Search

We investigate automated in situ optimization of the potential landscape in a quantum point contact device, using a $3 \times 3$ gate array patterned atop the constriction. Optimization is performed using the covariance matrix adaptation evolutionary strategy, for which we introduce a metric for how "step-like" the conductance is as the channel becomes constricted. We first perform the optimization of the gate voltages in a tight-binding simulation and show how such in situ tuning can be used to mitigate a random disorder potential. The optimization is then performed in a physical device in experiment, where we also observe a marked improvement in the quantization of the conductance resulting from the optimization procedure., Comment: 8 pages, 4 figures (supplement: 6 pages, 3 figures)

Pretrained language models (LMs) can generalize to implications of facts that they are finetuned on. For example, if finetuned on ``John Doe lives in Tokyo," LMs can correctly answer ``What language do the people in John Doe's city speak?'' with ``Japanese''. However, little is known about the mechanisms that enable this generalization or how they are learned during pretraining. We introduce extractive structures as a framework for describing how components in LMs (e.g., MLPs or attention heads) coordinate to enable this generalization. The structures consist of informative components that store training facts as weight changes, and upstream and downstream extractive components that query and process the stored information to produce the correct implication. We hypothesize that extractive structures are learned during pretraining when encountering implications of previously known facts. This yields two predictions: a data ordering effect where extractive structures can be learned only if facts precede their implications, and a weight grafting effect where extractive structures can be transferred to predict counterfactual implications. We empirically demonstrate these phenomena in the OLMo-7b, Llama 3-8b, Gemma 2-9b, and Qwen 2-7b models. Of independent interest, our results also indicate that fact learning can occur at both early and late layers, which lead to different forms of generalization.

$N$-Brownian bees is a branching-selection particle system in $\mathbb{R}^d$ in which $N$ particles behave as independent binary branching Brownian motions, and where at each branching event, we remove the particle furthest from the origin. We study a variant in which $d=1$ and particles have an additional drift $\mu\in\mathbb{R}$. We show that there is a critical value, $\mu_c^N$, and three distinct regimes (sub-critical, critical, and super-critical) and we describe the behaviour of the system in each case. In the sub-critical regime, the system is positive Harris recurrent and has an invariant distribution; in the super-critical regime, the system is transient; and in the critical case, after rescaling, the system behaves like a single reflected Brownian motion. We also show that the critical drift $\mu_c^N$ is in fact the speed of the well-studied $N$-BBM process, and give a rigorous proof for the speed of $N$-BBM, which was missing in the literature., Comment: 35 pages, no figures

Van der Waals magnets are an emerging material family for investigating light-matter interactions and spin-correlated excitations. Here, we report the discovery of a photo-induced state with a lifetime of 17 ps in the van der Waals antiferromagnet NiPS$_3$, which appears exclusively with resonant pumping at 1.476 eV in the antiferromagnetic state. The long-lived state comes with a negative photoconductivity, a characteristic optical response of population inversion. Our findings demonstrate a promising pathway to potentially achieve long-lived lasing at terahertz frequencies in reduced dimensions., Comment: 6 pages, 3 figures. Accepted for publication in Physical Review Letters

We report JWST NIRSpec/G395H observations of TOI-1685 b, a hot rocky super-Earth orbiting an M2.5V star, during a full orbit. We obtain transmission and emission spectra of the planet and characterize the properties of the phase curve, including its amplitude and offset. The transmission spectrum rules out clear H$_2$-dominated atmospheres, while secondary atmospheres (made of water, methane, or carbon dioxide) cannot be statistically distinguished from a flat line. The emission spectrum is featureless and consistent with a blackbody-like brightness temperature, helping rule out thick atmospheres with high mean molecular weight. Collecting all evidence, the properties of TOI-1685 b are consistent with a blackbody with no heat redistribution and a low albedo, with a dayside brightness temperature 0.98$\pm$0.07 times that of a perfect blackbody in the NIRSpec NRS2 wavelength range (3.823-5.172 um). Our results add to the growing number of seemingly airless M-star rocky planets, thus constraining the location of the "Cosmic Shoreline". Three independent data reductions have been carried out, all showing a high-amplitude correlated noise component in the white and spectroscopic light curves. The correlated noise properties are different between the NRS1 and NRS2 detectors - importantly the timescales of the strongest components (4.5 hours and 2.5 hours, respectively) - suggesting the noise is from instrumental rather than astrophysical origins. We encourage the community to look into the systematics of NIRSpec for long time-series observations., Comment: 26 pages, 19 figures, 8 tables. Submitted to AAS Journals

Let $E_2$ be the Morava E-theory of height 2 at the prime 2. In this paper, we compute the homotopy groups of $E_2^{hC_6} \wedge \mathbb{R}P_2$ and $E_2^{hC_6} \wedge \mathbb{R}P_2 \wedge \mathbb{C}P_2$ using the homotopy fixed point spectral sequences.

Torque and continuous rotation are fundamental methods of actuation and manipulation in rigid robots. Soft robot arms use soft materials and structures to mimic the passive compliance of biological arms that bend and extend. This use of compliance prevents soft arms from continuously transmitting and exerting torques to interact with their environment. Here, we show how relying on patterning structures instead of inherent material properties allows soft robotic arms to remain compliant while continuously transmitting torque to their environment. We demonstrate a soft robotic arm made from a pair of mechanical metamaterials that act as compliant constant-velocity joints. The joints are up to 52 times stiffer in torsion than bending and can bend up to 45{\deg}. This robot arm can continuously transmit torque while deforming in all other directions. The arm's mechanical design achieves high motion repeatability (0.4 mm and 0.1{\deg}) when tracking trajectories. We then trained a neural network to learn the inverse kinematics, enabling us to program the arm to complete tasks that are challenging for existing soft robots such as installing light bulbs, fastening bolts, and turning valves. The arm's passive compliance makes it safe around humans and provides a source of mechanical intelligence, enabling it to adapt to misalignment when manipulating objects. This work will bridge the gap between hard and soft robotics with applications in human assistance, warehouse automation, and extreme environments.

