Search

This paper argues that a dataset's legal risk cannot be accurately assessed by its license terms alone; instead, tracking dataset redistribution and its full lifecycle is essential. However, this process is too complex for legal experts to handle manually at scale. Tracking dataset provenance, verifying redistribution rights, and assessing evolving legal risks across multiple stages require a level of precision and efficiency that exceeds human capabilities. Addressing this challenge effectively demands AI agents that can systematically trace dataset redistribution, analyze compliance, and identify legal risks. We develop an automated data compliance system called NEXUS and show that AI can perform these tasks with higher accuracy, efficiency, and cost-effectiveness than human experts. Our massive legal analysis of 17,429 unique entities and 8,072 license terms using this approach reveals the discrepancies in legal rights between the original datasets before redistribution and their redistributed subsets, underscoring the necessity of the data lifecycle-aware compliance. For instance, we find that out of 2,852 datasets with commercially viable individual license terms, only 605 (21%) are legally permissible for commercialization. This work sets a new standard for AI data governance, advocating for a framework that systematically examines the entire lifecycle of dataset redistribution to ensure transparent, legal, and responsible dataset management.

Electrical control of quantum magnetic states is essential in spintronic science. Initial studies on the ferromagnetic state control were extended to collinear antiferromagnets and, more recently, noncollinear antiferromagnets. However, electrical control mechanisms of such exotic magnetic states remain poorly understood. Here, we report the first experimental and theoretical example of the current control of helical antiferromagnets, arising from the competition between collinear antiferromagnetic exchange and interlayer Dzyaloshinskii-Moriya interaction in new van-der-Waals (vdW) material Ni1/3NbS2. Due to the intrinsic broken inversion symmetry, an in-plane current generates spin-orbit torque that, in turn, interacts directly with the helical antiferromagnetic order. Our theoretical analyses indicate that a weak ferromagnetic order coexists due to the Dzyaloshinskii-Moriya interaction, mediating the spin-orbit torque to collectively rotate the helical antiferromagnetic order. Our Ni1/3NbS2 nanodevice experiments produce current-dependent resistance change consistent with the theoretical prediction. This work widens our understanding of the electrical control of helical antiferromagnets and promotes vdW quantum magnets as interesting material platforms for electrical control., Comment: Accepted by Physical Review Letters; 41 pages, 4 main figures, 12 supporting figures

Self-awareness, i.e., the ability to assess and correct one's own generation, is a fundamental aspect of human intelligence, making its replication in large language models (LLMs) an important yet challenging task. Previous works tackle this by employing extensive reinforcement learning or rather relying on large external verifiers. In this work, we propose Refine via Intrinsic Self-Verification (ReVISE), an efficient and effective framework that enables LLMs to self-correct their outputs through self-verification. The core idea of ReVISE is to enable LLMs to verify their reasoning processes and continually rethink reasoning trajectories based on its verification. We introduce a structured curriculum based upon online preference learning to implement this efficiently. Specifically, as ReVISE involves two challenging tasks (i.e., self-verification and reasoning correction), we tackle each task sequentially using curriculum learning, collecting both failed and successful reasoning paths to construct preference pairs for efficient training. During inference, our approach enjoys natural test-time scaling by integrating self-verification and correction capabilities, further enhanced by our proposed confidence-aware decoding mechanism. Our experiments on various reasoning tasks demonstrate that ReVISE achieves efficient self-correction and significantly improves reasoning performance.

Next token prediction has been the standard training objective used in large language model pretraining. Representations are learned as a result of optimizing for token-level perplexity. We propose Continuous Concept Mixing (CoCoMix), a novel pretraining framework that combines discrete next token prediction with continuous concepts. Specifically, CoCoMix predicts continuous concepts learned from a pretrained sparse autoencoder and mixes them into the model's hidden state by interleaving with token hidden representations. Through experiments on multiple benchmarks, including language modeling and downstream reasoning tasks, we show that CoCoMix is more sample efficient and consistently outperforms standard next token prediction, knowledge distillation and inserting pause tokens. We find that combining both concept learning and interleaving in an end-to-end framework is critical to performance gains. Furthermore, CoCoMix enhances interpretability and steerability by allowing direct inspection and modification of the predicted concept, offering a transparent way to guide the model's internal reasoning process.

