Search

We measure the time-integrated CP asymmetry in $D^{0} \rightarrow K^{0}_{S}K^{0}_{S}$ decays reconstructed in $e^{+}e^{-} \rightarrow c\overline{c}$ events collected by the Belle and Belle II experiments. The corresponding data samples have integrated luminosities of 980 fb$^{-1}$ and 427 fb$^{-1}$, respectively. The D$^{0}$ decays are required to originate from the $D^{*+} \rightarrow D^{0}\pi^{+}$ decay, which determines the charm flavor at production time. A control sample of $D^{0} \rightarrow K^{+}K^{-}$ decays is used to correct for production and detection asymmetries.The result, ($-$1.4 $\pm$ 1.3(\text{stat.})$\pm$ 0.1(\text{syst.}))\%, is consistent with previous determinations and with CP symmetry., Comment: 10 pages, 3 figures. arXiv admin note: text overlap with arXiv:2410.22961

Medical Decision-Making (MDM) is a multi-faceted process that requires clinicians to assess complex multi-modal patient data patient, often collaboratively. Large Language Models (LLMs) promise to streamline this process by synthesizing vast medical knowledge and multi-modal health data. However, single-agent are often ill-suited for nuanced medical contexts requiring adaptable, collaborative problem-solving. Our MDAgents addresses this need by dynamically assigning collaboration structures to LLMs based on task complexity, mimicking real-world clinical collaboration and decision-making. This framework improves diagnostic accuracy and supports adaptive responses in complex, real-world medical scenarios, making it a valuable tool for clinicians in various healthcare settings, and at the same time, being more efficient in terms of computing cost than static multi-agent decision making methods.

As social VR applications grow in popularity, blind and low vision users encounter continued accessibility barriers. Yet social VR, which enables multiple people to engage in the same virtual space, presents a unique opportunity to allow other people to support a user's access needs. To explore this opportunity, we designed a framework based on physical sighted guidance that enables a guide to support a blind or low vision user with navigation and visual interpretation. A user can virtually hold on to their guide and move with them, while the guide can describe the environment. We studied the use of our framework with 16 blind and low vision participants and found that they had a wide range of preferences. For example, we found that participants wanted to use their guide to support social interactions and establish a human connection with a human-appearing guide. We also highlight opportunities for novel guidance abilities in VR, such as dynamically altering an inaccessible environment. Through this work, we open a novel design space for a versatile approach for making VR fully accessible.

Social VR has increased in popularity due to its affordances for rich, embodied, and nonverbal communication. However, nonverbal communication remains inaccessible for blind and low vision people in social VR. We designed accessible cues with audio and haptics to represent three nonverbal behaviors: eye contact, head shaking, and head nodding. We evaluated these cues in real-time conversation tasks where 16 blind and low vision participants conversed with two other users in VR. We found that the cues were effective in supporting conversations in VR. Participants had statistically significantly higher scores for accuracy and confidence in detecting attention during conversations with the cues than without. We also found that participants had a range of preferences and uses for the cues, such as learning social norms. We present design implications for handling additional cues in the future, such as the challenges of incorporating AI. Through this work, we take a step towards making interpersonal embodied interactions in VR fully accessible for blind and low vision people.

Although pre-trained language models show good performance on various natural language processing tasks, they often rely on non-causal features and patterns to determine the outcome. For natural language inference tasks, previous results have shown that even a model trained on a large number of data fails to perform well on counterfactually revised data, indicating that the model is not robustly learning the semantics of the classes. In this paper, we propose a method in which we use token-based and sentence-based augmentation methods to generate counterfactual sentence pairs that belong to each class, and apply contrastive learning to help the model learn the difference between sentence pairs of different classes with similar contexts. Evaluation results with counterfactually-revised dataset and general NLI datasets show that the proposed method can improve the performance and robustness of the NLI model., Comment: accepted at INTERSPEECH 2023

GPT-4o is an autoregressive omni model that accepts as input any combination of text, audio, image, and video, and generates any combination of text, audio, and image outputs. It's trained end-to-end across text, vision, and audio, meaning all inputs and outputs are processed by the same neural network. GPT-4o can respond to audio inputs in as little as 232 milliseconds, with an average of 320 milliseconds, which is similar to human response time in conversation. It matches GPT-4 Turbo performance on text in English and code, with significant improvement on text in non-English languages, while also being much faster and 50\% cheaper in the API. GPT-4o is especially better at vision and audio understanding compared to existing models. In line with our commitment to building AI safely and consistent with our voluntary commitments to the White House, we are sharing the GPT-4o System Card, which includes our Preparedness Framework evaluations. In this System Card, we provide a detailed look at GPT-4o's capabilities, limitations, and safety evaluations across multiple categories, focusing on speech-to-speech while also evaluating text and image capabilities, and measures we've implemented to ensure the model is safe and aligned. We also include third-party assessments on dangerous capabilities, as well as discussion of potential societal impacts of GPT-4o's text and vision capabilities.

Fragmentation and evolution for the molecular shells of the compact HII regions are less explored compared to their evolved counterparts. We map nine compact HII regions with a typical diameter of 0.4 pc that are surrounded by molecular shells traced by CCH. Several to a dozen dense gas fragments probed by H13CO+ are embedded in these molecular shells. These gas fragments, strongly affected by the HII region, have a higher surface density, mass, and turbulence than those outside the shells but within the same pc-scale natal clump. These features suggest that the shells swept up by the early HII regions can enhance the formation of massive dense structures that may host the birth of higher-mass stars. We examine the formation of fragments and find that fragmentation of the swept-up shell is unlikely to occur in these early HII regions, by comparing the expected time scale of shell fragmentation with the age of HII region. We propose that the appearance of gas fragments in these shells is probably the result of sweeping up pre-existing fragments into the molecular shell that has not yet fragmented. Taken together, this work provides a basis for understanding the interplay of star-forming sites with an intricate environment containing ionization feedback such as those observed in starburst regions., Comment: Accepted by MNRAS, 24 pages, 14 figures