Recent advancements in video generation have significantly impacted daily life for both individuals and industries. However, the leading video generation models remain closed-source, resulting in a notable performance gap between industry capabilities and those available to the public. In this report, we introduce HunyuanVideo, an innovative open-source video foundation model that demonstrates performance in video generation comparable to, or even surpassing, that of leading closed-source models. HunyuanVideo encompasses a comprehensive framework that integrates several key elements, including data curation, advanced architectural design, progressive model scaling and training, and an efficient infrastructure tailored for large-scale model training and inference. As a result, we successfully trained a video generative model with over 13 billion parameters, making it the largest among all open-source models. We conducted extensive experiments and implemented a series of targeted designs to ensure high visual quality, motion dynamics, text-video alignment, and advanced filming techniques. According to evaluations by professionals, HunyuanVideo outperforms previous state-of-the-art models, including Runway Gen-3, Luma 1.6, and three top-performing Chinese video generative models. By releasing the code for the foundation model and its applications, we aim to bridge the gap between closed-source and open-source communities. This initiative will empower individuals within the community to experiment with their ideas, fostering a more dynamic and vibrant video generation ecosystem. The code is publicly available at https://github.com/Tencent/HunyuanVideo.

We introduce a new framework for analyzing classification datasets based on the ratios of reconstruction errors between autoencoders trained on individual classes. This analysis framework enables efficient characterization of datasets on the sample, class, and entire dataset levels. We define reconstruction error ratios (RERs) that probe classification difficulty and allow its decomposition into (1) finite sample size and (2) Bayes error and decision-boundary complexity. Through systematic study across 19 popular visual datasets, we find that our RER-based dataset difficulty probe strongly correlates with error rate for state-of-the-art (SOTA) classification models. By interpreting sample-level classification difficulty as a label mistakenness score, we further find that RERs achieve SOTA performance on mislabel detection tasks on hard datasets under symmetric and asymmetric label noise. Our code is publicly available at https://github.com/voxel51/reconstruction-error-ratios., Comment: 30 pages, 18 figures

Wireless minimally invasive bioelectronic implants enable a wide range of applications in healthcare, medicine, and scientific research. Magnetoelectric (ME) wireless power transfer (WPT) has emerged as a promising approach for powering miniature bio-implants because of its remarkable efficiency, safety limit, and misalignment tolerance. However, achieving low-power and high-quality uplink communication using ME remains a challenge. This paper presents a pulse-width modulated (PWM) ME backscatter uplink communication enabled by a switched-capacitor energy extraction (SCEE) technique. The SCEE rapidly extracts and dissipates the kinetic energy within the ME transducer during its ringdown period, enabling time-domain PWM in ME backscatter. Various circuit techniques are presented to realize SCEE with low power consumption. This paper also describes the high-order modeling of ME transducers to facilitate the design and analysis, which shows good matching with measurement. Our prototyping system includes a millimeter-scale ME implant with a fully integrated system-on-chip (SoC) and a portable transceiver for power transfer and bidirectional communication. SCEE is proven to induce >50% amplitude reduction within 2 ME cycles, leading to a PWM ME backscatter uplink with 17.73 kbps data rate and 0.9 pJ/bit efficiency. It also achieves 8.5 x 10 -5 bit-error-rate (BER) at a 5 cm distance, using a lightweight multi-layer-perception (MLP) decoding algorithm. Finally, the system demonstrates continuous wireless neural local-field potential (LFP) recording in an in vitro setup., Comment: 12 pages, 29 figures

In deep learning, the loss function plays a crucial role in optimizing the network. Many recent innovations in loss techniques have been made, and various margin-based angular loss functions (metric loss) have been designed particularly for face recognition. The concept of transformers is already well-researched and applied in many facets of machine vision. This paper presents a technique for loss evaluation that uses a transformer network as an additive loss in the face recognition domain. The standard metric loss function typically takes the final embedding of the main CNN backbone as its input. Here, we employ a transformer-metric loss, a combined approach that integrates both transformer-loss and metric-loss. This research intends to analyze the transformer behavior on the convolution output when the CNN outcome is arranged in a sequential vector. The transformer encoder takes input from the contextual vectors obtained from the final convolution layer of the network. With this technique, we use transformer loss with various base metric-loss functions to evaluate the effect of the combined loss functions. We observe that such a configuration allows the network to achieve SoTA results on various validation datasets with some limitations. This research expands the role of transformers in the machine vision domain and opens new possibilities for exploring transformers as a loss function., Comment: Face Recognition using Transformer Loss

Vehicle-to-everything (V2X) technologies offer a promising paradigm to mitigate the limitations of constrained observability in single-vehicle systems. Prior work primarily focuses on single-frame cooperative perception, which fuses agents' information across different spatial locations but ignores temporal cues and temporal tasks (e.g., temporal perception and prediction). In this paper, we focus on temporal perception and prediction tasks in V2X scenarios and design one-step and multi-step communication strategies (when to transmit) as well as examine their integration with three fusion strategies - early, late, and intermediate (what to transmit), providing comprehensive benchmarks with various fusion models (how to fuse). Furthermore, we propose V2XPnP, a novel intermediate fusion framework within one-step communication for end-to-end perception and prediction. Our framework employs a unified Transformer-based architecture to effectively model complex spatiotemporal relationships across temporal per-frame, spatial per-agent, and high-definition map. Moreover, we introduce the V2XPnP Sequential Dataset that supports all V2X cooperation modes and addresses the limitations of existing real-world datasets, which are restricted to single-frame or single-mode cooperation. Extensive experiments demonstrate our framework outperforms state-of-the-art methods in both perception and prediction tasks., Comment: Website link: https://mobility-lab.seas.ucla.edu/v2xpnp/

