Search

A phase transition in the dark sector (DS) presents a promising explanation for the stochastic gravitational wave (GW) signals detected in recent observations by Pulsar Timing Arrays (PTAs). Instead of focusing solely on fitting data with phenomenological parameters, we systematically delineate simple, underlying dark sector (DS) models at the microscopic, Lagrangian level and uncover the conditions required to yield the GW spectrum observed by PTAs. We also illustrate the possibilities of the DS cosmology, which may include a dark matter candidate with a $\mathcal{O}$(MeV) mass., Comment: 5 figures, 12 pages

Topic modeling is widely used for uncovering thematic structures within text corpora, yet traditional models often struggle with specificity and coherence in domain-focused applications. Guided approaches, such as SeededLDA and CorEx, incorporate user-provided seed words to improve relevance but remain labor-intensive and static. Large language models (LLMs) offer potential for dynamic topic refinement and discovery, yet their application often incurs high API costs. To address these challenges, we propose the LLM-assisted Iterative Topic Augmentation framework (LITA), an LLM-assisted approach that integrates user-provided seeds with embedding-based clustering and iterative refinement. LITA identifies a small number of ambiguous documents and employs an LLM to reassign them to existing or new topics, minimizing API costs while enhancing topic quality. Experiments on two datasets across topic quality and clustering performance metrics demonstrate that LITA outperforms five baseline models, including LDA, SeededLDA, CorEx, BERTopic, and PromptTopic. Our work offers an efficient and adaptable framework for advancing topic modeling and text clustering., Comment: Under Review

Tightly packed granular particles under shear often exhibit intriguing intermittencies, specifically, sudden stress drops that we refer to as quaking. To probe the nature of this phenomenon, we prototype a circular shear cell that is capable of imposing a uniform and unlimited shear strain under quasi-static cyclic driving. Spherical PDMS(polydimethylsiloxane) particles, immersed in fluid, are driven in a fixed total volume at a wide range of shear rates, with particle trajectories captured in 3D space via refraction-index-matched fluorescent tomography. Statistics on the magnitude of fluctuating displacements of individual particles shows distinct dependence on the shear rate. Particle motions are smooth at high shear rates. At intermediate shear rates, quaking emerges with clusters of particles exhibiting relatively large displacements. At low shear rates, a cluster can span the entire system. and the cluster exhibits substructures in view of localized particle movements. Overall, we have confirmed that the quaking phenomena in the current setup are consistent with our previous work [Phys. Rev. Lett.,126, 128001 (2021)], and that the dimensionless shear rate that we have proposed is indeed a good parameter for unifying the transitions observed in different experimental geometries.

OpenSciEd is a set of Creative Commons licensed, standards aligned curriculum and teacher professional learning materials that will be available for grades K-12. Using a storyline model that gives students the responsibility of "figuring out" science phenomena by engaging in science practices and classroom discussion to achieve consensus, OpenSciEd "empowers educators to go beyond traditional science teaching methods." This instructional model is ambitious for teachers, who must serve as facilitators and continually adapt instruction in response to directions students take. Because of this instructional shift, districts must also shift in how they adopt and implement science curriculum. Among the aims of the OpenSciEd Research Community, led by Digital Promise with support from the Carnegie Corporation of New York, is to develop and disseminate resources that support advancement of OpenSciEd-enabled research. Toward this goal, Digital Promise has released this report that synthesizes perspectives from OpenSciEd practitioners on their needs. The report identifies: (1) supports that teachers need to enact OpenSciEd with integrity, engage all their students, and gather evidence of students' standards-based learning outcomes; (2) ways districts can achieve deep, sustained adoption and meet their teachers' needs; and (3) potential research questions and opportunities for innovation that can improve OpenSciEd implementation in districts and classrooms. [This report was produced in collaboration with OpenSciEd.]

The existing single-pulse search algorithms for fast radio bursts (FRBs) do not adequately consider the frequency bandpass pattern of the pulse, rendering them incomplete for the relatively narrow-spectrum detection of pulses. We present a new search algorithm for narrow-band pulses to update the existing standard pipeline, Bandpass-Adaptive Single-pulse SEarch Toolkit (BASSET). The BASSET employs a time-frequency correlation analysis to identify and remove the noise involved by the zero-detection frequency band, thereby enhancing the signal-to-noise ratio (SNR) of the pulses. The BASSET algorithm was implemented on the FAST real dataset of FRB 20190520B, resulting in the discovery of additional 79 pulses through reprocessing. The new detection doubles the number of pulses compared to the previously known 75 pulses, bringing the total number of pulses to 154. In conjunction with the pulse calibration and the Markov Chain Monte Carlo (MCMC) simulated injection experiments, this work updates the quantified parameter space of the detection rate. Moreover, a parallel-accelerated version of the BASSET code was provided and evaluated through simulation. BASSET has the capacity of enhancing the detection sensitivity and the SNR of the narrow-band pulses from the existing pipeline, offering high performance and flexible applicability. BASSET not only enhances the completeness of the low-energy narrow-band pulse detection in a more robust mode, but also has the potential to further elucidate the FRB luminosity function at a wider energy scale., Comment: 22 pages, 11 figures, submitted to ApJS

Video personalization methods allow us to synthesize videos with specific concepts such as people, pets, and places. However, existing methods often focus on limited domains, require time-consuming optimization per subject, or support only a single subject. We present Video Alchemist $-$ a video model with built-in multi-subject, open-set personalization capabilities for both foreground objects and background, eliminating the need for time-consuming test-time optimization. Our model is built on a new Diffusion Transformer module that fuses each conditional reference image and its corresponding subject-level text prompt with cross-attention layers. Developing such a large model presents two main challenges: dataset and evaluation. First, as paired datasets of reference images and videos are extremely hard to collect, we sample selected video frames as reference images and synthesize a clip of the target video. However, while models can easily denoise training videos given reference frames, they fail to generalize to new contexts. To mitigate this issue, we design a new automatic data construction pipeline with extensive image augmentations. Second, evaluating open-set video personalization is a challenge in itself. To address this, we introduce a personalization benchmark that focuses on accurate subject fidelity and supports diverse personalization scenarios. Finally, our extensive experiments show that our method significantly outperforms existing personalization methods in both quantitative and qualitative evaluations., Comment: Project page: https://snap-research.github.io/open-set-video-personalization/

