which may fundamentally transform clinical practice in the near future., Comment: 25 pages,3 figures, 4 tables, submitted to NPJ imaging

Building on previous works to construct a homogeneous sample of brown dwarfs in binary systems, we investigate microlensing events detected by the Korea Microlensing Telescope Network (KMTNet) survey during the 2022 and 2023 seasons. Given the difficulty in distinguishing brown-dwarf events from those produced by binary lenses with nearly equal-mass components, we analyze all lensing events detected during the seasons that exhibit anomalies characteristic of binary-lens systems. Using the same criteria consistently applied in previous studies, we identify six additional brown dwarf candidates through the analysis of lensing events KMT-2022-BLG-0412, KMT-2022-BLG-2286, KMT-2023-BLG-0201, KMT-2023-BLG-0601, KMT-2023-BLG-1684, and KMT-2023-BLG-1743. An examination of the mass posteriors shows that the median mass of the lens companions ranges from 0.02 $M_\odot$ to 0.05 $M_\odot$, indicating that these companions fall within the brown-dwarf mass range. The mass of the primary lenses ranges from 0.11 $M_\odot$ to 0.68 $M_\odot$, indicating that they are low-mass stars with substantially lower masses compared to the Sun., Comment: 13 pages, 17 figures, 12 tables

In most of charge density wave (CDW) systems of different material classes, ranging from traditional correlated systems in low-dimension to recent topological systems with Kagome lattice, superconductivity emerges when the system is driven toward the quantum critical point (QCP) of CDW via external parameters of doping and pressure. Despite this rather universal trend, the essential hinge between CDW and superconductivity has not been established yet. Here, the evidence of coupling between electron and CDW fluctuation is reported, based on a temperature- and intercalation-dependent kink in the angle-resolved photoemission spectra of 2H-PdxTaSe2. Kinks are observed only when the system is in the CDW phase, regardless of whether a long- or short-range order is established. Notably, the coupling strength is enhanced upon long-range CDW suppression, albeit the coupling energy scale is reduced. Interestingly, estimation of the superconducting critical temperature by incorporating the observed coupling characteristics into McMillan's equation yields result closely resembling the known values of the superconducting dome. Our results thus highlight a compelling possibility that this new coupling mediates Cooper pairs, which provides new insights on the competing relationship not only for CDW, but also for other competing orders., Comment: 20 pages, 4 figures for the main text. To be published in Advanced Science

The explosive arrival of OpenAI's ChatGPT has fueled the globalization of large language model (LLM), which consists of billions of pretrained parameters that embodies the aspects of syntax and semantics. HyperAccel introduces latency processing unit (LPU), a latency-optimized and highly scalable processor architecture for the acceleration of LLM inference. LPU perfectly balances the memory bandwidth and compute logic with streamlined dataflow to maximize performance and efficiency. LPU is equipped with expandable synchronization link (ESL) that hides data synchronization latency between multiple LPUs. HyperDex complements LPU as an intuitive software framework to run LLM applications. LPU achieves 1.25 ms/token and 20.9 ms/token for 1.3B and 66B model, respectively, which is 2.09x and 1.37x faster than the GPU. LPU, synthesized using Samsung 4nm process, has total area of 0.824 mm2 and power consumption of 284.31 mW. LPU-based servers achieve 1.33x and 1.32x energy efficiency over NVIDIA H100 and L4 servers, respectively.

Large Language Models (LLMs) have demonstrated strong reasoning and memorization capabilities via pretraining on massive textual corpora. However, this poses risk of privacy and copyright violations, highlighting the need for efficient machine unlearning methods that remove sensitive data without retraining from scratch. While Gradient Ascent (GA) is commonly used to unlearn by reducing the likelihood of generating unwanted content, it leads to unstable optimization and catastrophic forgetting of retrained knowledge. We also find that combining GA with low-rank adaptation results in poor trade-offs between computational cost and generative performance. To address these challenges, we propose two novel techniques for robust and efficient unlearning for LLMs. First, we introduce Inverted Hinge loss, which suppresses unwanted tokens while maintaining fluency by boosting the probability of the next most likely token. Second, we develop a data-adaptive initialization for LoRA adapters via low-rank approximation weighted with relative Fisher information, thereby focusing updates on parameters critical for removing targeted knowledge. Experiments on the Training Data Extraction Challenge dataset using GPT-Neo models as well as on the TOFU benchmark with Phi-1.5B and Llama2-7B models demonstrate that our approach effectively removes sensitive information while maintaining reasoning and generative capabilities with minimal impact., Comment: Preprint