Capability evaluations play a critical role in ensuring the safe deployment of frontier AI systems, but this role may be undermined by intentional underperformance or ``sandbagging.'' We present a novel model-agnostic method for detecting sandbagging behavior using noise injection. Our approach is founded on the observation that introducing Gaussian noise into the weights of models either prompted or fine-tuned to sandbag can considerably improve their performance. We test this technique across a range of model sizes and multiple-choice question benchmarks (MMLU, AI2, WMDP). Our results demonstrate that noise injected sandbagging models show performance improvements compared to standard models. Leveraging this effect, we develop a classifier that consistently identifies sandbagging behavior. Our unsupervised technique can be immediately implemented by frontier labs or regulatory bodies with access to weights to improve the trustworthiness of capability evaluations., Comment: Published at NeurIPS 2024, SATA and SoLaR workshop, 6 pages, 4 figures, 1 table, code available at https://github.com/camtice/SandbagDetect

To prepare for the upcoming Legacy Survey of Space and Time, we develop methods for quantifying the selection function of a wide-field survey as a function of all six orbital parameters and absolute magnitude. We perform a HelioLinC3D search for Centaurs in the Pan-STARRS1 detection catalog and use a synthetic debiasing population to characterize our survey's selection function. We find nine new objects, including Centaur 2010 RJ$_{226}$, among 320 real objects, along with $\sim$70,000 debiasing objects. We use the debiasing population to fit a selection function and apply the selection function to a model Centaur population with literature orbital and size distributions. We confirm the model's marginal distributions but reject its joint distribution, and estimate an intrinsic population of 21,400$^{+3,400}_{-2,800}$ Centaurs with $H_r < 13.7$. The discovery of only nine new objects in archival data verifies that the Pan-STARRS discovery pipeline had high completeness, but also shows that new linking algorithms can contribute even to traditional single-tracklet surveys. As the first systematic application of HelioLinC3D to a survey with extensive sky coverage, this project proves the viability of HelioLinC3D as a discovery algorithm for big-data wide-field surveys., Comment: Accepted to The Astronomical Journal. 17 pages, 7 figures

Image inpainting is a fundamental task in computer vision, aiming to restore missing or corrupted regions in images realistically. While recent deep learning approaches have significantly advanced the state-of-the-art, challenges remain in maintaining structural continuity and generating coherent textures, particularly in large missing areas. Diffusion models have shown promise in generating high-fidelity images but often lack the structural guidance necessary for realistic inpainting. We propose a novel inpainting method that combines diffusion models with anisotropic Gaussian splatting to capture both local structures and global context effectively. By modeling missing regions using anisotropic Gaussian functions that adapt to local image gradients, our approach provides structural guidance to the diffusion-based inpainting network. The Gaussian splat maps are integrated into the diffusion process, enhancing the model's ability to generate high-fidelity and structurally coherent inpainting results. Extensive experiments demonstrate that our method outperforms state-of-the-art techniques, producing visually plausible results with enhanced structural integrity and texture realism.

Twisted Convolutional Networks (TCNs) are introduced as a novel neural network architecture designed to effectively process one-dimensional data with arbitrary feature order and minimal spatial relationships. Unlike traditional Convolutional Neural Networks (CNNs), which excel at handling structured two-dimensional data like images, TCNs reduce dependency on feature order by combining input features in innovative ways to create new representations. By explicitly enhancing feature interactions and employing diverse feature combinations, TCNs generate richer and more informative representations, making them especially effective for classification tasks on datasets with arbitrary feature arrangements. This paper details the TCN architecture and its feature combination strategy, providing a comprehensive comparison with traditional CNNs, DeepSets, Transformers, and Graph Neural Networks (GNNs). Extensive experiments on benchmark datasets demonstrate that TCNs achieve superior performance, particularly in classification scenarios involving one-dimensional data., Comment: The source code for the TCNs can be accessed at https://github.com/junbolian/Twisted-Convolutional-Networks

Electromagnetic whistler-mode waves play a crucial role in the acceleration and precipitation of radiation belt electrons. Statistical surveys of wave characteristics suggest that these waves should preferentially scatter and precipitate relativistic electrons on the day side. However, the night-side region is expected to be primarily associated with electron acceleration. The recent low-altitude observations reveal relativistic electron precipitation in the night-side region. In this paper, we present statistical surveys of night-side relativistic electron losses due to intense precipitation bursts. We demonstrate that such bursts are associated with storm time substorm injections and are likely related to relativistic electron scattering by ducted whistler-mode waves. We also speculate on the role of injections in creating conditions favorable for relativistic electron precipitation.

Parallel input performance issues are often neglected in large scale parallel applications in Computational Science and Engineering. Traditionally, there has been less focus on input performance because either input sizes are small (as in biomolecular simulations) or the time doing input is insignificant compared with the simulation with many timesteps. But newer applications, such as graph algorithms add a premium to file input performance. Additionally, over-decomposed systems, such as Charm++/AMPI, present new challenges in this context in comparison to MPI applications. In the over-decomposition model, naive parallel I/O in which every task makes its own I/O request is impractical. Furthermore, load balancing supported by models such as Charm++/AMPI precludes assumption of data contiguity on individual nodes. We develop a new I/O abstraction to address these issues by separating the decomposition of consumers of input data from that of file-reader tasks that interact with the file system. This enables applications to scale the number of consumers of data without impacting I/O behavior or performance. These ideas are implemented in a new input library, CkIO, that is built on Charm++, which is a well-known task-based and overdecomposed-partitions system. CkIO is configurable via multiple parameters (such as the number of file readers and/or their placement) that can be tuned depending on characteristics of the application, such as file size and number of application objects. Additionally, CkIO input allows for capabilities such as effective overlap of input and application-level computation, as well as load balancing and migration. We describe the relevant challenges in understanding file system behavior and architecture, the design alternatives being explored, and preliminary performance data.