In 2013 Zhi-Wei Sun conjectured that $p(n)$ is never a power of an integer when $n>1.$ We confirm this claim in many cases. We also observe that integral powers appear to repel the partition numbers. If $k>1$ and $\Delta_k(n)$ is the distance between $p(n)$ and the nearest $k$th power, then for every $d\geq 0$ we conjecture that there are at most finitely many $n$ for which $\Delta_k(n)\leq d.$ More precisely, for every $\varepsilon>0,$ we conjecture that $$M_k(d):=\max\{n \ : \ \Delta_k(n)\leq d\}=o( d^{\varepsilon}).$$ In $k$-power aspect with $d$ fixed, we also conjecture that if $k$ is sufficiently large, then $$ M_k(d)=\max \left\{ n \ : \ p(n)-1\leq d\right\}. $$ In other words, $1$ generally appears to be the closest $k$th power among the partition numbers., Comment: (1) Accepted for publication in Annals Rom. Acad. Sci. (2) This paper is dedicated to the memory of Haim Brezis, and will appear in a special issue dedicated to his memory

Covariance regression analysis is an approach to linking the covariance of responses to a set of explanatory variables $X$, where $X$ can be a vector, matrix, or tensor. Most of the literature on this topic focuses on the "Fixed-$X$" setting and treats $X$ as nonrandom. By contrast, treating explanatory variables $X$ as random, namely the "Random-$X$" setting, is often more realistic in practice. This article aims to fill this gap in the literature on the estimation and model assessment theory for Random-$X$ covariance regression models. Specifically, we construct a new theoretical framework for studying the covariance estimators under the Random-$X$ setting, and we demonstrate that the quasi-maximum likelihood estimator and the weighted least squares estimator are both consistent and asymptotically normal. In addition, we develop pioneering work on the model assessment theory of covariance regression. In particular, we obtain the bias-variance decompositions for the expected test errors under both the Fixed-$X$ and Random-$X$ settings. We show that moving from a Fixed-$X$ to a Random-$X$ setting can increase both the bias and the variance in expected test errors. Subsequently, we propose estimators of the expected test errors under the Fixed-$X$ and Random-$X$ settings, which can be used to assess the performance of the competing covariance regression models. The proposed estimation and model assessment approaches are illustrated via extensive simulation experiments and an empirical study of stock returns in the US market., Comment: 25 pages

The proposed Habitable Worlds Observatory is intended to observe the atmospheres of nearby terrestrial exoplanets with a resolution greater than that of any previous instrument. While these observations present a substantial opportunity for astrobiology, they also incur the risk of false positives and false negatives. Here, we explore the use of systems science (in the form of network theory and thermochemical kinetics) to mitigate these risks, and briefly describe the technical specifications HWO would require in order to use these methodologies.

The Apollo Advanced Telecommunications Computing Architecture (ATCA) platform is an open-source design consisting of a generic "Service Module" (SM) and a customizable "Command Module" (CM), allowing for cost-effective use in applications such as the readout of the inner tracker and the Level-1 track trigger for the CMS Phase-II upgrade at the HL-LHC. The SM integrates an intelligent IPMC, robust power entry and conditioning systems, a powerful system-on-module computer, and flexible clock and communication infrastructure. The CM is designed around two Xilinx Ultrascale+ FPGAs and high-density, high-bandwidth optical transceivers capable of 25 Gb/s. Crates of Apollo blades are currently being tested at Boston University, Cornell University, and CERN., Comment: 7 pages, 4 figures, TWEPP2024 conference proceedings

Twisted and coiled polymer actuators (TCPAs) offer the advantages of large stroke and large specific work as compared to other actuators. There have been extensive experimental investigations towards understanding their actuation response, however, a computational model with full material description is not utilized to probe into the underlying mechanisms responsible for their large actuation. In this work, we develop a three-dimensional finite element model that includes the physics of the fabrication process to simulate the actuation of TCPA under various loading and boundary conditions. The model is validated against the experimental data and used to explore the factors responsible for actuation under free and isobaric conditions. The model captures the physics of the angle of twist in the fiber and the distinction between the homochiral and heterochiral nature of TCPA actuation response. The simulations show that the anisotropy in the thermal expansion coefficient (CTE) matrix plays a major role in large actuation irrespective of the anisotropy or isotropy in the elasticity tensor. We further investigate the extent of anisotropy in thermal expansion and the parametric studies show that the key for TCPA actuation is the absolute value of mismatch in thermal expansion even if the material has positive or negative CTE in both directions of the fiber. Furthermore, we propose a new shell-core composite-based TCPA concept by combining the epoxy and hollow Nylon tubes to suppress the creep in TCPA. The results show that the volume fraction of epoxy-core can be tuned to attain a desired actuation while offering a stiffer and creep-resistant response. This framework provides a wider application for probing various kinds of TCPAs and enhancing their actuation performance.

Task arithmetic in large-scale pre-trained models enables flexible adaptation to diverse downstream tasks without extensive re-training. By leveraging task vectors (TVs), users can perform modular updates to pre-trained models through simple arithmetic operations like addition and subtraction. However, this flexibility introduces new security vulnerabilities. In this paper, we identify and evaluate the susceptibility of TVs to backdoor attacks, demonstrating how malicious actors can exploit TVs to compromise model integrity. By developing composite backdoors and eliminating redudant clean tasks, we introduce BadTV, a novel backdoor attack specifically designed to remain effective under task learning, forgetting, and analogies operations. Our extensive experiments reveal that BadTV achieves near-perfect attack success rates across various scenarios, significantly impacting the security of models using task arithmetic. We also explore existing defenses, showing that current methods fail to detect or mitigate BadTV. Our findings highlight the need for robust defense mechanisms to secure TVs in real-world applications, especially as TV services become more popular in machine-learning ecosystems.

Our brains are hardwired for pattern recognition as correlations are useful for predicting and understanding nature. As more exoplanet atmospheres are being characterized with JWST, we are starting to unveil their properties on a population level. Here we present a framework for comparing exoplanet transmission spectroscopy from 3 to 5$\mu$m with four bands: L (2.9 - 3.7$\mu$m), SO$_2$ (3.95 - 4.1$\mu$m), CO$_2$ (4.25 - 4.4$\mu$m) and CO (4.5 - 4.9$\mu$m). Together, the four bands cover the major carbon, oxygen, nitrogen, and sulfur-bearing molecules including H$_2$O, CH$_4$, NH$_3$, H$_2$S, SO$_2$, CO$_2$, and CO. Among the eight high-precision gas giant exoplanet planet spectra we collected, we found strong correlations between the SO$_2$-L index and planet mass (r=-0.41$\pm$0.09) and temperature (r=-0.64$\pm$0.08), indicating SO$_2$ preferably exists (SO$_2$-L$>$-0.5) among low mass ($\sim<$0.3M$_J$) and cooler ($\sim<$1200K) targets. We also observe strong temperature dependency for both CO$_2$-L and CO-L indices. Under equilibrium chemistry and isothermal thermal structure assumptions, we find that the planet sample favors super-solar metallicity and low C/O ratio ($<$0.7). In addition, the presence of a mass-metallicity correlation is favored over uniform metallicity with the eight planets. We further introduce the SO$_2$-L versus CO$_2$-L diagram alike the color-magnitude diagram for stars and brown dwarfs. All reported trends here will be testable and be further quantified with existing and future JWST observations within the next few years., Comment: Accepted to ApJ, JWST keeps on delivering!