We present a catalog of unobscured QSO candidates in the southern hemisphere from the early interim data of the KMTNet Synoptic Survey of Southern Sky (KS4). The KS4 data covers $\sim2500\,{\rm deg}^{2}$ sky area, reaching 5$\sigma$ detection limits of $\sim$22.1-22.7 AB mag in the $BVRI$ bands. Combining this with available infrared photometric data from the surveys covering the southern sky, we select the unobscured QSO candidates based on their colors and spectral energy distributions (SEDs) fitting results. The final catalog contains 72,964 unobscured QSO candidates, of which only 0.4% are previously identified as QSOs based on spectroscopic observations. Our selection method achieves an 87% recovery rate for spectroscopically confirmed bright QSOs at $z<2$ within the KS4 survey area. In addition, the number count of our candidates is comparable to that of spectroscopically confirmed QSOs from the Sloan Digital Sky Survey in the northern sky. These demonstrate that our approach is effective in searching for unobscured QSOs in the southern sky. Future spectro-photometric surveys covering the southern sky will enable us to discern their true nature and enhance our understanding of QSO populations in the southern hemisphere., Comment: 15 pages, 9 figures, 2 tables. Accepted for publication in ApJS

3D Gaussian Splatting has shown fast and high-quality rendering results in static scenes by leveraging dense 3D prior and explicit representations. Unfortunately, the benefits of the prior and representation do not involve novel view synthesis for dynamic motions. Ironically, this is because the main barrier is the reliance on them, which requires increasing training and rendering times to account for dynamic motions. In this paper, we design a Explicit 4D Gaussian Splatting(Ex4DGS). Our key idea is to firstly separate static and dynamic Gaussians during training, and to explicitly sample positions and rotations of the dynamic Gaussians at sparse timestamps. The sampled positions and rotations are then interpolated to represent both spatially and temporally continuous motions of objects in dynamic scenes as well as reducing computational cost. Additionally, we introduce a progressive training scheme and a point-backtracking technique that improves Ex4DGS's convergence. We initially train Ex4DGS using short timestamps and progressively extend timestamps, which makes it work well with a few point clouds. The point-backtracking is used to quantify the cumulative error of each Gaussian over time, enabling the detection and removal of erroneous Gaussians in dynamic scenes. Comprehensive experiments on various scenes demonstrate the state-of-the-art rendering quality from our method, achieving fast rendering of 62 fps on a single 2080Ti GPU., Comment: Accepted at NeurIPS 2024

In the bottomonium sector, the hindered magnetic dipole (M1) transitions between P-wave states $h_b(2P) \rightarrow \chi_{bJ}(1P) \gamma$, $J=0, \, 1, \, 2$, are expected to be severely suppressed according to the Relativized Quark Model, due to the spin flip of the $b$ quark. Nevertheless, a recent model following the coupled-channel approach predicts the corresponding branching fractions to be enhanced by orders of magnitude. In this Letter, we report the first search for such transitions. We find no significant signals and set upper limits at 90% CL on the corresponding branching fractions: $\mathcal{B}[h_b(2P)\to\gamma\chi_{b0}(1P)] < 2.7 \times 10^{-1}$, $\mathcal{B}[h_b(2P)\to\gamma\chi_{b1}(1P)] < 5.4 \times 10^{-3}$ and $\mathcal{B}[h_b(2P)\to\gamma\chi_{b2}(1P)] < 1.3 \times 10^{-2}$. These values help to constrain the parameters of the coupled-channel models. The results are obtained using a $121.4 \, fb^{-1}$ data sample taken around $\sqrt{s}= 10.860 \, GeV$ with the Belle detector at the KEKB asymmetric-energy $e^+e^-$ collider.

We present 850 {\mu}m thermal dust polarization observations with a resolution of 14.4"(~ 0.13 pc) towards an infrared dark cloud G16.96+0.27 using JCMT/POL-2. The average magnetic field orientation, which roughly agrees with the larger-scale magnetic field orientation traced by the Planck 353 GHz data, is approximately perpendicular to the filament structure. The estimated plane-of-sky magnetic field strength is ~ 96 {\mu}G and ~ 60 {\mu}G using two variants of the Davis-Chandrasekhar-Fermi methods. We calculate the virial and magnetic critical parameters to evaluate the relative importance of gravity, the magnetic field, and turbulence. The magnetic field and turbulence are both weaker than gravity, but magnetic fields and turbulence together are equal to gravity, suggesting that G16.96+0.27 is in a quasi-equilibrium state. The cloud-magnetic-field alignment is found to have a trend moving away from perpendicularity in the dense regions, which may serve as a tracer of potential fragmentation in such quiescent filaments., Comment: Accepted by ApJ. 13 pages, 5 figures

Recently, pre-trained language models (PLMs) have been increasingly adopted in spoken language understanding (SLU). However, automatic speech recognition (ASR) systems frequently produce inaccurate transcriptions, leading to noisy inputs for SLU models, which can significantly degrade their performance. To address this, our objective is to train SLU models to withstand ASR errors by exposing them to noises commonly observed in ASR systems, referred to as ASR-plausible noises. Speech noise injection (SNI) methods have pursued this objective by introducing ASR-plausible noises, but we argue that these methods are inherently biased towards specific ASR systems, or ASR-specific noises. In this work, we propose a novel and less biased augmentation method of introducing the noises that are plausible to any ASR system, by cutting off the non-causal effect of noises. Experimental results and analyses demonstrate the effectiveness of our proposed methods in enhancing the robustness and generalizability of SLU models against unseen ASR systems by introducing more diverse and plausible ASR noises in advance., Comment: 9 pages, 3 figures

In this paper, we present a detailed analysis of the IRS 17 filament within the intermediate-mass protocluster IRAS 08448-4343 (of $\sim\,10^3\,\rm L_{\odot}$), using ALMA data from the ATOMS 3-mm and QUARKS 1.3-mm surveys. The IRS 17 filament, which spans $\sim$54000 au ($0.26\,\rm pc$) in length and $\sim$4000 au ($0.02\,\rm pc$) in width, exhibits a complex, multi-component velocity field, and harbours hierarchical substructures. These substructures include three bundles of seven velocity-coherent fibers, and 29 dense ($n\sim 10^8\,\rm cm^{-3}$) condensations. The fibers have a median length of $\sim 4500\,\rm au$ and a median width of $\sim 1400\,\rm au$. Among these fibers, four are identified as ``fertile", each hosting at least three dense condensations, which are regarded as the ``seeds" of star formation. While the detected cores are randomly spaced within the IRS\,17 filament based on the 3-mm dust continuum image, periodic spacing ($\sim1600\,\rm au$) of condensations is observed in the fertile fibers according to the 1.3-mm dust map, consistent with the predictions of linear isothermal cylinder fragmentation models. These findings underscore the crucial role of fibers in star formation and suggest a hierarchical fragmentation process that extends from the filament to the fibers, and ultimately, to the smallest-scale condensations., Comment: 19 pages, 10 figures, 4 tables, accepted by ApJ