Certain inflationary models can feature periods of preheating - an era preceding reheating during which parametric resonance triggers an exponential production of bosons. This non-perturbative process can have significant impact on the history of our universe, with consequences ranging from altered reheating channels to overproduction of dark radiation to overclosure. In this work, we study parametric resonance production of axions in string models of inflation. We find that the kinetic couplings and moduli-dependent axion masses give rise to generalizations of the Mathieu equation. We study these generalizations and determine the strength of parametric resonance created by such couplings. We then apply this technology to fibre inflation models in Type IIB orientifold compactifications. We find that heavy axions can be copiously produced and avoidance of overclosure results in constraints on the typical fibre inflation parameter space., Comment: 48 pages, 10 figures, v2: several important references added

In astrophysics, understanding the evolution of galaxies in primarily through imaging data is fundamental to comprehending the formation of the Universe. This paper introduces a novel approach to conditioning Denoising Diffusion Probabilistic Models (DDPM) on redshifts for generating galaxy images. We explore whether this advanced generative model can accurately capture the physical characteristics of galaxies based solely on their images and redshift measurements. Our findings demonstrate that this model not only produces visually realistic galaxy images but also encodes the underlying changes in physical properties with redshift that are the result of galaxy evolution. This approach marks a significant advancement in using generative models to enhance our scientific insight into cosmic phenomena.

A pulsar's scintillation bandwidth is inversely proportional to the scattering delay, making accurate measurements of scintillation bandwidth critical to characterize unmitigated delays in efforts to measure low-frequency gravitational waves with pulsar timing arrays. In this pilot work, we searched for a subset of known pulsars within $\sim$97% of the data taken with the PUPPI instrument for the AO327 survey with the Arecibo telescope, attempting to measure the scintillation bandwidths in the dataset by fitting to the 2D autocorrelation function of their dynamic spectra. We successfully measured 38 bandwidths from 23 pulsars (six without prior literature values), finding that: almost all of the measurements are larger than the predictions from NE2001 and YMW16 (two popular galactic models); NE2001 is more consistent with our measurements than YMW16; Gaussian fits to the bandwidth are more consistent with both electron density models than Lorentzian ones; and for the 17 pulsars with prior literature values, the measurements between various sources often vary by factors of a few. The success of Gaussian fits may be due to the use of Gaussian fits to train models in previous work. The variance of literature values over time could relate to the scaling factor used to compare measurements, but also seems consistent with time-varying interstellar medium parameters. This work can be extended to the rest of AO327 to further investigate these trends, highlighting the continuing importance of large archival datasets for projects beyond their initial conception., Comment: 21 pages, 8 figures, 2 tables

The integration of machine learning in magnetic resonance imaging (MRI), specifically in neuroimaging, is proving to be incredibly effective, leading to better diagnostic accuracy, accelerated image analysis, and data-driven insights, which can potentially transform patient care. Deep learning models utilize multiple layers of processing to capture intricate details of complex data, which can then be used on a variety of tasks, including brain tumor classification, segmentation, image synthesis, and registration. Previous research demonstrates high accuracy in tumor segmentation using various model architectures, including nn-UNet and Swin-UNet. U-Mamba, which uses state space modeling, also achieves high accuracy in medical image segmentation. To leverage these models, we propose a deep learning framework that ensembles these state-of-the-art architectures to achieve accurate segmentation and produce finely synthesized images.

We study the equivariant cohomology classes of torus-equivariant subvarieties of the space of matrices. For a large class of torus actions, we prove that the polynomials representing these classes (up to suitably changing signs) are covolume polynomials in the sense of Aluffi. We study the cohomology rings of complex varieties in terms of Macaulay inverse systems over $\mathbb{Z}$. As applications, we show that under certain conditions, the Macaulay dual generator is a denormalized Lorentzian polynomial in the sense of Br\"and\'en and Huh, and we give a characteristic-free extension (over $\mathbb{Z}$) of the result of Khovanskii and Pukhlikov describing the cohomology ring of toric varieties in terms of volume polynomials.

Understanding coronal structure and dynamics can be facilitated by analyzing green-line emission, which enables the investigation of diverse coronal structures such as coronal loops, streamers, coronal holes, and various eruptions in the solar atmosphere. In this study, we investigated the spatiotemporal behaviors of green-line emissions in both low and high latitudes across nine solar cycles, ranging from cycle 17 to the current cycle 25, using the Modified Homogeneous Data Set (MHDS). We employed methodologies such as cross-correlation, power spectral density (PSD), and wavelet transform techniques for this analysis. We found distinct behaviors in green line energy across various latitudinal distributions in the solar atmosphere. The trends observed at higher latitudes differ from those at lower latitudes. The emission behaviors show a close association with other solar phenomena like solar flares, sunspots, and coronal mass ejections (CMEs) throughout the solar cycles. The observed variations exhibit harmonic periods. The emission activity is significantly higher in the low latitudes, accounting for over 70 percent of the emissions, while the higher latitudes contribute less than 30 percent. The emissions exhibit asymmetric behavior between the northern and southern hemispheres, leading to a 44-year cycle of solar hemispheric dominance shifts. Various factors, such as Alfv\'en waves, solar magnetic fields, sunspots, differential rotation, and reconnection events, influence the observed differences in behavior between lower and higher latitudes, suggesting the existence of potential underlying phenomena contributing to deviations in properties, intensity, temporal dynamics, and spatiotemporal lifetime., Comment: 21 pages, 13 figures, 6 ables, Published in the Astrophysical Journal Supplement Series, 275:3 (21pp), 2024 November