We present a disease transmission model that considers both explicit and non-explicit factors. This approach is crucial for accurate prediction and control of infectious disease spread. In this paper, we extend the spread model from our previous works \cite{ban2021mathematical,ban2023randomspread, ban2023mathematical, ban2023spread} to a projected spread model that considers both hidden and explicit types. Additionally, we provide the spread rate for the projected spread model corresponding to the topological and random models. Furthermore, examples and numerical results are provided to illustrate the theory.

We investigate the parameter recovery of Markov-switching ordinary differential processes from discrete observations, where the differential equations are nonlinear additive models. This framework has been widely applied in biological systems, control systems, and other domains; however, limited research has been conducted on reconstructing the generating processes from observations. In contrast, many physical systems, such as human brains, cannot be directly experimented upon and rely on observations to infer the underlying systems. To address this gap, this manuscript presents a comprehensive study of the model, encompassing algorithm design, optimization guarantees, and quantification of statistical errors. Specifically, we develop a two-stage algorithm that first recovers the continuous sample path from discrete samples and then estimates the parameters of the processes. We provide novel theoretical insights into the statistical error and linear convergence guarantee when the processes are $\beta$-mixing. Our analysis is based on the truncation of the latent posterior processes and demonstrates that the truncated processes approximate the true processes under mixing conditions. We apply this model to investigate the differences in resting-state brain networks between the ADHD group and normal controls, revealing differences in the transition rate matrices of the two groups.

Scientific user facilities, such as synchrotron beamlines, are equipped with a wide array of hardware and software tools that require a codebase for human-computer-interaction. This often necessitates developers to be involved to establish connection between users/researchers and the complex instrumentation. The advent of generative AI presents an opportunity to bridge this knowledge gap, enabling seamless communication and efficient experimental workflows. Here we present a modular architecture for the Virtual Scientific Companion (VISION) by assembling multiple AI-enabled cognitive blocks that each scaffolds large language models (LLMs) for a specialized task. With VISION, we performed LLM-based operation on the beamline workstation with low latency and demonstrated the first voice-controlled experiment at an X-ray scattering beamline. The modular and scalable architecture allows for easy adaptation to new instrument and capabilities. Development on natural language-based scientific experimentation is a building block for an impending future where a science exocortex -- a synthetic extension to the cognition of scientists -- may radically transform scientific practice and discovery.

The rise of large language models (LLMs) and their tight integration into our daily life make it essential to dedicate efforts towards their trustworthiness. Uncertainty quantification for LLMs can establish more human trust into their responses, but also allows LLM agents to make more informed decisions based on each other's uncertainty. To estimate the uncertainty in a response, internal token logits, task-specific proxy models, or sampling of multiple responses are commonly used. This work focuses on asking the LLM itself to verbalize its uncertainty with a confidence score as part of its output tokens, which is a promising way for prompt- and model-agnostic uncertainty quantification with low overhead. Using an extensive benchmark, we assess the reliability of verbalized confidence scores with respect to different datasets, models, and prompt methods. Our results reveal that the reliability of these scores strongly depends on how the model is asked, but also that it is possible to extract well-calibrated confidence scores with certain prompt methods. We argue that verbalized confidence scores can become a simple but effective and versatile uncertainty quantification method in the future. Our code is available at https://github.com/danielyxyang/llm-verbalized-uq .

In this paper, we introduce DirectorLLM, a novel video generation model that employs a large language model (LLM) to orchestrate human poses within videos. As foundational text-to-video models rapidly evolve, the demand for high-quality human motion and interaction grows. To address this need and enhance the authenticity of human motions, we extend the LLM from a text generator to a video director and human motion simulator. Utilizing open-source resources from Llama 3, we train the DirectorLLM to generate detailed instructional signals, such as human poses, to guide video generation. This approach offloads the simulation of human motion from the video generator to the LLM, effectively creating informative outlines for human-centric scenes. These signals are used as conditions by the video renderer, facilitating more realistic and prompt-following video generation. As an independent LLM module, it can be applied to different video renderers, including UNet and DiT, with minimal effort. Experiments on automatic evaluation benchmarks and human evaluations show that our model outperforms existing ones in generating videos with higher human motion fidelity, improved prompt faithfulness, and enhanced rendered subject naturalness.

This Letter presents an investigation of low-energy electron-neutrino interactions in the Fermilab Booster Neutrino Beam by the MicroBooNE experiment, motivated by the excess of electron-neutrino-like events observed by the MiniBooNE experiment. This is the first measurement to use data from all five years of operation of the MicroBooNE experiment, corresponding to an exposure of $1.11\times 10^{21}$ protons on target, a $70\%$ increase on past results. Two samples of electron neutrino interactions without visible pions are used, one with visible protons and one without any visible protons. MicroBooNE data is compared to two empirical models that modify the predicted rate of electron-neutrino interactions in different variables in the simulation to match the unfolded MiniBooNE low energy excess. In the first model, this unfolding is performed as a function of electron neutrino energy, while the second model aims to match the observed shower energy and angle distributions of the MiniBooNE excess. This measurement excludes an electron-like interpretation of the MiniBooNE excess based on these models at $> 99\%$ CL$_\mathrm{s}$ in all kinematic variables., Comment: 8 pages, 5 figures, 1 table

We give Euler-like recursive formulas for the $t$-colored partition function when $t=2$ or $t=3,$ as well as for all $t$-regular partition functions. In particular, we derive an infinite family of ``triangular number" recurrences for the $3$-colored partition function. Our proofs are inspired by the recent work of Gomez, Ono, Saad, and Singh on the ordinary partition function and make extensive use of $q$-series identities for $(q;q)_{\infty}$ and $(q;q)_{\infty}^3.$, Comment: 12 pages, 2 tables, corrected a typo in Theorem 1.1, added a new reference

In Industry 4.0, the digital twin is one of the emerging technologies, offering simulation abilities to predict, refine, and interpret conditions and operations, where it is crucial to emphasize a heightened concentration on the associated security and privacy risks. To be more specific, the adoption of digital twins in the manufacturing industry relies on integrating technologies like cyber-physical systems, the Industrial Internet of Things, virtualization, and advanced manufacturing. The interactions of these technologies give rise to numerous security and privacy vulnerabilities that remain inadequately explored. Towards that end, this paper analyzes the cybersecurity threats of digital twins for advanced manufacturing in the context of data collection, data sharing, machine learning and deep learning, and system-level security and privacy. We also provide several solutions to the threats in those four categories that can help establish more trust in digital twins.