Accelerating end-to-end inference of transformer-based large language models (LLMs) is a critical component of AI services in datacenters. However, diverse compute characteristics of end-to-end LLM inference present challenges as previously proposed accelerators only address certain operations or stages (e.g., self-attention, generation stage, etc.). To address the unique challenges of accelerating end-to-end inference, we propose IANUS -- Integrated Accelerator based on NPU-PIM Unified Memory System. IANUS is a domain-specific system architecture that combines a Neural Processing Unit (NPU) with a Processing-in-Memory (PIM) to leverage both the NPU's high computation throughput and the PIM's high effective memory bandwidth. In particular, IANUS employs a unified main memory system where the PIM memory is used both for PIM operations and for NPU's main memory. The unified main memory system ensures that memory capacity is efficiently utilized and the movement of shared data between NPU and PIM is minimized. However, it introduces new challenges since normal memory accesses and PIM computations cannot be performed simultaneously. Thus, we propose novel PIM Access Scheduling that manages normal memory accesses and PIM computations through workload mapping and scheduling across the PIM and the NPU. Our detailed simulation evaluations show that IANUS improves the performance of GPT-2 by 6.2$\times$ and 3.2$\times$, on average, compared to the NVIDIA A100 GPU and the state-of-the-art accelerator. As a proof-of-concept, we develop a prototype of IANUS with a commercial PIM, NPU, and an FPGA-based PIM controller to demonstrate the feasibility of IANUS., Comment: Updated version of the paper accepted to ASPLOS 2024

The rapid growth of virtual reality (VR) has led to increased use of social VR platforms for interaction. However, these platforms lack adequate features to support blind and low vision (BLV) users, posing significant challenges in navigation, visual interpretation, and social interaction. One promising approach to these challenges is employing human guides in VR. However, this approach faces limitations with a lack of availability of humans to serve as guides, or the inability to customize the guidance a user receives from the human guide. We introduce an AI-powered guide to address these limitations. The AI guide features six personas, each offering unique behaviors and appearances to meet diverse user needs, along with visual interpretation and navigation assistance. We aim to use this AI guide in the future to help us understand BLV users' preferences for guide forms and functionalities.

Demand for streaming services, including satellite, continues to exhibit unprecedented growth. Internet Service Providers find themselves at the crossroads of technological advancements and rising customer expectations. To stay relevant and competitive, these ISPs must ensure their networks deliver optimal video streaming quality, a key determinant of user satisfaction. Towards this end, it is important to have accurate Quality of Experience prediction models in place. However, achieving robust performance by these models requires extensive data sets labeled by subjective opinion scores on videos impaired by diverse playback disruptions. To bridge this data gap, we introduce the LIVE-Viasat Real-World Satellite QoE Database. This database consists of 179 videos recorded from real-world streaming services affected by various authentic distortion patterns. We also conducted a comprehensive subjective study involving 54 participants, who contributed both continuous-time opinion scores and endpoint (retrospective) QoE scores. Our analysis sheds light on various determinants influencing subjective QoE, such as stall events, spatial resolutions, bitrate, and certain network parameters. We demonstrate the usefulness of this unique new resource by evaluating the efficacy of prevalent QoE-prediction models on it. We also created a new model that maps the network parameters to predicted human perception scores, which can be used by ISPs to optimize the video streaming quality of their networks. Our proposed model, which we call SatQA, is able to accurately predict QoE using only network parameters, without any access to pixel data or video-specific metadata, estimated by Spearman's Rank Order Correlation Coefficient (SROCC), Pearson Linear Correlation Coefficient (PLCC), and Root Mean Squared Error (RMSE), indicating high accuracy and reliability.

Assessing the quality of bovine satellite cells (BSCs) is essential for the cultivated meat industry, which aims to address global food sustainability challenges. This study aims to develop a label-free method for predicting fluorescence markers in isolated BSCs using deep learning. We employed a U-Net-based CNN model to predict multiple fluorescence signals from a single bright-field microscopy image of cell culture. Two key biomarkers, DAPI and Pax7, were used to determine the abundance and quality of BSCs. The image pre-processing pipeline included fluorescence denoising to improve prediction performance and consistency. A total of 48 biological replicates were used, with statistical performance metrics such as Pearson correlation coefficient and SSIM employed for model evaluation. The model exhibited better performance with DAPI predictions due to uniform staining. Pax7 predictions were more variable, reflecting biological heterogeneity. Enhanced visualization techniques, including color mapping and image overlay, improved the interpretability of the predictions by providing better contextual and perceptual information. The findings highlight the importance of data pre-processing and demonstrate the potential of deep learning to advance non-invasive, label-free assessment techniques in the cultivated meat industry, paving the way for reliable and actionable AI-driven evaluations., Comment: 11 pages, 4 figures

Video Temporal Grounding (VTG) aims to identify visual frames in a video clip that match text queries. Recent studies in VTG employ cross-attention to correlate visual frames and text queries as individual token sequences. However, these approaches overlook a crucial aspect of the problem: a holistic understanding of the query sentence. A model may capture correlations between individual word tokens and arbitrary visual frames while possibly missing out on the global meaning. To address this, we introduce two primary contributions: (1) a visual frame-level gate mechanism that incorporates holistic textual information, (2) cross-modal alignment loss to learn the fine-grained correlation between query and relevant frames. As a result, we regularize the effect of individual word tokens and suppress irrelevant visual frames. We demonstrate that our method outperforms state-of-the-art approaches in VTG benchmarks, indicating that holistic text understanding guides the model to focus on the semantically important parts within the video., Comment: Accepted by ACMMM 24