Sub-Neptunes - volatile-rich exoplanets smaller than Neptune - are intrinsically the most common type of planet known. However, the formation and nature of these objects, as well as the distinctions between sub-classes (if any), remain unclear. Two powerful tools to tease out the secrets of these worlds are measurements of (i) atmospheric composition and structure revealed by transit and/or eclipse spectroscopy, and (ii) mass, radius, and density revealed by transit photometry and Doppler spectroscopy. Here we present OrCAS, a survey to better elucidate the origins, compositions, and atmospheres of sub-Neptunes. This radial velocity survey uses a repeatable, quantifiable metric to select targets suitable for subsequent transmission spectroscopy and address key science themes about the atmospheric & internal compositions and architectures of these systems. Our survey targets 26 systems with transiting sub-Neptune planet candidates, with the overarching goal of increasing the sample of such planets suitable for subsequent atmospheric characterization. This paper lays out our survey's science goals, defines our target prioritization metric, and performs light-curve fits and statistical validation using existing TESS photometry and ground-based follow-up observations. Our survey serves to continue expanding the sample of small exoplanets with well-measured properties orbiting nearby bright stars, ensuring fruitful studies of these systems for many years to come., Comment: 20 pages, 4 figures, 4 tables, 26 sub-Neptunes, 31 TOIs. Accepted to AJ

Optically-addressable spin qubits form the foundation of a new generation of emerging nanoscale sensors. The engineering of these sensors has mainly focused on solid-state systems such as the nitrogen-vacancy (NV) center in diamond. However, NVs are restricted in their ability to interface with biomolecules due to their bulky diamond host. Meanwhile, fluorescent proteins have become the gold standard in bioimaging, as they are genetically encodable and easily integrated with biomolecules. While fluorescent proteins have been suggested to possess a metastable triplet state, they have not been investigated as qubit sensors. Here, we realize an optically-addressable spin qubit in the Enhanced Yellow Fluorescent Protein (EYFP) enabled by a novel spin-readout technique. A near-infrared laser pulse allows for triggered readout of the triplet state with up to 44% spin contrast. Using coherent microwave control of the EYFP spin at liquid-nitrogen temperatures, we measure a spin-lattice relaxation time of $(141 \pm 5)$ {\mu}s, a $(16 \pm 2)$ {\mu}s coherence time under Carr-Purcell-Meiboom-Gill (CPMG) decoupling, and a predicted oscillating (AC) magnetic field sensitivity with an upper bound of $183 \, \mathrm{fT}\, \mathrm{mol}^{1/2}\, \mathrm{Hz}^{-1/2}$. We express the qubit in mammalian cells, maintaining contrast and coherent control despite the complex intracellular environment. Finally, we demonstrate optically-detected magnetic resonance at room temperature in aqueous solution with contrast up to 3%, and measure a static (DC) field sensitivity with an upper bound of $93 \, \mathrm{pT}\, \mathrm{mol}^{1/2}\, \mathrm{Hz}^{-1/2}$. Our results establish fluorescent proteins as a powerful new qubit sensor platform and pave the way for applications in the life sciences that are out of reach for solid-state technologies.

Qubits that are intrinsically insensitive to depolarization and dephasing errors promise to significantly reduce the overhead of fault-tolerant quantum computing. At their optimal operating points, the logical states of these qubits exhibit both exponentially suppressed matrix elements and sweet spots in energy dispersion, rendering the qubits immune to depolarization and dephasing, respectively. We introduce a multimode qubit, the protomon, encoded in a fluxonium molecule circuit. Compared to the closely related $0$-$\pi$ qubit, the protomon offers several advantages in theory: resilience to circuit parameter disorder, minimal dephasing from intrinsic harmonic modes, and no dependence on static offset charge. As a proof of concept, we realize four protomon qubits. By tuning the qubits to various operating points identified with calibrated two-tone spectroscopy, we measure depolarization times ranging from 64 to 73 $\mu$s and dephasing times between 0.2 to 0.5 $\mu$s for one selected qubit. The discrepancy between the relatively short measured coherence times and theoretical predictions is not fully understood. This calls for future studies investigating the limiting noise factors, informing the direction for improving coherence times of the protomon qubit., Comment: 13 pages, 6 figures

Structure editors operate directly on a program's syntactic tree structure. At first glance, this allows for the exciting possibility that such an editor could enforce correctness properties: programs could be well-formed and sometimes even well-typed by construction. Unfortunately, traditional approaches to structure editing that attempt to rigidly enforce these properties face a seemingly fundamental problem, known in the literature as viscosity. Making changes to existing programs often requires temporarily breaking program structure -- but disallowing such changes makes it difficult to edit programs! In this paper, we present a scheme for structure editing which always maintains a valid program structure without sacrificing the fluidity necessary to freely edit programs. Two key pieces help solve this puzzle: first, we develop a novel generalization of selection for tree-based structures that properly generalizes text-based selection and editing, allowing users to freely rearrange pieces of code by cutting and pasting one-hole contexts; second, we type these one-hole contexts with a category of type diffs and explore the metatheory of the system that arises for maintaining well-typedness systematically. We implement our approach as an editor called Pantograph, and we conduct a study in which we successfully taught students to program with Pantograph and compare their performance against a traditional text editor., Comment: This is the extended version of the paper

Despite the rapid pace at which deep networks are improving on standardized vision benchmarks, they are still outperformed by humans on real-world vision tasks. This paradoxical lack of generalization could be addressed by making deep networks more brain-like. Although several benchmarks have compared the ability of deep networks to predict brain responses to natural images, they do not capture subtle but important brain-like emergent properties. To resolve this issue, we report several well-known perceptual and neural emergent properties that can be tested on deep networks. To evaluate how various design factors impact brain-like properties, we systematically evaluated over 30 state-of-the-art networks with varying network architectures, training datasets and training regimes. Our main findings are as follows. First, network architecture had the strongest impact on brain-like properties compared to dataset and training regime variations. Second, networks varied widely in their alignment to the brain with no single network outperforming all others. Taken together, our results complement existing benchmarks by revealing brain-like properties that are either emergent or lacking in state-of-the-art deep networks.