Ventilated acoustic resonator(VAR), a type of acoustic metamaterial, emerge as an alternative for sound attenuation in environments that require ventilation, owing to its excellent low-frequency attenuation performance and flexible shape adaptability. However, due to the non-linear acoustic responses of VARs, the VAR designs are generally obtained within a limited parametrized design space, and the design relies on the iteration of the numerical simulation which consumes a considerable amount of computational time and resources. This paper proposes an acoustic response-encoded variational autoencoder (AR-VAE), a novel variational autoencoder-based generative design model for the efficient and accurate inverse design of VAR even with non-parametrized designs. The AR-VAE matches the high-dimensional acoustic response with the VAR cross-section image in the dimension-reduced latent space, which enables the AR-VAE to generate various non-parametrized VAR cross-section images with the target acoustic response. AR-VAE generates non-parameterized VARs from target acoustic responses, which show a 25-fold reduction in mean squared error compared to conventional deep learning-based parameter searching methods while exhibiting lower average mean squared error and peak frequency variance. By combining the inverse-designed VARs by AR-VAE, multi-cavity VAR was devised for broadband and multitarget peak frequency attenuation. The proposed design method presents a new approach for structural inverse-design with a high-dimensional non-linear physical response.

The spin-orbit assisted Mott insulator $\alpha$-RuCl3 is proximate to the coveted quantum spin liquid (QSL) predicted by the Kitaev model. In the search for the pure Kitaev QSL, reducing the dimensionality of this frustrated magnet by exfoliation has been proposed as a way to enhance magnetic fluctuations and Kitaev interactions. Here, we perform angle-dependent tunneling magnetoresistance (TMR) measurements on ultrathin $\alpha$-RuCl3 crystals with various layer numbers to probe their magnetic, electronic and crystal structure. We observe a giant change in resistance - as large as ~2500% - when the magnetic field rotates either within or out of the $\alpha$-RuCl3 plane, a manifestation of the strongly anisotropic spin interactions in this material. In combination with scanning transmission electron microscopy, this tunneling anisotropic magnetoresistance (TAMR) reveals that few-layer $\alpha$-RuCl3 crystals remain in the high-temperature monoclinic phase at low temperature. It also shows the presence of a zigzag antiferromagnetic order below the critical temperature TN ~ 14 K, which is twice the one typically observed in bulk samples with rhombohedral stacking. Our work offers valuable insights into the relation between the stacking order and magnetic properties of this material, which helps lay the groundwork for creating and electrically probing exotic magnetic phases like QSLs via van der Waals engineering.

Recent advancements in 3D object detection have benefited from multi-modal information from the multi-view cameras and LiDAR sensors. However, the inherent disparities between the modalities pose substantial challenges. We observe that existing multi-modal 3D object detection methods heavily rely on the LiDAR sensor, treating the camera as an auxiliary modality for augmenting semantic details. This often leads to not only underutilization of camera data but also significant performance degradation in scenarios where LiDAR data is unavailable. Additionally, existing fusion methods overlook the detrimental impact of sensor noise induced by environmental changes, on detection performance. In this paper, we propose MEFormer to address the LiDAR over-reliance problem by harnessing critical information for 3D object detection from every available modality while concurrently safeguarding against corrupted signals during the fusion process. Specifically, we introduce Modality Agnostic Decoding (MOAD) that extracts geometric and semantic features with a shared transformer decoder regardless of input modalities and provides promising improvement with a single modality as well as multi-modality. Additionally, our Proximity-based Modality Ensemble (PME) module adaptively utilizes the strengths of each modality depending on the environment while mitigating the effects of a noisy sensor. Our MEFormer achieves state-of-the-art performance of 73.9% NDS and 71.5% mAP in the nuScenes validation set. Extensive analyses validate that our MEFormer improves robustness against challenging conditions such as sensor malfunctions or environmental changes. The source code is available at https://github.com/hanchaa/MEFormer