Automatic question generation (QG) is essential for AI and NLP, particularly in intelligent tutoring, dialogue systems, and fact verification. Generating multiple-choice questions (MCQG) for professional exams, like the United States Medical Licensing Examination (USMLE), is particularly challenging, requiring domain expertise and complex multi-hop reasoning for high-quality questions. However, current large language models (LLMs) like GPT-4 struggle with professional MCQG due to outdated knowledge, hallucination issues, and prompt sensitivity, resulting in unsatisfactory quality and difficulty. To address these challenges, we propose MCQG-SRefine, an LLM self-refine-based (Critique and Correction) framework for converting medical cases into high-quality USMLE-style questions. By integrating expert-driven prompt engineering with iterative self-critique and self-correction feedback, MCQG-SRefine significantly enhances human expert satisfaction regarding both the quality and difficulty of the questions. Furthermore, we introduce an LLM-as-Judge-based automatic metric to replace the complex and costly expert evaluation process, ensuring reliable and expert-aligned assessments., Comment: Equal contribution for the first two authors

As emerging marine technologies lead to the development of new infrastructure across the ocean, they enter an environment that existing ecosystems and industries already rely on. Although necessary to provide sustainable sources of energy and food, careful planning will be important to make informed decisions and avoid conflicts. This paper examines several techniques used for marine spatial planning, an approach for analyzing and planning the use of marine resources. Using open source software including QGIS and Python, the potential for developing wave-powered offshore aquaculture farms using the RM3 wave energy converter along the Northeast coast of the United States is assessed and several feasible sites are identified. The optimal site, located at 43.7{\deg}N, 68.9{\deg}W along the coast of Maine, has a total cost for a 5-pen farm of \$56.8M, annual fish yield of 676 tonnes, and a levelized cost of fish of \$9.23 per kilogram. Overall trends indicate that the cost greatly decreases with distance to shore due to the greater availability of wave energy and that conflicts and environmental constraints significantly limit the number of feasible sites in this region.

Perfect circular dichroism has been observed in the Raman scattering by the optical phonons in single chiral domain NiCo2TeO6 crystals. The selection rules for the optical phonons are determined by the combination of the chiral structure C and the electric polarization P along the c-axis. These two symmetry operations are equivalent to the ferroaxial order (C dot P) = A, so the observed optical phonons are referred to as "ferroaxial". For a given Raman scattering geometry the observed effect may also be described as a complete non-reciprocal propagation of the optical phonons, whose preferable vector direction is determined by the sign of C dot P. The combination of Raman scattering and polarization plane rotation of the transmitted white light allows for identification of the direction of electric polarization P in mono domain chiral crystals.

Aspect-based sentiment analysis (ABSA) is the challenging task of extracting sentiment along with its corresponding aspects and opinions from human language. Due to the inherent variability of natural language, aspect and opinion terms can be expressed in various surface forms, making their accurate identification complex. Current evaluation methods for this task often restrict answers to a single ground truth, penalizing semantically equivalent predictions that differ in surface form. To address this limitation, we propose a novel, fully automated pipeline that augments existing test sets with alternative valid responses for aspect and opinion terms. This approach enables a fairer assessment of language models by accommodating linguistic diversity, resulting in higher human agreement than single-answer test sets (up to 10%p improvement in Kendall's Tau score). Our experimental results demonstrate that Large Language Models (LLMs) show substantial performance improvements over T5 models when evaluated using our augmented test set, suggesting that LLMs' capabilities in ABSA tasks may have been underestimated. This work contributes to a more comprehensive evaluation framework for ABSA, potentially leading to more accurate assessments of model performance in information extraction tasks, particularly those involving span extraction., Comment: Preprint

We present a measurement of the branching fraction and time-dependent charge-parity ($CP$) decay-rate asymmetries in $B^0 \to J/\psi \pi^0$ decays. The data sample was collected with the Belle~II detector at the SuperKEKB asymmetric $e^+e^-$ collider in 2019-2022 and contains $(387\pm 6)\times 10^6$ $B\overline{B}$ meson pairs from $\Upsilon(4S)$ decays. We reconstruct $392\pm 24$ signal decays and fit the $CP$ parameters from the distribution of the proper-decay-time difference of the two $B$ mesons. We measure the branching fraction to be $B(B^0 \to J/\psi \pi^0)=(2.02 \pm 0.12 \pm 0.10)\times 10^{-5}$ and the direct and mixing-induced $CP$ asymmetries to be $C_{CP}=0.13 \pm 0.12 \pm 0.03$ and $S_{CP}=-0.88 \pm 0.17 \pm 0.03$, respectively, where the first uncertainties are statistical and the second are systematic. We observe mixing-induced $CP$ violation with a significance of $5.0$ standard deviations for the first time in this mode.

The perennial demand for highly efficient short-haul communications is evidenced by a sustained explosion of growth in data center infrastructure that is predicted to continue for the foreseeable future. In these relatively compact networks, cost-sensitivity is of particular importance, which limits options to direct detection schemes that are more cost efficient than their coherent counterparts. Since their initial demonstration, multi-soliton states in optical microresonators have been observed to manifest in self-organised ensembles where soliton pulses are equally spaced around the resonators. In the spectral domain, these states, dubbed soliton crystals (SCs), result in significant enhancements to individual comb lines depending on the crystal state, making them well suited towards intensity-modulated direct detection (IMDD) schemes. In this work, we experimentally demonstrate adiabatic, deterministic access to lower-order soliton crystal states using an auxiliary-assisted cavity pumping method, attaining up to 19.6 dB enhancement of the comb lines in the 7-SC configuration compared to the single-soliton state. Seven comb lines of each 46 Gbaud/s pulse amplitude modulation 4 (PAM4) is transmitted over 4km of fiber in comb lines across the C-band with bit-error-rates (BER) as low as 5E-5. Our demonstration shows the promising way of using soliton crystal states as future integrated sources for highly stable Terabaud/s datacenter communications.