Recent works in clustering-based topic models perform well in monolingual topic identification by introducing a pipeline to cluster the contextualized representations. However, the pipeline is suboptimal in identifying topics across languages due to the presence of language-dependent dimensions (LDDs) generated by multilingual language models. To address this issue, we introduce a novel, SVD-based dimension refinement component into the pipeline of the clustering-based topic model. This component effectively neutralizes the negative impact of LDDs, enabling the model to accurately identify topics across languages. Our experiments on three datasets demonstrate that the updated pipeline with the dimension refinement component generally outperforms other state-of-the-art cross-lingual topic models., Comment: Accepted to 18th BUCC Workshop at COLING 2025

For a complex manifold $\Sigma $ with $\mathbb{C}^{\ast }$-action, we define the $m$-th $\mathbb{C}^{\ast }$ Fourier-Dolbeault cohomology group and consider the $m$-index on $\Sigma $. By applying the method of transversal heat kernel asymptotics, we obtain a local index formula for the $m$-index. We can reinterpret Kawasaki's Hirzebruch-Riemann-Roch formula for a compact complex orbifold with an orbifold holomorphic line bundle by our integral formulas over a (smooth) complex manifold and finitely many complex submanifolds arising from singular strata. We generalize $\mathbb{C}^{\ast }$-action to complex reductive Lie group $G$-action on a compact or noncompact complex manifold. Among others, we study the nonextendability of open group action and the space of all $G$-invariant holomorphic $p$-forms. Finally, in the case of two compatible holomorphic $\mathbb{C}^{\ast }$-actions, a mirror-type isomorphism is found between two linear spaces of holomorphic forms, and the Euler characteristic associated with these spaces can be computed by our $\mathbb{C}^{\ast }$ local index formula on the total space. In the perspective of the equivariant algebraic cobordism theory $\Omega _{\ast }^{\mathbb{C}^{\ast }}(\Sigma ),$ a speculative connection is remarked. Possible relevance to the recent development in physics and number theory is briefly mentioned., Comment: 129 pages

With the development of intelligence, the combination of big data and judicial practice has become a hot research topic. There are fewer studies on credit card contract disputes related to big data, which makes it difficult to respond to the trend of Big data era. This paper uses the data source of credit card disputes related to the protection of personal information in Beijing from 2022 to 2024, introduces a social network analysis methodology to analyse validated judgements and creates a database. Through the analysis of the relationship network indicators of applicable laws and regulations, it can clearly show the laws and regulations applicable to this type of dispute in China in terms of substantive and procedural matters. This paper provides a methodology for combining big data with judicial trials and assisting judges in trials. The effective use of social networks will help fill the gap in the application of big data in judicial trials. The result and discussion of the paper is also of practical significance for improving the efficiency of judicial adjudication, constructing a database for searching classified cases, constructing a holistic system for digital courts, and finally promoting justice.

Due to its peculiar and highly variable nature, the blazar 3C 454.3 has been extensively monitored by the WEBT team. Here, we present for the first time these long-term optical flux and color variability results using data acquired in B, V, R, and I bands over a time span of $\sim$ 2 decades. We include data from WEBT collaborators and public archives such as SMARTS, Steward Observatory, and ZTF. The data are binned and segmented to study the source over this long term when more regular sampling was available. During our study, the long-term spectral variability reveals a redder when brighter (RWB) trend, which, however, stabilizes at a particular brightness cutoff $\sim$ 14.5 mag in the I-band, after which it saturates and evolves into a complex state. This trend indicates increasing jet emission dominance over accretion disk emission until jet emission completely dominates. Plots of the spectral index variation (following $F_{\nu} \propto \nu^{-\alpha}$) reveal a bimodal distribution using a one-day binning. These correlate with two extreme phases of 3C 454.3, an outburst or high flux state and quiescent or low flux state, which are respectively jet and accretion disk dominated. We have also conducted intra-day variability studies of nine light curves and found that six of them are variable. Discrete Correlation Function (DCF) analysis between different optical waveband pairs peak at zero lags, indicating co-spatial emission in different optical bands., Comment: 18 pages, 6 figures, 5 tables

Multimodal incremental learning needs to digest the information from multiple modalities while concurrently learning new knowledge without forgetting the previously learned information. There are numerous challenges for this task, mainly including the larger storage size of multimodal data in exemplar-based methods and the computational requirement of finetuning on huge multimodal models. In this paper, we leverage the parameter-efficient tuning scheme to reduce the burden of fine-tuning and propose the exemplar masking framework to efficiently replay old knowledge. Specifically, the non-important tokens are masked based on the attention weights and the correlation across different modalities, significantly reducing the storage size of an exemplar and consequently saving more exemplars under the same memory buffer. Moreover, we design a multimodal data augmentation technique to diversify exemplars for replaying prior knowledge. In experiments, we not only evaluate our method in existing multimodal datasets but also extend the ImageNet-R dataset to a multimodal dataset as a real-world application, where captions are generated by querying multimodal large language models (e.g., InstructBLIP). Extensive experiments show that our exemplar masking framework is more efficient and robust to catastrophic forgetting under the same limited memory buffer. Code is available at https://github.com/YiLunLee/Exemplar_Masking_MCIL., Comment: Project page: https://github.com/YiLunLee/Exemplar_Masking_MCIL

While the capacity to self-regulate has been found to be crucial for secondary school students, prior studies often rely on self-report surveys and think-aloud protocols that present notable limitations in capturing self-regulated learning (SRL) processes. This study advances the understanding of SRL in secondary education by using trace data to examine SRL processes during multi-source writing tasks, with higher education participants included for comparison. We collected fine-grained trace data from 66 secondary school students and 59 university students working on the same writing tasks within a shared SRL-oriented learning environment. The data were labelled using Bannert's validated SRL coding scheme to reflect specific SRL processes, and we examined the relationship between these processes, essay performance, and educational levels. Using epistemic network analysis (ENA) to model and visualise the interconnected SRL processes in Bannert's coding scheme, we found that: (a) secondary school students predominantly engaged in three SRL processes -- Orientation, Re-reading, and Elaboration/Organisation; (b) high-performing secondary students engaged more in Re-reading, while low-performing students showed more Orientation process; and (c) higher education students exhibited more diverse SRL processes such as Monitoring and Evaluation than their secondary education counterparts, who heavily relied on following task instructions and rubrics to guide their writing. These findings highlight the necessity of designing scaffolding tools and developing teacher training programs to enhance awareness and development of SRL skills for secondary school learners.