We investigate microlensing data collected by the Korea Microlensing Telescope Network (KMTNet) survey. Our investigation reveals that the light curves of two lensing events, KMT-2021-BLG-2609 and KMT-2022-BLG-0303, exhibit a similar anomaly, in which short-term positive deviations appear on the sides of the low-magnification lensing light curves. To unravel the nature of these anomalies, we meticulously analyze each of the lensing events. Our investigations reveal that these anomalies stem from a shared channel, wherein the source passed near the planetary caustic induced by a planet with projected separations from the host star exceeding the Einstein radius. We find that interpreting the anomaly of KMT-2021-BLG-2609 is complicated by the "inner--outer" degeneracy, whereas for KMT-2022-BLG-0303, there is no such issue despite similar lens-system configurations. In addition to this degeneracy, interpreting the anomaly in KMT-2021-BLG-2609 involves an additional degeneracy between a pair of solutions, in which the source partially envelops the caustic and the other three solutions in which the source fully envelopes the caustic. As in an earlier case of this so-called von Schlieffen--Cannae degeneracy, the former solutions have substantially higher mass ratio. Through Bayesian analyses conducted based on the measured lensing observables of the event time scale and angular Einstein radius, the host of KMT-2021-BLG-2609L is determined to be a low-mass star with a mass $\sim 0.2~M_\odot$ in terms of a median posterior value, while the planet's mass ranges from approximately 0.032 to 0.112 times that of Jupiter, depending on the solutions. For the planetary system KMT-2022-BLG-0303L, it features a planet with a mass of approximately $0.51~M_{\rm J}$ and a host star with a mass of about $0.37~M_\odot$. In both cases, the lenses are most likely situated in the bulge., Comment: 10 pages, 11 figures, 6 tables

This paper presents a novel approach for reconstructing dynamic radiance fields from monocular videos. We integrate kinematics with dynamic radiance fields, bridging the gap between the sparse nature of monocular videos and the real-world physics. Our method introduces the kinematic field, capturing motion through kinematic quantities: velocity, acceleration, and jerk. The kinematic field is jointly learned with the dynamic radiance field by minimizing the photometric loss without motion ground truth. We further augment our method with physics-driven regularizers grounded in kinematics. We propose physics-driven regularizers that ensure the physical validity of predicted kinematic quantities, including advective acceleration and jerk. Additionally, we control the motion trajectory based on rigidity equations formed with the predicted kinematic quantities. In experiments, our method outperforms the state-of-the-arts by capturing physical motion patterns within challenging real-world monocular videos., Comment: ECCV 2024

In the pursuit of understanding the population of stellar remnants within the Milky Way, we analyze the sample of $\sim 950$ microlensing events observed by the Spitzer Space Telescope between 2014 and 2019. In this study we focus on a sub-sample of nine microlensing events, selected based on their long timescales, small microlensing parallaxes and joint observations by the Gaia mission, to increase the probability that the chosen lenses are massive and the mass is measurable. Among the selected events we identify lensing black holes and neutron star candidates, with potential confirmation through forthcoming release of the Gaia time-series astrometry in 2026. Utilizing Bayesian analysis and Galactic models, along with the Gaia Data Release 3 proper motion data, four good candidates for dark remnants were identified: OGLE-2016-BLG-0293, OGLE-2018-BLG-0483, OGLE-2018-BLG-0662, and OGLE-2015-BLG-0149, with lens masses of $2.98^{+1.75}_{-1.28}~M_{\odot}$, $4.65^{+3.12}_{-2.08}~M_{\odot}$, $3.15^{+0.66}_{-0.64}~M_{\odot}$ and $1.4^{+0.75}_{-0.55}~M_{\odot}$, respectively. Notably, the first two candidates are expected to exhibit astrometric microlensing signals detectable by Gaia, offering the prospect of validating the lens masses. The methodologies developed in this work will be applied to the full Spitzer microlensing sample, populating and analyzing the time-scale ($t_{\rm E}$) vs. parallax ($\pi_{\rm E}$) diagram to derive constraints on the population of lenses in general and massive remnants in particular., Comment: submitted to ApJ