Brown Dwarfs (BDs) are crucial objects in our understanding of both star and planet formation. However, there is still an unconcluded debate about which is the dominant formation mechanism of these objects. For this, it is mandatory to study BDs in their earliest evolutionary stages (what we call pre- and proto-BDs), comparable to the `pre-stellar' and `Class 0/I' stages well characterized for the formation of low-mass stars. In this review, the recent efforts aimed at searching, identifying and characterising pre- and proto-BD candidates in nearby star-forming regions are presented, and revised requirements for an object to be a promising proto-BD or pre-BD candidate are provided, based on a new, unexplored so far, relation between the internal luminosity and the accreted mass. By applying these requirements, a list of 67 promising proto-BD candidates is presented, along with a compilation of possible pre-BDs from the literature. Updated correlations of protostellar properties such as mass infall rate or outflow momentum rate with bolometric luminosity are provided down to the low-mass BD regime, where no significant deviations are apparent. Furthermore, the number of proto-BD candidates in different clouds of the Solar Neighborhood seem to follow the known relations of number of protostars with cloud properties. In addition, proto(star-to-BD) ratios for the different clouds are also explored, unveiling a particular underproduction of low-mass proto-BD candidates in Ophiuchus compared to Lupus and Taurus. Possible explanations for this behavior are discussed, including heating of the Ophiuchus cloud by the nearby OB stars. The overall results of this work tend to favor a star-like process for BD formation down to the planetary boundary, of about 10 Mjup, below which other mechanisms might be at work., Comment: Invited review to New Astronomy Reviews. 63 pages. In press

The first very long baseline interferometry (VLBI) detections at 870$\mu$m wavelength (345$\,$GHz frequency) are reported, achieving the highest diffraction-limited angular resolution yet obtained from the surface of the Earth, and the highest-frequency example of the VLBI technique to date. These include strong detections for multiple sources observed on inter-continental baselines between telescopes in Chile, Hawaii, and Spain, obtained during observations in October 2018. The longest-baseline detections approach 11$\,$G$\lambda$ corresponding to an angular resolution, or fringe spacing, of 19$\mu$as. The Allan deviation of the visibility phase at 870$\mu$m is comparable to that at 1.3$\,$mm on the relevant integration time scales between 2 and 100$\,$s. The detections confirm that the sensitivity and signal chain stability of stations in the Event Horizon Telescope (EHT) array are suitable for VLBI observations at 870$\mu$m. Operation at this short wavelength, combined with anticipated enhancements of the EHT, will lead to a unique high angular resolution instrument for black hole studies, capable of resolving the event horizons of supermassive black holes in both space and time., Comment: Corresponding author: S. Doeleman

In this paper, we propose a new method to enhance compositional understanding in pre-trained vision and language models (VLMs) without sacrificing performance in zero-shot multi-modal tasks. Traditional fine-tuning approaches often improve compositional reasoning at the cost of degrading multi-modal capabilities, primarily due to the use of global hard negative (HN) loss, which contrasts global representations of images and texts. This global HN loss pushes HN texts that are highly similar to the original ones, damaging the model's multi-modal representations. To overcome this limitation, we propose Fine-grained Selective Calibrated CLIP (FSC-CLIP), which integrates local hard negative loss and selective calibrated regularization. These innovations provide fine-grained negative supervision while preserving the model's representational integrity. Our extensive evaluations across diverse benchmarks for both compositionality and multi-modal tasks show that FSC-CLIP not only achieves compositionality on par with state-of-the-art models but also retains strong multi-modal capabilities. Code is available at: https://github.com/ytaek-oh/fsc-clip., Comment: EMNLP 2024 (Long, Main). Project page: https://ytaek-oh.github.io/fsc-clip

Online hate speech has become increasingly prevalent on social media platforms, causing harm to individuals and society. While efforts have been made to combat this issue through content moderation, the potential of user-driven counterspeech as an alternative solution remains underexplored. Existing counterspeech methods often face challenges such as fear of retaliation and skill-related barriers. To address these challenges, we introduce CounterQuill, an AI-mediated system that assists users in composing effective and empathetic counterspeech. CounterQuill provides a three-step process: (1) a learning session to help users understand hate speech and counterspeech; (2) a brainstorming session that guides users in identifying key elements of hate speech and exploring counterspeech strategies; and (3) a co-writing session that enables users to draft and refine their counterspeech with CounterQuill. We conducted a within-subjects user study with 20 participants to evaluate CounterQuill in comparison to ChatGPT. Results show that CounterQuill's guidance and collaborative writing process provided users a stronger sense of ownership over their co-authored counterspeech. Users perceived CounterQuill as a writing partner and thus were more willing to post the co-written counterspeech online compared to the one written with ChatGPT.

Reward models are key in reinforcement learning from human feedback (RLHF) systems, aligning the model behavior with human preferences. Particularly in the math domain, there have been plenty of studies using reward models to align policies for improving reasoning capabilities. Recently, as the importance of reward models has been emphasized, RewardBench is proposed to understand their behavior. However, we figure out that the math subset of RewardBench has different representations between chosen and rejected completions, and relies on a single comparison, which may lead to unreliable results as it only see an isolated case. Therefore, it fails to accurately present the robustness of reward models, leading to a misunderstanding of its performance and potentially resulting in reward hacking. In this work, we introduce a new design for reliable evaluation of reward models, and to validate this, we construct RewardMATH, a benchmark that effectively represents the robustness of reward models in mathematical reasoning tasks. We demonstrate that the scores on RewardMATH strongly correlate with the results of optimized policy and effectively estimate reward overoptimization, whereas the existing benchmark shows almost no correlation. The results underscore the potential of our design to enhance the reliability of evaluation, and represent the robustness of reward model. We make our code and data publicly available., Comment: Work in progress

Artificial intelligence (AI) and large language models (LLMs) in healthcare require advanced clinical skills (CS), yet current benchmarks fail to evaluate these comprehensively. We introduce MedQA-CS, an AI-SCE framework inspired by medical education's Objective Structured Clinical Examinations (OSCEs), to address this gap. MedQA-CS evaluates LLMs through two instruction-following tasks, LLM-as-medical-student and LLM-as-CS-examiner, designed to reflect real clinical scenarios. Our contributions include developing MedQA-CS, a comprehensive evaluation framework with publicly available data and expert annotations, and providing the quantitative and qualitative assessment of LLMs as reliable judges in CS evaluation. Our experiments show that MedQA-CS is a more challenging benchmark for evaluating clinical skills than traditional multiple-choice QA benchmarks (e.g., MedQA). Combined with existing benchmarks, MedQA-CS enables a more comprehensive evaluation of LLMs' clinical capabilities for both open- and closed-source LLMs.