While large vision-language models (LVLMs) have shown impressive capabilities in generating plausible responses correlated with input visual contents, they still suffer from hallucinations, where the generated text inaccurately reflects visual contents. To address this, recent approaches apply contrastive decoding to calibrate the model's response via contrasting output distributions with original and visually distorted samples, demonstrating promising hallucination mitigation in a training-free manner. However, the potential of changing information in visual inputs is not well-explored, so a deeper investigation into the behaviors of visual contrastive decoding is of great interest. In this paper, we first explore various methods for contrastive decoding to change visual contents, including image downsampling and editing. Downsampling images reduces the detailed textual information while editing yields new contents in images, providing new aspects as visual contrastive samples. To further study benefits by using different contrastive samples, we analyze probability-level metrics, including entropy and distribution distance. Interestingly, the effect of these samples in mitigating hallucinations varies a lot across LVLMs and benchmarks. Based on our analysis, we propose a simple yet effective method to combine contrastive samples, offering a practical solution for applying contrastive decoding across various scenarios. Extensive experiments are conducted to validate the proposed fusion method among different benchmarks., Comment: Under review. Project pages: https://github.com/YiLunLee/VCD_Analysis

Recent advances in vision-language models (VLMs) have made significant progress in downstream tasks that require quantitative concepts such as facial age estimation and image quality assessment, enabling VLMs to explore applications like image ranking and retrieval. However, existing studies typically focus on the reasoning based on a single image and heavily depend on text prompting, limiting their ability to learn comprehensive understanding from multiple images. To address this, we propose an effective yet efficient approach that reframes the CLIP model into a learning-to-rank task and introduces a lightweight adapter to augment CLIP for text-guided image ranking. Specifically, our approach incorporates learnable prompts to adapt to new instructions for ranking purposes and an auxiliary branch with ranking-aware attention, leveraging text-conditioned visual differences for additional supervision in image ranking. Our ranking-aware adapter consistently outperforms fine-tuned CLIPs on various tasks and achieves competitive results compared to state-of-the-art models designed for specific tasks like facial age estimation and image quality assessment. Overall, our approach primarily focuses on ranking images with a single instruction, which provides a natural and generalized way of learning from visual differences across images, bypassing the need for extensive text prompts tailored to individual tasks. Code is available: https://github.com/uynaes/RankingAwareCLIP., Comment: github link: https://github.com/uynaes/RankingAwareCLIP

Isolated attosecond pulses (IAPs) generated by few-cycle femtosecond lasers are essential for capturing ultrafast dynamics in atoms, molecules, and solids. Nonetheless, the advancement of attosecond science critically depends on achieving stable, high-temporal-contrast IAPs. Our study reveals a universal scenario in which self-compression of the infrared driver in high harmonic generation in extended gas media leads to high-contrast high-frequency IAP generation. Our experimental and theoretical results reveal that filamentation in a semi-infinite gas cell not only shapes the infrared driving pulse spatially and temporally, but also creates a stable propagation region where high harmonic generation is phase-matched, leading to the production of bright IAPs. In an argon-filled gas cell, filamentation notably reduces the pulse duration of Yb-based 1030 nm pulses from 4.7 fs to 3.5 fs, while simultaneously generating high-contrast 200-attosecond IAPs at 70 eV. We demonstrate the universality of filamentation-assisted IAP generation, showing that post-compressed Yb-based laser filaments in neon and helium yield even shorter IAPs: 69-attoseconds at 100 eV, and 65-attoseconds IAPs at 135 eV, respectively. This spatiotemporal reshaping of few-cycle pulses through filamentation possesses immediate impacts on both post-compression techniques and attosecond-based technologies.

Hot dust-obscured galaxies (Hot DOGs), are a family of hyper-luminous, heavily obscured quasars. A number of studies have shown that these objects reside in significantly overdense regions of the Universe based on the identification of companions at optical through far-IR wavelengths. Here we present further characterization of their environments by studying the surface density of Lyman break galaxy (LBG) candidates in the vicinity of three Hot DOGs. For two of them, WISE J041010.60-091305.2 at z=3.631 and WISE J083153.25+014010.8 at z=3.912, we identify the candidate LBG companions using deep observations obtained with Baade/IMACS. For the third, WISE J224607.56-052634.9 at z=4.601, we re-analyse previously published data obtained with Gemini-S/GMOS-S. We optimise the LBG photometric selection criteria at the redshift of each target using the COSMOS2020 catalog. When comparing the density of LBG candidates found in the vicinity of these Hot DOGs with that in the COSMOS2020 catalog, we find overdensities of $\delta=1.83\pm 0.08$ ($\delta' = 7.49\pm 0.68$), $\delta=4.67\pm 0.21$ ($\delta' = 29.17\pm 2.21$), and $\delta = 2.36\pm 0.25$ ($\delta' = 11.60\pm 1.96$) around W0410-0913, W0831+0140, and W2246-0526, respectively, without (with) contamination correction. Additionally, we find that the overdensities are centrally concentrated around each Hot DOG. Our analysis also reveals that the overdensity of the fields surrounding W0410-0913 and W0831+0140 declines steeply beyond physical scales of $\sim$2 Mpc. If these overdensities evolve to clusters by z=0, these results suggest that the Hot DOG may correspond to the early formation stages of the brightest cluster galaxy. We were unable to determine if this is also the case for W2246-0526 due to the smaller field of view of the GMOS-S observations. Our results imply that Hot DOGs may be excellent tracers of protoclusters., Comment: Accepted for publication in A&A, the manuscript consists of 14 pages, 16 figures, and 4 tables

The BL Lac object 3C 371 is one of the targets that are regularly monitored by the Whole Earth Blazar Telescope (WEBT) Collaboration to study blazar variability on both short and long timescales. We aim to evaluate the long-term multiwavelength (MWL) behaviour of 3C 371, comparing it with the results derived for its optical emission in our previous study. For this, we make use of the multi-band campaigns organized by the WEBT Collaboration in optical and radio between January 2018 and December 2020, and of public data from Swift and Fermi satellites and the MOJAVE Very Large Interferometry programme. We evaluate the variability shown by the source in each band with the amplitude variability quantification, as well as possible interband correlation using the z-Discrete Correlation Function. We also present a deep analysis of the optical-UV, X-ray and $\gamma$-ray spectral variability. With the MOJAVE data we perform a kinematics analysis, looking for components propagating along the jet, calculating its kinematics parameters. This set of parameters is later used for the interpretation of the source MWL behaviour, modelling the broadband spectral energy distribution (SED) of the source with theoretical blazar emission scenarios., Comment: Accepted in A&A, 23 pages, 15 figures