We investigate variants of Marstrand's projection theorem that hold for sets of directions and classes of sets in $\mathbb{R}^2$. We say that a set of directions $D \subseteq\mathcal{S}^1$ is $\textit{universal}$ for a class of sets if, for every set $E$ in the class, there is a direction $e\in D$ such that the projection of $E$ in the direction $e$ has maximal Hausdorff dimension. We construct small universal sets for certain classes. Particular attention is paid to the role of regularity. We prove the existence of universal sets with arbitrarily small positive Hausdorff dimension for the class of weakly regular sets. We prove that there is a universal set of zero Hausdorff dimension for the class of AD-regular sets., Comment: 30 pages

We theoretically investigate the supercurrent flow in a Josephson junction consisting of two spin-split superconductors combined by a normal metal weak link. The normal metal may be driven out of equilibrium, thus modifying the electron and hole occupation and consequently the supercurrent through the system. Considering first an equilibrium normal metal, we find that increasing the spin-splitting field can enhance the supercurrent strongly for long junctions at low temperatures. In contrast to previous work, this is a much larger enhancement (over 100%) and it is achieved for both parallel and antiparallel spin-splitting field configurations, making the effect robust. On the other hand, when a gate voltage is applied to drive the system out of equilibrium, we demonstrate a more efficient $\pi$-transition of the supercurrent in terms of a lower transition voltage by tuning the spin-splitting. Moreover, we find the application of temperature bias strongly suppresses the supercurrent, resulting in very sharp supercurrent jumps as outputs., Comment: 8 pages, 8 figures

Let $G$ be a finite solvable group and let $\Delta(G)$ be the character degree graph of $G$. In this paper, we obtain the metric dimension of certain character degree graphs. Specifically, we calculate the metric dimension for a regular character degree graph, a character degree graph with a diameter of $2$ that is not a block, a character degree graph with a diameter of $3$ that also has a cut vertex and a character degree graph with Fitting height $2.$ We also consider two related parameters, base size and adjacency dimension, and their relation to metric dimension for character degree graphs of solvable groups.

Mechanical systems have emerged as a compelling platform for applications in quantum information, leveraging recent advances in the control of phonons, the quanta of mechanical vibrations. Several experiments have demonstrated control and measurement of phonon states in mechanical resonators integrated with superconducting qubits, and while entanglement of two mechanical resonators has been demonstrated in some approaches, a full exploitation of the bosonic nature of phonons, such as multi-phonon entanglement, remains a challenge. Here, we describe a modular platform capable of rapid multi-phonon entanglement generation and subsequent tomographic analysis, using two surface acoustic wave resonators on separate substrates, each connected to a superconducting qubit. We generate a mechanical Bell state between the two mechanical resonators, achieving a fidelity of $\mathcal{F} = 0.872\pm 0.002$, and further demonstrate the creation of a multi-phonon entangled state (N=2 N00N state), shared between the two resonators, with fidelity $\mathcal{F} = 0.748\pm 0.008$. This approach promises the generation and manipulation of more complex phonon states, with potential future applications in bosonic quantum computing in mechanical systems. The compactness, modularity, and scalability of our platform further promises advances in both fundamental science and advanced quantum protocols, including quantum random access memory and quantum error correction., Comment: 25 pages, 9 figures

Deep learning increasingly relies on massive data with substantial costs for storage, annotation, and model training. To reduce these costs, coreset selection aims to find a representative subset of data to train models while ideally performing on par with the full data training. State-of-the-art coreset methods use carefully-designed criteria to quantify the importance of each data example via ground truth labels and dataset-specific training, then select examples whose scores lie in a certain range to construct a coreset. These methods work well in their respective settings, however, they cannot select data that are unlabeled, which is the majority of real-world data. To that end, this paper motivates and formalizes the problem of unlabeled coreset selection to enable greater scale and reduce annotation costs for deep learning. As a solution, we develop Zero-Shot Coreset Selection (ZCore), a method that efficiently selects coresets without ground truth labels or training on candidate data. Instead, ZCore uses existing foundation models to generate a zero-shot embedding space for unlabeled data, then quantifies the relative importance of each example based on overall coverage and redundancy within the embedding distribution. We evaluate ZCore on four datasets and outperform several state-of-the-art label-based methods, leading to a strong baseline for future research in unlabeled coreset selection. On ImageNet, ZCore selections achieve a downstream model accuracy of 53.99% with only 10% training data, which outperforms label-based methods while removing annotation requirements for 1.15 million images. Our code is publicly available at https://github.com/voxel51/zcore.

Language model post-training is applied to refine behaviors and unlock new skills across a wide range of recent language models, but open recipes for applying these techniques lag behind proprietary ones. The underlying training data and recipes for post-training are simultaneously the most important pieces of the puzzle and the portion with the least transparency. To bridge this gap, we introduce Tulu 3, a family of fully-open state-of-the-art post-trained models, alongside its data, code, and training recipes, serving as a comprehensive guide for modern post-training techniques. Tulu 3, which builds on Llama 3.1 base models, achieves results surpassing the instruct versions of Llama 3.1, Qwen 2.5, Mistral, and even closed models such as GPT-4o-mini and Claude 3.5-Haiku. The training algorithms for our models include supervised finetuning (SFT), Direct Preference Optimization (DPO), and a novel method we call Reinforcement Learning with Verifiable Rewards (RLVR). With Tulu 3, we introduce a multi-task evaluation scheme for post-training recipes with development and unseen evaluations, standard benchmark implementations, and substantial decontamination of existing open datasets on said benchmarks. We conclude with analysis and discussion of training methods that did not reliably improve performance. In addition to the Tulu 3 model weights and demo, we release the complete recipe -- including datasets for diverse core skills, a robust toolkit for data curation and evaluation, the training code and infrastructure, and, most importantly, a detailed report for reproducing and further adapting the Tulu 3 approach to more domains.