In this paper, we consider people counting and localization systems exploiting channel state information (CSI) measured from commodity WiFi network interface cards (NICs). While CSI has useful information of amplitude and phase to describe signal propagation in a measurement environment of interest, CSI measurement suffers from offsets due to various uncertainties. Moreover, an uncontrollable external environment where other WiFi devices communicate each other induces interfering signals, resulting in erroneous CSI captured at a receiver. In this paper, preprocessing of CSI is first proposed for offset removal, and it guarantees low-latency operation without any filtering process. Afterwards, we design people counting and localization models based on pre-training. To be adaptive to different measurement environments, meta-learning-based people counting and localization models are also proposed. Numerical results show that the proposed meta-learning-based people counting and localization models can achieve high sensing accuracy, compared to other learning schemes that follow simple training and test procedures., Comment: 13 pages, 15 figures, submitted to IEEE Internet of Things Journal (IoTJ)

In social networks, people influence each other through social links, which can be represented as propagation among nodes in graphs. Influence minimization (IMIN) is the problem of manipulating the structures of an input graph (e.g., removing edges) to reduce the propagation among nodes. IMIN can represent time-critical real-world applications, such as rumor blocking, but IMIN is theoretically difficult and computationally expensive. Moreover, the discrete nature of IMIN hinders the usage of powerful machine learning techniques, which requires differentiable computation. In this work, we propose DiffIM, a novel method for IMIN with two differentiable schemes for acceleration: (1) surrogate modeling for efficient influence estimation, which avoids time-consuming simulations (e.g., Monte Carlo), and (2) the continuous relaxation of decisions, which avoids the evaluation of individual discrete decisions (e.g., removing an edge). We further propose a third accelerating scheme, gradient-driven selection, that chooses edges instantly based on gradients without optimization (spec., gradient descent iterations) on each test instance. Through extensive experiments on real-world graphs, we show that each proposed scheme significantly improves speed with little (or even no) IMIN performance degradation. Our method is Pareto-optimal (i.e., no baseline is faster and more effective than it) and typically several orders of magnitude (spec., up to 15,160X) faster than the most effective baseline while being more effective., Comment: Accepted to AAAI'25

Listing k-cliques plays a fundamental role in various data mining tasks, such as community detection and mining of cohesive substructures. Existing algorithms for the k-clique listing problem are built upon a general framework, which finds k-cliques by recursively finding (k-1)-cliques within subgraphs induced by the out-neighbors of each vertex. However, this framework has inherent inefficiency of finding smaller cliques within certain subgraphs repeatedly. In this paper, we propose an algorithm DIST for the k-clique listing problem. In contrast to existing works, the main idea in our approach is to compute each clique in the given graph only once and store it into a data structure called Induced Subgraph Trie, which allows us to retrieve the cliques efficiently. Furthermore, we propose a method to prune search space based on a novel concept called soft embedding of an l-tree, which further improves the running time. We show the superiority of our approach in terms of time and space usage through comprehensive experiments conducted on real-world networks; DIST outperforms the state-of-the-art algorithm by up to two orders of magnitude in both single-threaded and parallel experiments.

In MMORPGs (Massively Multiplayer Online Role-Playing Games), abnormal players (bots) using unauthorized automated programs to carry out pre-defined behaviors systematically and repeatedly are commonly observed. Bots usually engage in these activities to gain in-game money, which they eventually trade for real money outside the game. Such abusive activities negatively impact the in-game experiences of legitimate users since bots monopolize specific hunting areas and obtain valuable items. Thus, detecting abnormal players is a significant task for game companies. Motivated by the fact that bots tend to behave collectively with similar in-game trajectories due to the auto-programs, we developed BotTRep, a framework that comprises trajectory representation learning followed by clustering using a completely unlabeled in-game trajectory dataset. Our model aims to learn representations for in-game trajectory sequences so that players with contextually similar trajectories have closer embeddings. Then, by applying DBSCAN to these representations and visualizing the corresponding moving patterns, our framework ultimately assists game masters in identifying and banning bots.