We report integral field spectroscopy observations with the Near-Infrared Spectrograph on board JWST targeting the 60 kpc environment surrounding the most luminous quasar known at $z=4.6$. We detect ionized gas filaments on 40 kpc scales connecting a network of merging galaxies likely to form a cluster. We find regions of low ionization consistent with large-scale shock excitation surrounding the central dust-obscured quasar, out to distances nearly eight times the effective stellar radius of the quasar host galaxy. In the nuclear region, we find an ionized outflow driven by the quasar with velocities reaching 13,000 km s$^{-1}$, one of the fastest discovered to date with an outflow rate of 2000 M$_\odot$ yr$^{-1}$ and a kinetic luminosity of 6$\times10^{46}$ erg s$^{-1}$ resulting in coupling efficiency between the bolometric luminosity of the quasar and the outflow of 5%. The kinetic luminosity of the outflow is sufficient to power the turbulent motion of the gas on galactic and circumgalactic scales and is likely the primary driver of the radiative shocks on interstellar medium and circumgalactic medium scales. This provides compelling evidence supporting long-standing theoretical predictions that powerful quasar outflows are a main driver in regulating the heating and accretion rate of gas onto massive central cluster galaxies., Comment: 16 pages, 9 figures, 1 table, submitted to ApJ

Emerging superionic conductors Li3InCl6 (LIC) and Li6PS5Cl (LPSC) are very promising for solid-state electrolytes (SSEs) in all-solid-state lithium batteries (ASSLBs). However, unstable lithium-anode interfaces in LIC and LPSC have been observed through experiments and ab initio calculations, while the interphases formed in determining interfacial stability remain unclear. In this study, we investigate the ab initio stability of LIC-Li and LPSC-Li interfaces and interphases. Our ab initio calculations revealed that both interfaces are not chemically or electrochemically thermodynamically stable. Interestingly, the LPSC-Li has a stable interphase, but the LIC-Li doesn't. Moreover, the interlayers were systematically evaluated for the LIC-Li and LPSC-Li interfaces, and the desired interlayer materials are clarified for the two interfaces. This ab initio understanding of the interfaces, interphases and interlayers would help the development of a variety of stable interfaces in ASSLBs.

In [Amer. J. Math. 141 (2019), no. 5, 1281-1315], Ren and Wang proved the curvature estimates for the $n-1$ curvature equation. The purpose of this note is to give a simple proof of their theorem., Comment: 13 pages

In this study, we aim to determine and solve the deficiency of Stable Diffusion Inpainting (SDI) in following the instruction of both prompt and mask. Due to the training bias from masking, the inpainting quality is hindered when the prompt instruction and image condition are not related. Therefore, we conduct a detailed analysis of the internal representations learned by SDI, focusing on how the mask input influences the cross-attention layer. We observe that adapting text key tokens toward the input mask enables the model to selectively paint within the given area. Leveraging these insights, we propose FreeCond, which adjusts only the input mask condition and image condition. By increasing the latent mask value and modifying the frequency of image condition, we align the cross-attention features with the model's training bias to improve generation quality without additional computation, particularly when user inputs are complicated and deviate from the training setup. Extensive experiments demonstrate that FreeCond can enhance any SDI-based model, e.g., yielding up to a 60% and 58% improvement of SDI and SDXLI in the CLIP score.

The rapid advancement of generative models has introduced serious risks, including deepfake techniques for facial synthesis and editing. Traditional approaches rely on training classifiers and enhancing generalizability through various feature extraction techniques. Meanwhile, training-free detection methods address issues like limited data and overfitting by directly leveraging statistical properties from vision foundation models to distinguish between real and fake images. The current leading training-free approach, RIGID, utilizes DINOv2 sensitivity to perturbations in image space for detecting fake images, with fake image embeddings exhibiting greater sensitivity than those of real images. This observation prompts us to investigate how detection performance varies across model backbones, perturbation types, and datasets. Our experiments reveal that detection performance is closely linked to model robustness, with self-supervised (SSL) models providing more reliable representations. While Gaussian noise effectively detects general objects, it performs worse on facial images, whereas Gaussian blur is more effective due to potential frequency artifacts. To further improve detection, we introduce Contrastive Blur, which enhances performance on facial images, and MINDER (MINimum distance DetEctoR), which addresses noise type bias, balancing performance across domains. Beyond performance gains, our work offers valuable insights for both the generative and detection communities, contributing to a deeper understanding of model robustness property utilized for deepfake detection.

Modern laser plasma accelerators (LPAs) often require meter-scale plasma waveguides to propagate a high-intensity drive laser pulse. Tapering the longitudinal gas density profile in meter-scale gas jets could allow for single stage laser plasma acceleration well beyond 10 GeV with current petawatt-class laser systems. Via simulation and interferometry measurements, we show density control by longitudinally adjusting the throat width and jet angle. Density profiles appropriate for tapering were calculated analytically and via particle-in-cell (PIC) simulations, and were matched experimentally. These simulations show that tapering can increase electron beam energy using 19 J laser energy from $\sim$9 GeV to $>$12 GeV in a 30 cm plasma, and the accelerated charge by an order of magnitude.

We present a novel neural algorithm for performing high-quality, high-resolution, real-time novel view synthesis. From a sparse set of input RGB images or videos streams, our network both reconstructs the 3D scene and renders novel views at 1080p resolution at 30fps on an NVIDIA A100. Our feed-forward network generalizes across a wide variety of datasets and scenes and produces state-of-the-art quality for a real-time method. Our quality approaches, and in some cases surpasses, the quality of some of the top offline methods. In order to achieve these results we use a novel combination of several key concepts, and tie them together into a cohesive and effective algorithm. We build on previous works that represent the scene using semi-transparent layers and use an iterative learned render-and-refine approach to improve those layers. Instead of flat layers, our method reconstructs layered depth maps (LDMs) that efficiently represent scenes with complex depth and occlusions. The iterative update steps are embedded in a multi-scale, UNet-style architecture to perform as much compute as possible at reduced resolution. Within each update step, to better aggregate the information from multiple input views, we use a specialized Transformer-based network component. This allows the majority of the per-input image processing to be performed in the input image space, as opposed to layer space, further increasing efficiency. Finally, due to the real-time nature of our reconstruction and rendering, we dynamically create and discard the internal 3D geometry for each frame, generating the LDM for each view. Taken together, this produces a novel and effective algorithm for view synthesis. Through extensive evaluation, we demonstrate that we achieve state-of-the-art quality at real-time rates. Project page: https://quark-3d.github.io/, Comment: SIGGRAPH Asia 2024 camera ready version; project page https://quark-3d.github.io/