The Moving Sofa Problem, formally proposed by Leo Moser in 1966, seeks to determine the largest area of a two-dimensional shape that can navigate through an $L$-shaped corridor with unit width. The current best lower bound is about 2.2195, achieved by Joseph Gerver in 1992, though its global optimality remains unproven. In this paper, we investigate this problem by leveraging the universal approximation strength and computational efficiency of neural networks. We report two approaches, both supporting Gerver's conjecture that his shape is the unique global maximum. Our first approach is continuous function learning. We drop Gerver's assumptions that i) the rotation of the corridor is monotonic and symmetric and, ii) the trajectory of its corner as a function of rotation is continuously differentiable. We parameterize rotation and trajectory by independent piecewise linear neural networks (with input being some pseudo time), allowing for rich movements such as backward rotation and pure translation. We then compute the sofa area as a differentiable function of rotation and trajectory using our "waterfall" algorithm. Our final loss function includes differential terms and initial conditions, leveraging the principles of physics-informed machine learning. Under such settings, extensive training starting from diverse function initialization and hyperparameters is conducted, unexceptionally showing rapid convergence to Gerver's solution. Our second approach is via discrete optimization of the Kallus-Romik upper bound, which converges to the maximum sofa area from above as the number of rotation angles increases. We uplift this number to 10000 to reveal its asymptotic behavior. It turns out that the upper bound yielded by our models does converge to Gerver's area (within an error of 0.01% when the number of angles reaches 2100). We also improve their five-angle upper bound from 2.37 to 2.3337., Comment: 16 pages, 9 figures

Two-dimensional electrides can acquire topologically non-trivial phases due to intriguing interplay between the cationic atomic layers and anionic electron layers. However, experimental evidence of topological surface states has yet to be verified. Here, via angle-resolved photoemission spectroscopy (ARPES) and scanning tunnelling microscopy (STM), we probe the magnetic Weyl states of the ferromagnetic electride $[Gd_{2}$C]^{2+}\cdot2e^{-}$. In particular, the presence of Weyl cones and Fermi-arc states is demonstrated through photon energy-dependent ARPES measurements, agreeing with theoretical band structure calculations. Notably, the STM measurements reveal that the Fermi-arc states exist underneath a floating quantum electron liquid on the top Gd layer, forming double-stacked surface states in a heterostructure. Our work thus not only unveils the non-trivial topology of the $[Gd_{2}$C]^{2+}\cdot2e^{-}$ electride but also realizes a surface heterostructure that can host phenomena distinct from the bulk., Comment: 22 pages, 6 figures

English as a Foreign Language (EFL) students often struggle to deliver oral presentations due to a lack of reliable resources and the limited effectiveness of instructors' feedback. Large Language Model (LLM) can offer new possibilities to assist students' oral presentations with real-time feedback. This paper investigates how ChatGPT can be effectively integrated into EFL oral presentation practice to provide personalized feedback. We introduce a novel learning platform, CHOP (ChatGPT-based interactive platform for oral presentation practice), and evaluate its effectiveness with 13 EFL students. By collecting student-ChatGPT interaction data and expert assessments of the feedback quality, we identify the platform's strengths and weaknesses. We also analyze learners' perceptions and key design factors. Based on these insights, we suggest further development opportunities and design improvements for the education community.