In this work, we investigate how a model's tendency to broadly integrate its parametric knowledge evolves throughout pretraining, and how this behavior affects overall performance, particularly in terms of knowledge acquisition and forgetting. We introduce the concept of knowledge entropy, which quantifies the range of memory sources the model engages with; high knowledge entropy indicates that the model utilizes a wide range of memory sources, while low knowledge entropy suggests reliance on specific sources with greater certainty. Our analysis reveals a consistent decline in knowledge entropy as pretraining advances. We also find that the decline is closely associated with a reduction in the model's ability to acquire and retain knowledge, leading us to conclude that diminishing knowledge entropy (smaller number of active memory sources) impairs the model's knowledge acquisition and retention capabilities. We find further support for this by demonstrating that increasing the activity of inactive memory sources enhances the model's capacity for knowledge acquisition and retention.

Electro-optic active metasurfaces have attracted attention due to their ability to electronically control optical wavefront with unprecedented spatiotemporal resolutions. In most studies, such devices require gate arrays composed of a large number of independently-controllable local gate electrodes that address local scattering response of individual metaatoms. Although this approach in principle enables arbitrary wavefront control, the complicated driving mechanism and low optical efficiency have been hindering its practical applications. In this work, we demonstrate an active beam switching device that provides high directivity, uniform efficiency across diffraction orders, and a wide field of view while operating with only a single-gate bias. Experimentally, the metasurface achieves 57{\deg} of active beam switching from the 0th to the -1st order diffraction, with efficiencies of 0.084 and 0.078 and directivities of 0.765 and 0.836, respectively. Furthermore, an analytical framework using nonlocal quasinormal mode expansion provides deeper insight into the operating mechanism of active beam switching. Finally, we discuss the performance limitations of this design platform and provide insights into potential improvements.

NASA's forthcoming Lunar Gateway space station, which will be uncrewed most of the time, will need to operate with an unprecedented level of autonomy. Enhancing autonomy on the Gateway presents several unique challenges, one of which is to equip the Canadarm3, the Gateway's external robotic system, with the capability to perform worksite monitoring. Monitoring will involve using the arm's inspection cameras to detect any anomalies within the operating environment, a task complicated by the widely-varying lighting conditions in space. In this paper, we introduce the visual anomaly detection and localization task for space applications and establish a benchmark with our novel synthetic dataset called ALLO (for Anomaly Localization in Lunar Orbit). We develop a complete data generation pipeline to create ALLO, which we use to evaluate the performance of state-of-the-art visual anomaly detection algorithms. Given the low tolerance for risk during space operations and the lack of relevant data, we emphasize the need for novel, robust, and accurate anomaly detection methods to handle the challenging visual conditions found in lunar orbit and beyond., Comment: Submitted to International Conference on Robotics and Automation (ICRA'25), Atlanta, USA, May 19-23, 2025

This paper presents Coffee-Gym, a comprehensive RL environment for training models that provide feedback on code editing. Coffee-Gym includes two major components: (1) Coffee, a dataset containing humans' code edit traces for coding questions and machine-written feedback for editing erroneous code; (2) CoffeeEval, a reward function that faithfully reflects the helpfulness of feedback by assessing the performance of the revised code in unit tests. With them, Coffee-Gym addresses the unavailability of high-quality datasets for training feedback models with RL, and provides more accurate rewards than the SOTA reward model (i.e., GPT-4). By applying Coffee-Gym, we elicit feedback models that outperform baselines in enhancing open-source code LLMs' code editing, making them comparable with closed-source LLMs. We make the dataset and the model checkpoint publicly available., Comment: EMNLP2024

Clinical experts employ diverse philosophies and strategies in patient care, influenced by regional patient populations. However, existing medical artificial intelligence (AI) models are often trained on data distributions that disproportionately reflect highly prevalent patterns, reinforcing biases and overlooking the diverse expertise of clinicians. To overcome this limitation, we introduce the Mixture of Multicenter Experts (MoME) approach. This method strategically integrates specialized expertise from diverse clinical strategies, enhancing the AI model's ability to generalize and adapt across multiple medical centers. The MoME-based multimodal target volume delineation model, trained with few-shot samples including images and clinical notes from each medical center, outperformed baseline methods in prostate cancer radiotherapy target delineation. The advantages of MoME were most pronounced when data characteristics varied across centers or when data availability was limited, demonstrating its potential for broader clinical applications. Therefore, the MoME framework enables the deployment of AI-based target volume delineation models in resource-constrained medical facilities by adapting to specific preferences of each medical center only using a few sample data, without the need for data sharing between institutions. Expanding the number of multicenter experts within the MoME framework will significantly enhance the generalizability, while also improving the usability and adaptability of clinical AI applications in the field of precision radiation oncology., Comment: 39 pages

This paper introduces a speech enhancement solution tailored for true wireless stereo (TWS) earbuds on-device usage. The solution was specifically designed to support conversations in noisy environments, with active noise cancellation (ANC) activated. The primary challenges for speech enhancement models in this context arise from computational complexity that limits on-device usage and latency that must be less than 3 ms to preserve a live conversation. To address these issues, we evaluated several crucial design elements, including the network architecture and domain, design of loss functions, pruning method, and hardware-specific optimization. Consequently, we demonstrated substantial improvements in speech enhancement quality compared with that in baseline models, while simultaneously reducing the computational complexity and algorithmic latency., Comment: Accepted by Interspeech 2024

We consider actions of Taft algebras on noetherian graded down-up algebras. We classify all such actions and determine properties of the corresponding invariant rings $A^T$. We identify precisely when $A^T$ is commutative, when it is Artin-Schelter regular, and give sufficient conditions for it to be Artin-Schelter Gorenstein. Our results show that many results and conjectures in the literature concerning actions of semisimple Hopf algebras on Artin-Schelter regular algebras can fail when the semisimple hypothesis is omitted., Comment: 29 pages

The electrical resistivity of conventional metals, such as copper, is known to increase in thinner films due to electron-surface scattering, limiting the performance of metals in nanoscale electronics. Here, we uncover an exceptional reduction of resistivity with decreasing film thickness in NbP semimetal, deposited at relatively low temperatures of 400 {\deg}C. In sub-5 nm thin films, we find a significantly lower resistivity (~34 microOhm.cm for 1.5 nm thin NbP, at room temperature) than in the bulk form, and lower than conventional metals at similar thickness. Remarkably, the NbP films are not crystalline, but display local nanocrystalline, short-range order within an amorphous matrix. Our analysis suggests that the lower resistivity is due to conduction through surface channels, together with high surface carrier density and sufficiently good mobility, as the film thickness is reduced. These results and the fundamental insights obtained here could enable ultrathin, low-resistivity wires for nanoelectronics, beyond the limitations of conventional metals.