Legacy software systems, written in outdated languages like MUMPS and mainframe assembly, pose challenges in efficiency, maintenance, staffing, and security. While LLMs offer promise for modernizing these systems, their ability to understand legacy languages is largely unknown. This paper investigates the utilization of LLMs to generate documentation for legacy code using two datasets: an electronic health records (EHR) system in MUMPS and open-source applications in IBM mainframe Assembly Language Code (ALC). We propose a prompting strategy for generating line-wise code comments and a rubric to evaluate their completeness, readability, usefulness, and hallucination. Our study assesses the correlation between human evaluations and automated metrics, such as code complexity and reference-based metrics. We find that LLM-generated comments for MUMPS and ALC are generally hallucination-free, complete, readable, and useful compared to ground-truth comments, though ALC poses challenges. However, no automated metrics strongly correlate with comment quality to predict or measure LLM performance. Our findings highlight the limitations of current automated measures and the need for better evaluation metrics for LLM-generated documentation in legacy systems., Comment: Abbreviated version submitted to LLM4Code 2025 (a workshop co-located with ICSE 2025), 13 pages, 3 figures

Evidence has emerged for a stochastic signal correlated among 67 pulsars within the 15-year pulsar-timing data set compiled by the NANOGrav collaboration. Similar signals have been found in data from the European, Indian, Parkes, and Chinese PTAs. This signal has been interpreted as indicative of the presence of a nanohertz stochastic gravitational wave background. To explore the internal consistency of this result we investigate how the recovered signal strength changes as we remove the pulsars one by one from the data set. We calculate the signal strength using the (noise-marginalized) optimal statistic, a frequentist metric designed to measure correlated excess power in the residuals of the arrival times of the radio pulses. We identify several features emerging from this analysis that were initially unexpected. The significance of these features, however, can only be assessed by comparing the real data to synthetic data sets. After conducting identical analyses on simulated data sets, we do not find anything inconsistent with the presence of a stochastic gravitational wave background in the NANOGrav 15-year data. The methodologies developed here can offer additional tools for application to future, more sensitive data sets. While this analysis provides an internal consistency check of the NANOGrav results, it does not eliminate the necessity for additional investigations that could identify potential systematics or uncover unmodeled physical phenomena in the data., Comment: 21 pages, 11 figures, 2 tables

We consider $\mathcal{N} = 2$ superconformal gauge theories in four dimensions. We explain how these quiver gauge theories arise as low-energy worldvolume theories of D3-branes on orientifolds. Then, we examine their associated chiral algebras, and propose novel examples of twisted holographic dualities arising in the large-N limit. These dualities involve topological strings in the bulk, which is a Calabi-Yau threefold taking the form $\text{SL}_2 \mathbb{C} / \Gamma$., Comment: 24 pages, 13 figures, 4 tables

Large Language Models (LLMs) demonstrate strong abilities in common-sense reasoning and interactive decision-making, but often struggle with complex, long-horizon planning tasks. Recent techniques have sought to structure LLM outputs using control flow and other code-adjacent techniques to improve planning performance. These techniques include using variables (to track important information) and functions (to divide complex tasks into smaller re-usable sub-tasks). However, purely code-based approaches can be error-prone and insufficient for handling ambiguous or unstructured data. To address these challenges, we propose REPL-Plan, an LLM planning approach that is fully code-expressive (it can utilize all the benefits of code) while also being dynamic (it can flexibly adapt from errors and use the LLM for fuzzy situations). In REPL-Plan, an LLM solves tasks by interacting with a Read-Eval-Print Loop (REPL), which iteratively executes and evaluates code, similar to language shells or interactive code notebooks, allowing the model to flexibly correct errors and handle tasks dynamically. We demonstrate that REPL-Plan achieves strong results across various planning domains compared to previous methods.

A natural open problem in Ramsey theory is to determine those $3$-graphs $H$ for which the off-diagonal Ramsey number $r(H, K_n^{(3)})$ grows polynomially with $n$. We make substantial progress on this question by showing that if $H$ is tightly connected or has at most two tight components, then $r(H, K_n^{(3)})$ grows polynomially if and only if $H$ is not contained in an iterated blowup of an edge., Comment: 12 pages

Magnetic transition-metal dichalcogenides (TMDs) have been of particular interest due to their unique magnetic properties and layered structure that can be promising for a wide range of spintronic applications. One of the most exciting compounds in this family of magnets is chromium telluride, Cr$_{1+x}$Te$_2$, which has shown rich magnetic phases with varied Cr concentrations. An emergent antiferromagnetic (AFM) ordering has been found in Cr$_{1.25}$Te$_2$ (equivalently, Cr$_{5}$Te$_8$), which is induced by intercalating 0.25 Cr atom per unit cell within the van der Waals (vdW) gaps of CrTe$_2$. In this work, we report an increased N\'eel Temperature ($T_\mathrm{N}$) of the AFM phase in Cr$_{1+x}$Te$_2$ by slightly reducing the concentration of Cr intercalants. Moreover, the intercalated Cr atoms form a metastable 2$\times$2 supercell structure that can be manipulated by electron beam irradiation. This work offers a promising approach to tuning magnetic and structural properties by adjusting the concentration of self-intercalated magnetic atoms., Comment: 5 figures, 1 table

The Laser Interferometer Space Antenna (LISA) mission is being developed by ESA with NASA participation. As it has recently passed the Mission Adoption milestone, models of the instruments and noise performance are becoming more detailed, and likewise prototype data analyses must as well. Assumptions such as Gaussianity, Stationarity, and continuous data continuity are unrealistic, and must be replaced with physically motivated data simulations, and data analysis methods adapted to accommodate such likely imperfections. To this end, the LISA Data Challenges have produced datasets featuring time-varying and unequal constellation armlength, and measurement artifacts including data interruptions and instrumental transients. In this work, we assess the impact of these data artifacts on the inference of Galactic Binary and Massive Black Hole properties. Our analysis shows that the treatment of noise transients and gaps is necessary for effective parameter estimation. We find that straightforward mitigation techniques can significantly suppress artifacts, albeit leaving a non-negligible impact on aspects of the science., Comment: 28 pages, 14 figures

Dramatic increases in the capabilities of neural network models in recent years are driven by scaling model size, training data, and corresponding computational resources. To develop the exceedingly large networks required in modern applications, such as large language models (LLMs), model training is distributed across tens of thousands of hardware accelerators (e.g. GPUs), requiring orchestration of computation and communication across large computing clusters. In this work, we demonstrate that careful consideration of hardware configuration and parallelization strategy is critical for effective (i.e. compute- and cost-efficient) scaling of model size, training data, and total computation. We conduct an extensive empirical study of the performance of large-scale LLM training workloads across model size, hardware configurations, and distributed parallelization strategies. We demonstrate that: (1) beyond certain scales, overhead incurred from certain distributed communication strategies leads parallelization strategies previously thought to be sub-optimal in fact become preferable; and (2) scaling the total number of accelerators for large model training quickly yields diminishing returns even when hardware and parallelization strategies are properly optimized, implying poor marginal performance per additional unit of power or GPU-hour.