Two-dimensional (2D) materials serve as exceptional platforms for controlled second harmonic generation (SHG), an important nonlinear optical phenomenon with diverse applications. Current approaches to SHG control often depend on non-resonant conditions or symmetry breaking via single-gate control. Here, we employ dual-gate bilayer WSe2 to demonstrate a new SHG enhancement concept that leverages strong exciton resonance and layer-dependent exciton-polaron effect. By selectively localizing injected holes within one layer, we induce exciton-polaron states in the hole-filled layer while maintaining normal exciton states in the charge-neutral layer. The distinct resonant conditions of these layers effectively break interlayer inversion symmetry, thereby promoting resonant SHG. Our method achieves a remarkable 40-fold enhancement of SHG at minimal electric field, equivalent to conditions near the dielectric-breakdown threshold but using only ~3% of the critical breakdown field. Our findings also reveal significant sensitivity of resonant SHG to carrier density and carrier type, with distinct enhancement and quenching observed across different gating regimes. This advancement offers an innovative approach to manipulating SHG in 2D excitonic materials and provides a potent spectroscopic tool for probing layer-dependent quantum states.

Electronic Health Records (EHRs) are integral for storing comprehensive patient medical records, combining structured data (e.g., medications) with detailed clinical notes (e.g., physician notes). These elements are essential for straightforward data retrieval and provide deep, contextual insights into patient care. However, they often suffer from discrepancies due to unintuitive EHR system designs and human errors, posing serious risks to patient safety. To address this, we developed EHRCon, a new dataset and task specifically designed to ensure data consistency between structured tables and unstructured notes in EHRs. EHRCon was crafted in collaboration with healthcare professionals using the MIMIC-III EHR dataset, and includes manual annotations of 3,943 entities across 105 clinical notes checked against database entries for consistency. EHRCon has two versions, one using the original MIMIC-III schema, and another using the OMOP CDM schema, in order to increase its applicability and generalizability. Furthermore, leveraging the capabilities of large language models, we introduce CheckEHR, a novel framework for verifying the consistency between clinical notes and database tables. CheckEHR utilizes an eight-stage process and shows promising results in both few-shot and zero-shot settings. The code is available at https://github.com/dustn1259/EHRCon.

The spread of fake news negatively impacts individuals and is regarded as a significant social challenge that needs to be addressed. A number of algorithmic and insightful features have been identified for detecting fake news. However, with the recent LLMs and their advanced generation capabilities, many of the detectable features (e.g., style-conversion attacks) can be altered, making it more challenging to distinguish from real news. This study proposes adversarial style augmentation, AdStyle, to train a fake news detector that remains robust against various style-conversion attacks. Our model's key mechanism is the careful use of LLMs to automatically generate a diverse yet coherent range of style-conversion attack prompts. This improves the generation of prompts that are particularly difficult for the detector to handle. Experiments show that our augmentation strategy improves robustness and detection performance when tested on fake news benchmark datasets., Comment: 8 pages

We investigated the nature of the anomalies appearing in four microlensing events KMT-2020-BLG-0757, KMT-2022-BLG-0732, KMT-2022-BLG-1787, and KMT-2022-BLG-1852. The light curves of these events commonly exhibit initial bumps followed by subsequent troughs that extend across a substantial portion of the light curves. We performed thorough modeling of the anomalies to elucidate their characteristics. Despite their prolonged durations, which differ from the usual brief anomalies observed in typical planetary events, our analysis revealed that each anomaly in these events originated from a planetary companion located within the Einstein ring of the primary star. It was found that the initial bump arouse when the source star crossed one of the planetary caustics, while the subsequent trough feature occurred as the source traversed the region of minor image perturbations lying between the pair of planetary caustics. The estimated masses of the host and planet, their mass ratios, and the distance to the discovered planetary systems are $(M_{\rm host}/M_\odot, M_{\rm planet}/M_{\rm J}, q/10^{-3}, \dl/{\rm kpc}) = (0.58^{+0.33}_{-0.30}, 10.71^{+6.17}_{-5.61}, 17.61\pm 2.25,6.67^{+0.93}_{-1.30})$ for KMT-2020-BLG-0757, $(0.53^{+0.31}_{-0.31}, 1.12^{+0.65}_{-0.65}, 2.01 \pm 0.07, 6.66^{+1.19}_{-1.84})$ for KMT-2022-BLG-0732, $(0.42^{+0.32}_{-0.23}, 6.64^{+4.98}_{-3.64}, 15.07\pm 0.86, 7.55^{+0.89}_{-1.30})$ for KMT-2022-BLG-1787, and $(0.32^{+0.34}_{-0.19}, 4.98^{+5.42}_{-2.94}, 8.74\pm 0.49, 6.27^{+0.90}_{-1.15})$ for KMT-2022-BLG-1852. These parameters indicate that all the planets are giants with masses exceeding the mass of Jupiter in our solar system and the hosts are low-mass stars with masses substantially less massive than the Sun., Comment: 10 pages, 12 figures, 7 tables