This work introduces a model-free reinforcement learning framework that enables various modes of motion (quadruped, tripod, or biped) and diverse tasks for legged robot locomotion. We employ a motion-style reward based on a relaxed logarithmic barrier function as a soft constraint, to bias the learning process toward the desired motion style, such as gait, foot clearance, joint position, or body height. The predefined gait cycle is encoded in a flexible manner, facilitating gait adjustments throughout the learning process. Extensive experiments demonstrate that KAIST HOUND, a 45 kg robotic system, can achieve biped, tripod, and quadruped locomotion using the proposed framework; quadrupedal capabilities include traversing uneven terrain, galloping at 4.67 m/s, and overcoming obstacles up to 58 cm (67 cm for HOUND2); bipedal capabilities include running at 3.6 m/s, carrying a 7.5 kg object, and ascending stairs-all performed without exteroceptive input., Comment: 7 pages, 5 figures, Videos at https://youtu.be/JV2_HfTlOKI

This paper studies the problem of information retrieval, to adapt to unseen tasks. Existing work generates synthetic queries from domain-specific documents to jointly train the retriever. However, the conventional query generator assumes the query as a question, thus failing to accommodate general search intents. A more lenient approach incorporates task-adaptive elements, such as few-shot learning with an 137B LLM. In this paper, we challenge a trend equating query and question, and instead conceptualize query generation task as a "compilation" of high-level intent into task-adaptive query. Specifically, we propose EGG, a query generator that better adapts to wide search intents expressed in the BeIR benchmark. Our method outperforms baselines and existing models on four tasks with underexplored intents, while utilizing a query generator 47 times smaller than the previous state-of-the-art. Our findings reveal that instructing the LM with explicit search intent is a key aspect of modeling an effective query generator.

The success of visual instruction tuning has accelerated the development of large language and vision models (LLVMs). Following the scaling laws of instruction-tuned large language models (LLMs), LLVMs either have further increased their sizes, reaching 26B, 34B, and even 80B parameters. While this increase in model size has yielded significant performance gains, it demands substantially more hardware resources for both training and inference. Consequently, there naturally exists a strong need for efficient LLVMs that achieve the performance of larger models while being smaller in size. To achieve this need, we present a new efficient LLVM family with model sizes of 0.5B, 1.8B, 3.8B, and 7B parameters, Phantom, which significantly enhances learning capabilities within limited structures. By temporarily increasing the latent hidden dimension during multi-head self-attention (MHSA), we make LLVMs prepare to look and understand much more vision-language knowledge on the latent, without substantially increasing physical model sizes. To maximize its advantage, we introduce Phantom Optimization (PO) using both autoregressive supervised fine-tuning (SFT) and direct preference optimization (DPO)-like concept, which effectively follows correct answers while eliminating incorrect and ambiguous ones. Phantom outperforms numerous larger open- and closed-source LLVMs, positioning itself as a leading solution in the landscape of efficient LLVMs., Comment: Code is available in https://github.com/ByungKwanLee/Phantom

Vision language models (VLM) have achieved success in both natural language comprehension and image recognition tasks. However, their use in pathology report generation for whole slide images (WSIs) is still limited due to the huge size of multi-scale WSIs and the high cost of WSI annotation. Moreover, in most of the existing research on pathology report generation, sufficient validation regarding clinical efficacy has not been conducted. Herein, we propose a novel Patient-level Multi-organ Pathology Report Generation (PMPRG) model, which utilizes the multi-scale WSI features from our proposed multi-scale regional vision transformer (MR-ViT) model and their real pathology reports to guide VLM training for accurate pathology report generation. The model then automatically generates a report based on the provided key features attended regional features. We assessed our model using a WSI dataset consisting of multiple organs, including the colon and kidney. Our model achieved a METEOR score of 0.68, demonstrating the effectiveness of our approach. This model allows pathologists to efficiently generate pathology reports for patients, regardless of the number of WSIs involved.

HOPS 87 is a Class 0 protostellar core known to harbor an extremely young bipolar outflow and a hot corino. We report the discovery of localized, chemically rich regions near the bases of the two-lobe bipolar molecular outflow in HOPS 87 containing molecules such as H$_2$CO, $^{13}$CS, H$_2$S, OCS, and CH$_3$OH, the simplest complex organic molecule (COM). The locations and kinematics suggest that these localized features are due to jet-driven shocks rather than being part of the hot corino region encasing the protostar. The COM compositions of the molecular gas in these jet-localized regions are relatively simpler than those in the hot corino zone. We speculate that this simplicity is due to either the liberation of ice with a less complex chemical history or the effects of shock chemistry. Our study highlights the dynamic interplay between the protostellar bipolar outflow, disk, inner core environment, and the surrounding medium, contributing to our understanding of molecular complexity in solar-like young stellar objects., Comment: 16 pages, 6+2 figures, accepted by ApJ

In this paper, we study the Navier-Stokes equation and the Burgers equation for the dynamical motion of a passive particle with harmonic and viscous forces, subject to an exponentially correlated Gaussian force. As deriving the Fokker-Planck equation for the joint probability density of a passive particle, we find obviously the important solution of the joint probability density by using double Fourier transforms in three-time domains, and the moments from derived moment equation are numerically calculated. As a result, the dynamical motion of a passive particle with respect to the probability density having two variables of displacement and velocity in the short-time domain has a super-diffusive form, whereas the distribution in the long-time domain is obtained to be Gaussian by analyzing only from the velocity probability density., Comment: 10 pages, 5 tables

Given a set P of n points in the plane, the two-line center problem asks to find two lines that minimize the maximum distance from each point in P to its closer one of the two resulting lines. The currently best algorithm for the problem takes $O(n^2\log^2n)$ time by Jaromczyk and Kowaluk in 1995. In this paper, we present faster algorithms for three variants of the two-line center problem in which the orientations of the resulting lines are constrained. Specifically, our algorithms solve the problem in $O(n \log n)$ time when the orientations of both lines are fixed; in $O(n \log^3 n)$ time when the orientation of one line is fixed; and in $O(n^2 \alpha(n) \log n)$ time when the angle between the two lines is fixed, where $\alpha(n)$ denotes the inverse Ackermann function.