The computation of collision probability ($\mathcal{P}_c$) is crucial for space environmentalism and sustainability by providing decision-making knowledge that can prevent collisions between anthropogenic space objects. However, the accuracy and precision of $\mathcal{P}_c$ computations is often compromised by limitations in computational resources and data availability. While significant improvements have been made in the computational aspects, the rising concerns regarding the privacy of collaborative data sharing can be a major limiting factor in the future conjunction analysis and risk assessment, especially as the space environment grows increasingly privatized, competitive, and fraught with conflicting strategic interests. This paper argues that the importance of privacy measures in space situational awareness (SSA) is underappreciated, and regulatory and compliance measures currently in place are not sufficient by themselves, presenting a significant gap. To address this gap, we introduce a novel encrypted architecture that leverages advanced cryptographic techniques, including homomorphic encryption (HE) and multi-party computation (MPC), to safeguard the privacy of entities computing space sustainability metrics, inter alia, $\mathcal{P}_c$. Our proposed protocol, Encrypted $\mathcal{P}_c$, integrates the Monte Carlo estimation algorithm with cryptographic solutions, enabling secure collision probability computation without exposing sensitive or proprietary information. This research advances secure conjunction analysis by developing a secure MPC protocol for $\mathcal{P}_c$ computation and highlights the need for innovative protocols to ensure a more secure and cooperative SSA landscape.

Recently, crossbar array based in-memory accelerators have been gaining interest due to their high throughput and energy efficiency. While software and compiler support for the in-memory accelerators has also been introduced, they are currently limited to the case where all weights are assumed to be on-chip. This limitation becomes apparent with the significantly increasing network sizes compared to the in-memory footprint. Weight replacement schemes are essential to address this issue. We propose COMPASS, a compiler framework for resource-constrained crossbar-based processing-in-memory (PIM) deep neural network (DNN) accelerators. COMPASS is specially targeted for networks that exceed the capacity of PIM crossbar arrays, necessitating access to external memories. We propose an algorithm to determine the optimal partitioning that divides the layers so that each partition can be accelerated on chip. Our scheme takes into account the data dependence between layers, core utilization, and the number of write instructions to minimize latency, memory accesses, and improve energy efficiency. Simulation results demonstrate that COMPASS can accommodate much more networks using a minimal memory footprint, while improving throughput by 1.78X and providing 1.28X savings in energy-delay product (EDP) over baseline partitioning methods., Comment: Accepted IEEE DATE 2025

Very long baseline interferometry (VLBI) enables high-angular-resolution observations in astronomy and geodesy by synthesizing a virtual telescope with baselines spanning hundreds to thousands of kilometres. Achieving high instrumental phase stability in VLBI relies on the generation of high-quality, atomic-referenced RF local oscillator (LO) and RF-comb signals for the effective downconversion of celestial RF signals and precise phase calibration, respectively. As observing frequencies move into higher ranges with wider bandwidth, conventional electronic methods face significant challenges in maintaining the quality of these signals. Here, we demonstrate that an optical frequency comb (OFC) can be used as a versatile tool to generate and distribute low-noise and atomic-referenced RF-comb and RF-LO signals in the VLBI telescope. Hydrogen maser-stabilized optical pulses are transmitted over a timing-stabilized fibre link from the observatory building to the VLBI receiver system at the telescope, where photodetection converts them into the required RF-comb and RF-LO signals. In VLBI test observation, we successfully detected VLBI fringes and extracted the RF-combs characteristics in a format suitable for VLBI instrumental phase calibration. These results highlight the high potential of OFC-based technology for enhancing next-generation broadband VLBI measurements, advancing astrophysical research and facilitating intercontinental clock comparison., Comment: 25 pages, 7 figures

Magnetization switching by charge current without a magnetic field is essential for device applications and information technology. It generally requires a current-induced out-of-plane spin polarization beyond the capability of conventional ferromagnet/heavy-metal systems, where the current-induced spin polarization aligns in-plane orthogonal to the in-plane charge current and out-of-plane spin current. Here, we demonstrate a new approach for magnetic-field-free switching by fabricating a van-der-Waals magnet and oxide Fe3GeTe2/SrTiO3 heterostructure. This new magnetic-field-free switching is possible because the current-driven accumulated spins at the Rashba interface precess around an emergent interface magnetism, eventually producing an ultimate out-of-plane spin polarization. This interpretation is further confirmed by the switching polarity change controlled by the in-plane initialization magnetic fields with clear hysteresis. We successfully combined van-der-Waals magnet and oxide for the first time, especially taking advantage of spin-orbit torque on the SrTiO3 oxide. This allows us to establish a new way of magnetic field-free switching. Our work demonstrates an unusual perpendicular switching application of large spin Hall angle materials and precession of accumulated spins, and in doing so, opens up a new field and opportunities for van-der-Waals magnets and oxide spintronics., Comment: Accepted by Advanced Materials (2025); 47 pages, 4 main figures, 16 supporting figures