Predicting electronic band structures from crystal structures is crucial for understanding structure-property correlations in materials science. First-principles approaches are accurate but computationally intensive. Recent years, machine learning (ML) has been extensively applied to this field, while existing ML models predominantly focus on band gap predictions or indirect band structure estimation via solving predicted Hamiltonians. An end-to-end model to predict band structure accurately and efficiently is still lacking. Here, we introduce a graph Transformer-based end-to-end approach that directly predicts band structures from crystal structures with high accuracy. Our method leverages the continuity of the k-path and treat continuous bands as a sequence. We demonstrate that our model not only provides accurate band structure predictions but also can derive other properties (such as band gap, band center, and band dispersion) with high accuracy. We verify the model performance on large and diverse datasets., Comment: 8 pages, 3 figures

Long-period radio transients (LPTs) are a newly discovered class of radio emitters with yet incomprehensibly long rotation periods, ranging from minutes to hours. The astrophysical nature of their isolated counterparts remains undetermined. We report a new LPT, DART J1832-0911 (2656.23 $\pm$ 0.15 s period), the first evidence associating such objects to supernova remnants (SNRs). Its dispersion measure distance aligns well with the distance of the SNR, confirming its origin from a supernova explosion. The source displays either phase-locked circularly polarized emission or nearly 100% linear polarization in radio bands. No detectable optical counterpart was found, even with a 10 m class telescope. The J1832-0911's SNR association, stable, highly polarized emission, and abnormally long period strongly favor its origin from a young neutron star, whose spin has been braked, possibly by interaction with supernova's fallback materials. This discovery provides critical insights into the nature of ultra-long period transients and their evolutionary link to stellar remnants., Comment: 36 pages, 12 figures

We synthesized crystalline films of neodymium nickel oxide (NdNiO3), a perovskite quantum material, switched the films from a metal phase (intrinsic) into an insulator phase (electron-doped) by field-driven lithium-ion intercalation, and characterized their structural and optical properties. Time-of-flight secondary-ion mass spectrometry (ToF-SIMS) showed that the intercalation process resulted in a gradient of the dopant concentration along the thickness direction of the films, turning the films into insulator-metal bilayers. We used variable-angle spectroscopic ellipsometry to measure the complex refractive indices of the metallic and insulating phases of NdNiO3. The insulator phase has a refractive index of n ~ 2 and low absorption in the visible and near infrared, and analysis of the complex refractive indices indicated that the band gap of the insulating phase is roughly 3-4 eV. Electrical control of the optical band gap, with corresponding large changes to the optical refractive indices, creates new opportunities for tunable optics., Comment: Main text + supplementary

There is widespread concern about the negative impacts of social media feed ranking algorithms on political polarization. Leveraging advancements in large language models (LLMs), we develop an approach to re-rank feeds in real-time to test the effects of content that is likely to polarize: expressions of antidemocratic attitudes and partisan animosity (AAPA). In a preregistered 10-day field experiment on X/Twitter with 1,256 consented participants, we increase or decrease participants' exposure to AAPA in their algorithmically curated feeds. We observe more positive outparty feelings when AAPA exposure is decreased and more negative outparty feelings when AAPA exposure is increased. Exposure to AAPA content also results in an immediate increase in negative emotions, such as sadness and anger. The interventions do not significantly impact traditional engagement metrics such as re-post and favorite rates. These findings highlight a potential pathway for developing feed algorithms that mitigate affective polarization by addressing content that undermines the shared values required for a healthy democracy.

Green Peas (GPs) and blueberry galaxies (BBs) are thought to be local analogs ($z<$0.1) of high redshift Ly$\alpha$ emitters. H I study of these can help us understand the star formation in the primordial Universe. In this Letter, we present the results of H I 21 cm study of 28 high specific star formation rate (sSFR $\gtrsim$10$^{-8}$ yr$^{-1}$) BBs at $z\lesssim$0.05 with the Five-hundred-meter Aperture Spherical radio Telescope. We report significant H I detection towards two BBs namely J1026+0426 and J1132+0809, and discuss possible H I contribution from neighboring galaxies. The median 3$\sigma$ upper limit of $\sim$2.0$\times$10$^{8}$ M$_{\odot}$ was obtained on H I mass for galaxies with nondetections. We find BBs tend to have lower H I-to-stellar mass ratio or gas fraction ($f_{\rm HI}$) than expected from $f_{\rm HI}$-sSFR and $f_{\rm HI}$-$M_{\ast}$ relations for main-sequence galaxies. The BBs also have a median 3$\sigma$ upper limit on H I gas depletion time scale ($\tau_{\rm HI}$) $\sim$0.5 Gyr, about 1 order of magnitude lower than $\tau_{\rm HI}$ for local main-sequence galaxies. We find a significantly low H I detection rate of 2/28 (7.1$^{+9.4}_{-4.6}$ \%) towards these galaxies, which is similar to previous H I studies of low redshift GPs of high ionization parameter indicator, O32 $\equiv$O[{\sc iii}]$\lambda$5007/O[{\sc ii}]$\lambda$3727 ratios $\gtrsim$10., Comment: 10 pages, 4 figures, 1 table, accepted for publication in the Astrophysical Journal Letters (ApJL), this is proof corrected version

The standardization of an interface for dense linear algebra operations in the BLAS standard has enabled interoperability between different linear algebra libraries, thereby boosting the success of scientific computing, in particular in scientific HPC. Despite numerous efforts in the past, the community has not yet agreed on a standardization for sparse linear algebra operations due to numerous reasons. One is the fact that sparse linear algebra objects allow for many different storage formats, and different hardware may favor different storage formats. This makes the definition of a FORTRAN-style all-circumventing interface extremely challenging. Another reason is that opposed to dense linear algebra functionality, in sparse linear algebra, the size of the sparse data structure for the operation result is not always known prior to the information. Furthermore, as opposed to the standardization effort for dense linear algebra, we are late in the technology readiness cycle, and many production-ready software libraries using sparse linear algebra routines have implemented and committed to their own sparse BLAS interface. At the same time, there exists a demand for standardization that would improve interoperability, and sustainability, and allow for easier integration of building blocks. In an inclusive, cross-institutional effort involving numerous academic institutions, US National Labs, and industry, we spent two years designing a hardware-portable interface for basic sparse linear algebra functionality that serves the user needs and is compatible with the different interfaces currently used by different vendors. In this paper, we present a C++ API for sparse linear algebra functionality, discuss the design choices, and detail how software developers preserve a lot of freedom in terms of how to implement functionality behind this API., Comment: 43 pages