Moving beyond traditional surveys, combining heterogeneous data sources with AI-driven inference models brings new opportunities to measure socio-economic conditions, such as poverty and population, over expansive geographic areas. The current research presents GeoSEE, a method that can estimate various socio-economic indicators using a unified pipeline powered by a large language model (LLM). Presented with a diverse set of information modules, including those pre-constructed from satellite imagery, GeoSEE selects which modules to use in estimation, for each indicator and country. This selection is guided by the LLM's prior socio-geographic knowledge, which functions similarly to the insights of a domain expert. The system then computes target indicators via in-context learning after aggregating results from selected modules in the format of natural language-based texts. Comprehensive evaluation across countries at various stages of development reveals that our method outperforms other predictive models in both unsupervised and low-shot contexts. This reliable performance under data-scarce setting in under-developed or developing countries, combined with its cost-effectiveness, underscores its potential to continuously support and monitor the progress of Sustainable Development Goals, such as poverty alleviation and equitable growth, on a global scale.

The increasing frequency and intensity of natural disasters demand more sophisticated approaches for rapid and precise damage assessment. To tackle this issue, researchers have developed various methods on disaster benchmark datasets from satellite imagery to aid in detecting disaster damage. However, the diverse nature of geographical landscapes and disasters makes it challenging to apply existing methods to regions unseen during training. We present DAVI (Disaster Assessment with VIsion foundation model), which overcomes domain disparities and detects structural damage (e.g., building) without requiring ground-truth labels of the target region. DAVI integrates task-specific knowledge from a model trained on source regions with an image segmentation foundation model to generate pseudo labels of possible damage in the target region. It then employs a two-stage refinement process, targeting both the pixel and overall image, to more accurately pinpoint changes in disaster-struck areas based on before-and-after images. Comprehensive evaluations demonstrate that DAVI achieves exceptional performance across diverse terrains (e.g., USA and Mexico) and disaster types (e.g., wildfires, hurricanes, and earthquakes). This confirms its robustness in assessing disaster impact without dependence on ground-truth labels., Comment: 9 pages, 4 figures, 2 tables

The significance of mass spectrometry lies in its unparalleled ability to accurately identify and quantify molecules in complex samples, providing invaluable insights into molecular structures and interactions. Here, we leverage diamond nanostructures as highly sensitive mass sensors by utilizing a self-excitation mechanism under an electron beam in a conventional scanning electron microscope (SEM). The diamond molecular balance (DMB) exhibits an exceptional mass resolution of 0.36 MDa, based on its outstanding mechanical quality factor and frequency stability, along with an extensive dynamic range from MDa to TDa. This positions the DMB at the forefront of molecular balances operating at room temperature. Notably, the DMB demonstrates its ability to measure the mass of a single bacteriophage T4 by precisely locating the analyte on the device. These findings highlight the groundbreaking potential of the DMB as a revolutionary tool for mass spectrometry at room temperature., Comment: 16 pages, 4 figures

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