The recent advent of Large Language Models (LLMs) has ushered sophisticated reasoning capabilities into the realm of video through Video Large Language Models (VideoLLMs). However, VideoLLMs currently rely on a single vision encoder for all of their visual processing, which limits the amount and type of visual information that can be conveyed to the LLM. Our method, MERV, Multi-Encoder Representation of Videos, instead leverages multiple frozen visual encoders to create a unified representation of a video, providing the VideoLLM with a comprehensive set of specialized visual knowledge. Spatio-temporally aligning the features from each encoder allows us to tackle a wider range of open-ended and multiple-choice video understanding questions and outperform prior state-of-the-art works. MERV is up to 3.7% better in accuracy than Video-LLaVA across the standard suite video understanding benchmarks, while also having a better Video-ChatGPT score. We also improve upon SeViLA, the previous best on zero-shot Perception Test accuracy, by 2.2%. MERV introduces minimal extra parameters and trains faster than equivalent single-encoder methods while parallelizing the visual processing. Finally, we provide qualitative evidence that MERV successfully captures domain knowledge from each of its encoders. Our results offer promising directions in utilizing multiple vision encoders for comprehensive video understanding., Comment: Project page: https://tylerzhu.com/merv/

This report explores the enhancement of text retrieval performance using advanced data refinement techniques. We develop Linq-Embed-Mistral\footnote{\url{https://huggingface.co/Linq-AI-Research/Linq-Embed-Mistral}} by building on the E5-mistral and Mistral-7B-v0.1 models, focusing on sophisticated data crafting, data filtering, and negative mining methods, which are highly tailored to each task, applied to both existing benchmark dataset and highly tailored synthetic dataset generated via large language models (LLMs). Linq-Embed-Mistral excels in the MTEB benchmarks (as of May 29, 2024), achieving an average score of 68.2 across 56 datasets, and ranks 1st among all models for retrieval tasks on the MTEB leaderboard with a performance score of 60.2. This performance underscores its superior capability in enhancing search precision and reliability. Our contributions include advanced data refinement methods that significantly improve model performance on benchmark and synthetic datasets, techniques for homogeneous task ordering and mixed task fine-tuning to enhance model generalization and stability, and a streamlined evaluation process using 4-bit precision and a light retrieval evaluation set, which accelerates validation without sacrificing accuracy., Comment: 15 pages

Sign language translation (SLT) is challenging, as it involves converting sign language videos into natural language. Previous studies have prioritized accuracy over diversity. However, diversity is crucial for handling lexical and syntactic ambiguities in machine translation, suggesting it could similarly benefit SLT. In this work, we propose DiffSLT, a novel gloss-free SLT framework that leverages a diffusion model, enabling diverse translations while preserving sign language semantics. DiffSLT transforms random noise into the target latent representation, conditioned on the visual features of input video. To enhance visual conditioning, we design Guidance Fusion Module, which fully utilizes the multi-level spatiotemporal information of the visual features. We also introduce DiffSLT-P, a DiffSLT variant that conditions on pseudo-glosses and visual features, providing key textual guidance and reducing the modality gap. As a result, DiffSLT and DiffSLT-P significantly improve diversity over previous gloss-free SLT methods and achieve state-of-the-art performance on two SLT datasets, thereby markedly improving translation quality., Comment: Project page: https://diffslt.github.io/

Traditional neural network-driven inpainting methods struggle to deliver high-quality results within the constraints of mobile device processing power and memory. Our research introduces an innovative approach to optimize memory usage by altering the composition of input data. Typically, video inpainting relies on a predetermined set of input frames, such as neighboring and reference frames, often limited to five-frame sets. Our focus is to examine how varying the proportion of these input frames impacts the quality of the inpainted video. By dynamically adjusting the input frame composition based on optical flow and changes of the mask, we have observed an improvement in various contents including rapid visual context changes.

This paper presents an approach to joint wireless and computing resource management in slice-enabled metaverse networks, addressing the challenges of inter-slice and intra-slice resource allocation in the presence of in-network computing. We formulate the problem as a mixed-integer nonlinear programming (MINLP) problem and derive an optimal solution using standard optimization techniques. Through extensive simulations, we demonstrate that our proposed method significantly improves system performance by effectively balancing the allocation of radio and computing resources across multiple slices. Our approach outperforms existing benchmarks, particularly in scenarios with high user demand and varying computational tasks.