Interconnection networks, or `interconnects,' play a crucial role in administering the communication among computing units of high-performance computing (HPC) systems. Efficient provisioning of interconnects minimizes the processing delay wherein computing units await information sharing between each other, thereby enhancing the overall computation efficiency. Ideally, interconnects are designed with topologies tailored to match specific workflows, requiring diverse structures for different applications. However, since modifying their structures mid-operation renders impractical, indirect communication incurs across distant units. In managing numerous long-routed data deliveries, heavy burdens on the network side may lead to the under-utilization of computing resources. In view of state-of-the-art HPC paradigms that solicit dense interconnections for diverse computation-hungry applications, this article presents a versatile wireless interconnecting framework, coined as Wireless Interconnection NEtwork (WINE). The framework exploits cutting-edge wireless technologies that promote workload adaptability and scalability of modern interconnects. Design and implementation of wirelessly reliable links are strategized under network-oriented scrutiny of HPC architectures. A virtual HPC platform is developed to assess WINE's feasibilities, verifying its practicality for integration into modern HPC infrastructures., Comment: 20 pages, 5 figures, to be published in IEEE Wireless Communications Magazine

Digital pathology has made significant advances in tumor diagnosis and segmentation, but image variability due to differences in organs, tissue preparation, and acquisition - known as domain shift - limits the effectiveness of current algorithms. The COSAS (Cross-Organ and Cross-Scanner Adenocarcinoma Segmentation) challenge addresses this issue by improving the resilience of segmentation algorithms to domain shift, with Task 2 focusing on adenocarcinoma segmentation using a diverse dataset from six scanners, pushing the boundaries of clinical diagnostics. Our approach employs unsupervised learning through stain separation within a multi-task learning framework using a multi-decoder autoencoder. This model isolates stain matrix and stain density, allowing it to handle color variation and improve generalization across scanners. We further enhanced the robustness of the model with a mixture of stain augmentation techniques and used a U-net architecture for segmentation. The novelty of our method lies in the use of stain separation within a multi-task learning framework, which effectively disentangles histological structures from color variations. This approach shows promise for improving segmentation accuracy and generalization across different histopathological stains, paving the way for more reliable diagnostic tools in digital pathology.

An unprecedented amount of existing functional Magnetic Resonance Imaging (fMRI) data provides a new opportunity to understand the relationship between functional fluctuation and human cognition/behavior using a data-driven approach. To that end, tremendous efforts have been made in machine learning to predict cognitive states from evolving volumetric images of blood-oxygen-level-dependent (BOLD) signals. Due to the complex nature of brain function, however, the evaluation on learning performance and discoveries are not often consistent across current state-of-the-arts (SOTA). By capitalizing on large-scale existing neuroimaging data (34,887 data samples from six public databases), we seek to establish a well-founded empirical guideline for designing deep models for functional neuroimages by linking the methodology underpinning with knowledge from the neuroscience domain. Specifically, we put the spotlight on (1) What is the current SOTA performance in cognitive task recognition and disease diagnosis using fMRI? (2) What are the limitations of current deep models? and (3) What is the general guideline for selecting the suitable machine learning backbone for new neuroimaging applications? We have conducted a comprehensive evaluation and statistical analysis, in various settings, to answer the above outstanding questions.

Blood oxygenation level-dependent (BOLD) functional magnetic resonance imaging (fMRI) is widely used to visualize brain activation regions by detecting hemodynamic responses associated with increased metabolic demand. While alternative MRI methods have been employed to monitor functional activities, the investigation of in-vivo electrical property changes during brain function remains limited. In this study, we explored the relationship between fMRI signals and electrical conductivity (measured at the Larmor frequency) changes using phase-based electrical properties tomography (EPT). Our results revealed consistent patterns: conductivity changes showed negative correlations, with conductivity decreasing in the functionally active regions whereas B1 phase mapping exhibited positive correlations around activation regions. These observations were consistent across both motor and visual cortex activations. To further substantiate these findings, we conducted electromagnetic radio-frequency simulations that modeled activation states with varying conductivity, which demonstrated trends similar to our in-vivo results for both B1 phase and conductivity. These findings suggest that in-vivo electrical conductivity changes can indeed be measured during brain activity. However, further investigation is needed to fully understand the underlying mechanisms driving these measurements.

Recent advancements in automatic speaker verification (ASV) studies have been achieved by leveraging large-scale pretrained networks. In this study, we analyze the approaches toward such a paradigm and underline the significance of interlayer information processing as a result. Accordingly, we present a novel approach for exploiting the multilayered nature of pretrained models for ASV, which comprises a layer/frame-level network and two steps of pooling architectures for each layer and frame axis. Specifically, we let convolutional architecture directly processes a stack of layer outputs.Then, we present a channel attention-based scheme of gauging layer significance and squeeze the layer level with the most representative value. Finally, attentive statistics over frame-level representations yield a single vector speaker embedding. Comparative experiments are designed using versatile data environments and diverse pretraining models to validate the proposed approach. The experimental results demonstrate the stability of the approach using multi-layer outputs in leveraging pretrained architectures. Then, we verify the superiority of the proposed ASV backend structure, which involves layer-wise operations, in terms of performance improvement along with cost efficiency compared to the conventional method. The ablation study shows how the proposed interlayer processing aids in maximizing the advantage of utilizing pretrained models., Comment: Preprint