Accurate segmentation of Optical Coherence Tomography (OCT) images is crucial for diagnosing and monitoring retinal diseases. However, the labor-intensive nature of pixel-level annotation limits the scalability of supervised learning with large datasets. Weakly Supervised Semantic Segmentation (WSSS) provides a promising alternative by leveraging image-level labels. In this study, we propose a novel WSSS approach that integrates structural guidance with text-driven strategies to generate high-quality pseudo labels, significantly improving segmentation performance. In terms of visual information, our method employs two processing modules that exchange raw image features and structural features from OCT images, guiding the model to identify where lesions are likely to occur. In terms of textual information, we utilize large-scale pretrained models from cross-domain sources to implement label-informed textual guidance and synthetic descriptive integration with two textual processing modules that combine local semantic features with consistent synthetic descriptions. By fusing these visual and textual components within a multimodal framework, our approach enhances lesion localization accuracy. Experimental results on three OCT datasets demonstrate that our method achieves state-of-the-art performance, highlighting its potential to improve diagnostic accuracy and efficiency in medical imaging., Comment: 21 pages, 9 figures, 8 tables

Under a multinormal distribution with an arbitrary unknown covariance matrix, the main purpose of this paper is to propose a framework to achieve the goal of reconciliation of Bayesian, frequentist, and Fisher's reporting $p$-values, Neyman-Pearson's optimal theory and Wald's decision theory for the problems of testing mean against restricted alternatives (closed convex cones). To proceed, the tests constructed via the likelihood ratio (LR) and the union-intersection (UI) principles are studied. For the problems of testing against restricted alternatives, first, we show that the LRT and the UIT are not the proper Bayes tests, however, they are shown to be the integrated LRT and the integrated UIT, respectively. For the problem of testing against the positive orthant space alternative, both the null distributions of the LRT and the UIT depend on the unknown nuisance covariance matrix. Hence we have difficulty adopting Fisher's approach to reporting $p$-values. On the other hand, according to the definition of the level of significance, both the LRT and the UIT are shown to be power-dominated by the corresponding LRT and UIT for testing against the half-space alternative, respectively. Hence, both the LRT and the UIT are $\alpha$-inadmissible, these results are against the common statistical sense. Neither Fisher's approach of reporting $p$-values alone nor Neyman-Pearson's optimal theory for power function alone is a satisfactory criterion for evaluating the performance of tests. Wald's decision theory via $d$-admissibility may shed light on resolving these challenging issues of imposing the balance between type 1 error and power., Comment: arXiv admin note: substantial text overlap with arXiv:1710.06573

Millimeter-wave refracting telescopes targeting the degree-scale structure of the cosmic microwave background (CMB) have recently grown to diffraction-limited apertures of over 0.5 meters. These instruments are entirely housed in vacuum cryostats to support their sub-kelvin bolometric detectors and to minimize radiative loading from thermal emission due to absorption loss in their transmissive optical elements. The large vacuum window is the only optical element in the system at ambient temperature, and therefore minimizing loss in the window is crucial for maximizing detector sensitivity. This motivates the use of low-loss polymer materials and a window as thin as practicable. However, the window must simultaneously meet the requirement to keep sufficient vacuum, and therefore must limit gas permeation and remain mechanically robust against catastrophic failure under pressure. We report on the development of extremely thin composite polyethylene window technology that meets these goals. Two windows have been deployed for two full observing seasons on the BICEP3 and BA150 CMB telescopes at the South Pole. On BICEP3, the window has demonstrated a 6% improvement in detector sensitivity., Comment: 20 pages, 12 figures, 4 tables

The human brain receives nutrients and oxygen through an intricate network of blood vessels. Pathology affecting small vessels, at the mesoscopic scale, represents a critical vulnerability within the cerebral blood supply and can lead to severe conditions, such as Cerebral Small Vessel Diseases. The advent of 7 Tesla MRI systems has enabled the acquisition of higher spatial resolution images, making it possible to visualise such vessels in the brain. However, the lack of publicly available annotated datasets has impeded the development of robust, machine learning-driven segmentation algorithms. To address this, the SMILE-UHURA challenge was organised. This challenge, held in conjunction with the ISBI 2023, in Cartagena de Indias, Colombia, aimed to provide a platform for researchers working on related topics. The SMILE-UHURA challenge addresses the gap in publicly available annotated datasets by providing an annotated dataset of Time-of-Flight angiography acquired with 7T MRI. This dataset was created through a combination of automated pre-segmentation and extensive manual refinement. In this manuscript, sixteen submitted methods and two baseline methods are compared both quantitatively and qualitatively on two different datasets: held-out test MRAs from the same dataset as the training data (with labels kept secret) and a separate 7T ToF MRA dataset where both input volumes and labels are kept secret. The results demonstrate that most of the submitted deep learning methods, trained on the provided training dataset, achieved reliable segmentation performance. Dice scores reached up to 0.838 $\pm$ 0.066 and 0.716 $\pm$ 0.125 on the respective datasets, with an average performance of up to 0.804 $\pm$ 0.15.

Accurate segmentation of retinal images plays a crucial role in aiding ophthalmologists in diagnosing retinopathy of prematurity (ROP) and assessing its severity. However, due to their underdeveloped, thinner vessels, manual annotation in infant fundus images is very complex, and this presents challenges for fully supervised learning. To address the scarcity of annotations, we propose a semi supervised segmentation framework designed to advance ROP studies without the need for extensive manual vessel annotation. Unlike previous methods that rely solely on limited labeled data, our approach leverages teacher student learning by integrating two powerful components: an uncertainty weighted vessel unveiling module and domain adversarial learning. The vessel unveiling module helps the model effectively reveal obscured and hard to detect vessel structures, while adversarial training aligns feature representations across different domains, ensuring robust and generalizable vessel segmentations. We validate our approach on public datasets (CHASEDB, STARE) and an in-house ROP dataset, demonstrating its superior performance across multiple evaluation metrics. Additionally, we extend the model's utility to a downstream task of ROP multi-stage classification, where vessel masks extracted by our segmentation model improve diagnostic accuracy. The promising results in classification underscore the model's potential for clinical application, particularly in early-stage ROP diagnosis and intervention. Overall, our work offers a scalable solution for leveraging unlabeled data in pediatric ophthalmology, opening new avenues for biomarker discovery and clinical research., Comment: 10 pages, 5 figures