Spatial control methods using additional modules on pretrained diffusion models have gained attention for enabling conditional generation in natural images. These methods guide the generation process with new conditions while leveraging the capabilities of large models. They could be beneficial as training strategies in the context of 3D medical imaging, where training a diffusion model from scratch is challenging due to high computational costs and data scarcity. However, the potential application of spatial control methods with additional modules to 3D medical images has not yet been explored. In this paper, we present a tailored spatial control method for 3D medical images with a novel lightweight module, Volumetric Conditioning Module (VCM). Our VCM employs an asymmetric U-Net architecture to effectively encode complex information from various levels of 3D conditions, providing detailed guidance in image synthesis. To examine the applicability of spatial control methods and the effectiveness of VCM for 3D medical data, we conduct experiments under single- and multimodal conditions scenarios across a wide range of dataset sizes, from extremely small datasets with 10 samples to large datasets with 500 samples. The experimental results show that the VCM is effective for conditional generation and efficient in terms of requiring less training data and computational resources. We further investigate the potential applications for our spatial control method through axial super-resolution for medical images. Our code is available at \url{https://github.com/Ahn-Ssu/VCM}, Comment: 17 pages, 18 figures, accepted @ WACV 2025

We study partial regularity for degenerate elliptic systems of double-phase type, where the growth function is given by $H(x,t)=t^p+a(x)t^q$ with $1

Large language models (LLMs) have recently gained much attention in building autonomous agents. However, the performance of current LLM-based web agents in long-horizon tasks is far from optimal, often yielding errors such as repeatedly buying a non-refundable flight ticket. By contrast, humans can avoid such an irreversible mistake, as we have an awareness of the potential outcomes (e.g., losing money) of our actions, also known as the "world model". Motivated by this, our study first starts with preliminary analyses, confirming the absence of world models in current LLMs (e.g., GPT-4o, Claude-3.5-Sonnet, etc.). Then, we present a World-model-augmented (WMA) web agent, which simulates the outcomes of its actions for better decision-making. To overcome the challenges in training LLMs as world models predicting next observations, such as repeated elements across observations and long HTML inputs, we propose a transition-focused observation abstraction, where the prediction objectives are free-form natural language descriptions exclusively highlighting important state differences between time steps. Experiments on WebArena and Mind2Web show that our world models improve agents' policy selection without training and demonstrate our agents' cost- and time-efficiency compared to recent tree-search-based agents., Comment: Work in progress

Despite significant advancements in automatic brain tumor segmentation methods, their performance is not guaranteed when certain MR sequences are missing. Addressing this issue, it is crucial to synthesize the missing MR images that reflect the unique characteristics of the absent modality with precise tumor representation. Typically, MRI synthesis methods generate partial images rather than full-sized volumes due to computational constraints. This limitation can lead to a lack of comprehensive 3D volumetric information and result in image artifacts during the merging process. In this paper, we propose a two-stage approach that first synthesizes MR images from 2D slices using a novel intensity encoding method and then refines the synthesized MRI. The proposed intensity encoding reduces artifacts when synthesizing MRI on a 2D slice basis. Then, the \textit{Refiner}, which leverages complete 3D volume information, further improves the quality of the synthesized images and enhances their applicability to segmentation methods. Experimental results demonstrate that the intensity encoding effectively minimizes artifacts in the synthesized MRI and improves perceptual quality. Furthermore, using the \textit{Refiner} on synthesized MRI significantly improves brain tumor segmentation results, highlighting the potential of our approach in practical applications., Comment: MICCAI 2024 BraSyn Challenge 1st place

We present an analytical model describing a stable shock-like structure that is formed when an ultra-intense laser propagates through an underdense plasma. It is shown that such structures exist in a wide range of laser-plasma parameters, with a unique sub-luminal shock front velocity for each parameter. Numerical methods to accurately describe such shock-front is developed. The formalism is applied to describe the parameter space in which the Carrier-Envelope-Phase (CEP) effect under which phase and polarization dependent super-ponderomotive effects becomes significant. The developed formalism will enable quick identification of regimes in which CEP effects become significant, expediting designing of Laser Wakefield Accelerators operating in the superponderomotive regime.

Achieving low duty cycle operation in low-power wireless networks in urban environments is complicated by the complex and variable dynamics of external interference and fading. We explore the use of reinforcement learning for achieving low power consumption for the task of optimal selection of channels. The learning relies on a hybrid of passive channel sampling for dealing with external interference and active channel sampling for dealing with fading. Our solution, Passive-Active Multi-armed bandit for LoRa (PAMLR, pronounced "Pamela"), balances the two types of samples to achieve energy-efficient channel selection: active channel measurements are tuned to an appropriately low level to update noise thresholds, and to compensate passive channel measurements are tuned to an appropriately high level for selecting the top-most channels from channel exploration using the noise thresholds. The rates of both types of samples are adapted in response to channel dynamics. Based on extensive testing in multiple environments in different cities, we validate that PAMLR can maintain excellent communication quality, as demonstrated by a low SNR regret compared to the optimal channel allocation policy, while substantially minimizing the energy cost associated with channel measurements., Comment: BuildSys 23

We introduce fractional weighted Sobolev spaces with degenerate weights. For these spaces we provide embeddings and Poincar\'e inequalities. When the order of fractional differentiability goes to $0$ or $1$, we recover the weighted Lebesgue and Sobolev spaces with Muckenhoupt weights, respectively. Moreover, we prove interior H\"older continuity and Harnack inequalities for solutions to the corresponding weighted nonlocal integro-differential equations. This naturally extends a classical result by Fabes, Kenig, and Serapioni to the nonlinear, nonlocal setting.

We relaxe the constraint on the domains of combinatorial HHS machinery so combinatorial HHS machinery works for most cubical curve graphs. As an application we extend the factor system machinery of the CAT(0) cube complex to the quasi-median graphs., Comment: 34 pages

This paper is devoted to studying the well-posedness, (conditional) conservation of magnetic helicity, inviscid limit and asymptotic stability of the generalized Navier-Stokes-Maxwell equations (NSM) under the Hall effect in two and three dimensions. More precisely, in the viscous case we prove the global well-posedness of NSM for small initial data, which allows us to establish a connection with either the Hall-magnetohydrodynamics (H-MHD) system as the speed of light tends to infinity or NSM without the Hall coefficient as this constant goes to zero. In addition, in the inviscid case the local well-posedness of NSM is also obtained for possibly large initial data. Moreover, under suitable conditions on the initial data and additional assumptions of solutions to NSM in three dimensions, the magnetic helicity is conserved as the electric conductivity goes to infinity. It is different to the case of the fractional H-MHD with critical fractional Laplacian exponents for both the velocity and magnetic fields, where the conservation of magnetic helicity can be provided for smooth initial data without any further conditions on the solution. Furthermore, the asymptotic stability of NSM around a constant magnetic field is established in the case of having a velocity damping term., Comment: arXiv admin note: text overlap with arXiv:2401.14839

Self-dual codes have been studied actively because they are connected with mathematical structures including block designs and lattices and have practical applications in quantum error-correcting codes and secret sharing schemes. Nevertheless, there has been less attention to construct self-dual codes from self-orthogonal codes with smaller dimensions. Hence, the main purpose of this paper is to propose a way to expand any self-orthogonal code over a ring $\Z_4$ to many self-dual codes over $\Z_4$. We show that all self-dual codes over $\Z_4$ of lengths $4$ to $8$ can be constructed this way. Furthermore, we have found five new self-dual codes over $\Z_4$ of lengths $27, 28, 29, 33,$ and $34$ with the highest Euclidean weight $12$. Moreover, using Construction $A$ applied to our new Euclidean-optimal self-dual codes over $\Z_4$, we have constructed a new odd extremal unimodular lattice in dimension 34 whose kissing number was not previously known.

Learning with a limited number of labeled data is a central problem in real-world applications of machine learning, as it is often expensive to obtain annotations. To deal with the scarcity of labeled data, transfer learning is a conventional approach; it suggests to learn a transferable knowledge by training a neural network from multiple other sources. In this paper, we investigate transfer learning of tabular tasks, which has been less studied and successful in the literature, compared to other domains, e.g., vision and language. This is because tables are inherently heterogeneous, i.e., they contain different columns and feature spaces, making transfer learning difficult. On the other hand, recent advances in natural language processing suggest that the label scarcity issue can be mitigated by utilizing in-context learning capability of large language models (LLMs). Inspired by this and the fact that LLMs can also process tables within a unified language space, we ask whether LLMs can be effective for tabular transfer learning, in particular, under the scenarios where the source and target datasets are of different format. As a positive answer, we propose a novel tabular transfer learning framework, coined Prompt to Transfer (P2T), that utilizes unlabeled (or heterogeneous) source data with LLMs. Specifically, P2T identifies a column feature in a source dataset that is strongly correlated with a target task feature to create examples relevant to the target task, thus creating pseudo-demonstrations for prompts. Experimental results demonstrate that P2T outperforms previous methods on various tabular learning benchmarks, showing good promise for the important, yet underexplored tabular transfer learning problem. Code is available at https://github.com/jaehyun513/P2T., Comment: COLM 2024

In recent years, there has been a significant focus on research related to text-guided image inpainting. However, the task remains challenging due to several constraints, such as ensuring alignment between the image and the text, and maintaining consistency in distribution between corrupted and uncorrupted regions. In this paper, thus, we propose a dual affine transformation generative adversarial network (DAFT-GAN) to maintain the semantic consistency for text-guided inpainting. DAFT-GAN integrates two affine transformation networks to combine text and image features gradually for each decoding block. Moreover, we minimize information leakage of uncorrupted features for fine-grained image generation by encoding corrupted and uncorrupted regions of the masked image separately. Our proposed model outperforms the existing GAN-based models in both qualitative and quantitative assessments with three benchmark datasets (MS-COCO, CUB, and Oxford) for text-guided image inpainting., Comment: ACM MM'2024. 9 pages, 3 tables, 9 figures

GroundBIRD is a ground-based cosmic microwave background (CMB) experiment for observing the polarization pattern imprinted on large angular scales ($\ell > 6$ ) from the Teide Observatory in Tenerife, Spain. Our primary scientific objective is a precise measurement of the optical depth $\tau$ ($\sigma(\tau) \sim 0.01$) to the reionization epoch of the Universe to cross-check systematic effects in the measurements made by previous experiments. GroundBIRD observes a wide sky area in the Northern Hemisphere ($\sim 40\%$ of the full sky) while continuously rotating the telescope at a high speed of up to 20 rotations per minute (rpm) to overcome the fluctuations of atmospheric radiation. We have adopted the NbTiN/Al hybrid microwave kinetic inductance detectors (MKIDs) as focal plane detectors. We observe two frequency bands centered at 145 GHz and 220 GHz. The 145 GHz band picks up the peak frequency of the CMB spectrum. The 220 GHz band helps accurate removal of the contamination of thermal emission from the Galactic interstellar dust. The MKID arrays (138 MKIDs for 145GHz and 23 MKIDs for 220GHz) were designed and optimized so as to minimize the contamination of the two-level-system noise and maximize the sensitivity. The MKID arrays were successfully installed in May 2023 after the performance verification tests were performed at a laboratory. GroundBIRD has been upgraded to use the full MKID arrays, and scientific observations are now underway. The telescope is automated, so that all observations are performed remotely. Initial validations, including polarization response tests and observations of Jupiter and the moon, have been completed successfully. We are now running scientific observations., Comment: Event: SPIE Astronomical Telescopes + Instrumentation, 2024, Yokohama, Japan; paper number 13102-7, Millimeter, Submillimeter, and Far-Infrared Detectors and Instrumentation for Astronomy XII

Deep learning-based segmentation techniques have shown remarkable performance in brain segmentation, yet their success hinges on the availability of extensive labeled training data. Acquiring such vast datasets, however, poses a significant challenge in many clinical applications. To address this issue, in this work, we propose a novel 3D brain segmentation approach using complementary 2D diffusion models. The core idea behind our approach is to first mine 2D features with semantic information extracted from the 2D diffusion models by taking orthogonal views as input, followed by fusing them into a 3D contextual feature representation. Then, we use these aggregated features to train multi-layer perceptrons to classify the segmentation labels. Our goal is to achieve reliable segmentation quality without requiring complete labels for each individual subject. Our experiments on training in brain subcortical structure segmentation with a dataset from only one subject demonstrate that our approach outperforms state-of-the-art self-supervised learning methods. Further experiments on the minimum requirement of annotation by sparse labeling yield promising results even with only nine slices and a labeled background region., Comment: Extended version of "3D Segmentation of Subcortical Brain Structure with Few Labeled Data using 2D Diffusion Models" (ISMRM 2024 oral)