Predicting Sea Surface Temperature (SST) in the Great Barrier Reef (GBR) region is crucial for the effective management of its fragile ecosystems. This study provides a rigorous comparative analysis of several machine learning techniques to identify the most effective method for SST prediction in this area. We evaluate the performance of ridge regression, Least Absolute Shrinkage and Selection Operator (LASSO), Random Forest, and Extreme Gradient Boosting (XGBoost) algorithms. Our results reveal that while LASSO and ridge regression perform well, Random Forest and XGBoost significantly outperform them in terms of predictive accuracy, as evidenced by lower Mean Squared Error (MSE), Mean Absolute Error (MAE), and Root Mean Squared Prediction Error (RMSPE). Additionally, XGBoost demonstrated superior performance in minimizing Kullback- Leibler Divergence (KLD), indicating a closer alignment of predicted probability distributions with actual observations. These findings highlight the efficacy of using ensemble methods, particularly XGBoost, for predicting sea surface temperatures, making them valuable tools for climatological and environmental modeling.

Miniature bioelectronic implants promise revolutionary therapies for cardiovascular and neurological disorders. Wireless power transfer (WPT) is a significant method for miniaturization, eliminating the need for bulky batteries in devices. Despite successful demonstrations of millimetric battery free implants in animal models, the robustness and efficiency of WPT are known to degrade significantly under misalignment incurred by body movements, respiration, heart beating, and limited control of implant orientation during surgery. This article presents an omnidirectional WPT platform for millimetric bioelectronic implants, employing the emerging magnetoelectric (ME) WPT modality, and magnetic field steering technique based on multiple transmitter (TX) coils. To accurately sense the weak coupling in a miniature implant and adaptively control the multicoil TX array in a closed loop, we develop an active echo (AE) scheme using a tiny coil on the implant. Our prototype comprises a fully integrated 14.2 mm3 implantable stimulator embedding a custom low power system on chip (SoC) powered by an ME film, a TX with a custom three channel AE RX chip, and a multicoil TX array with mutual inductance cancellation. The AE RX achieves negative 161 dBm per Hz input referred noise with 64 dB gain tuning range to reliably sense the AE signal, and offers fast polarity detection for driver control. AE simultaneously enhances the robustness, efficiency, and charging range of ME WPT. Under 90 degree rotation from the ideal position, our omnidirectional WPT system achieves 6.8x higher power transfer efficiency (PTE) than a single coil baseline. The tracking error of AE negligibly degrades the PTE by less than 2 percent from using ideal control., Comment: 13 pages, 27 figures

Traditional approaches to measurement in upper-limb therapy have gaps that electronic sensing and recording can help fill. We highlight shortcomings in current kinematic recording devices, and we introduce a wrist sensing device that performs multimodal sensing during single-axis rotation. Our goal is to characterize normative kinesthetic perception and real-world performance as a multimodal sensory "fingerprint" that can serve as a reference point for identifying deficit in persons affected by stroke, and then as a jumping point for later neuroscientific interrogation. We present an experiment involving psychophysical measurements of passive stimuli discrimination, matching adjustment acuity, and ADL performance in 11 neurologically-intact persons. We found that passive velocity sense and active position sense of healthy controls, measured by velocity discrimination and position matching respectively, correlated in rank with each other, but other score comparisons of acuity or task performance had no statistically significant correlations. We also found that participants differed in acuity between passive and active velocity sense, which supports current understanding about muscle spindle activation being modulated by conscious motor command. The potential for our null correlation results to reveal dissociable aspects of deficit is discussed, as well as implications for future neuroscientific study with more kinematic measures and larger datasets., Comment: 14 pages, 15 figures; A newer version of this work has been submitted to the 2024 IEEE EMBC for possible publication in their conference proceedings

Rerankers, typically cross-encoders, are often used to re-score the documents retrieved by cheaper initial IR systems. This is because, though expensive, rerankers are assumed to be more effective. We challenge this assumption by measuring reranker performance for full retrieval, not just re-scoring first-stage retrieval. Our experiments reveal a surprising trend: the best existing rerankers provide diminishing returns when scoring progressively more documents and actually degrade quality beyond a certain limit. In fact, in this setting, rerankers can frequently assign high scores to documents with no lexical or semantic overlap with the query. We hope that our findings will spur future research to improve reranking.

Nonlinear electrodynamics in materials manifests as an electronic response that depends on second- or higher-order powers of the applied electromagnetic field. This response is highly dependent on the underlying crystal symmetries in the material and is typically smaller than the linear responses. Nonlinear responses are therefore usually employed to expose the symmetry breaking, geometric properties of the electronic band structure in materials. Naturally, a material system with a strong nonlinear response is also the key component in nonlinear devices. Here we report the strong room-temperature second-harmonic transport response in a quantum magnet,TbMn6Sn6, which is governed by the quantum metric and can be tuned with applied magnetic fields and temperature. We show that around room temperature, which is close to the spontaneous spin-reorientation transition, the magnetic configurations, and therefore the related symmetry breaking phases, are easily controlled. Our results pave the way from quantum materials to high performance tuneable nonlinear device applications at room temperature., Comment: 12 pages, 3 figures

Nuclear magnetic resonance instruments are becoming available to the do-it-yourself community. The challenges encountered in the endeavor to build a magnetic resonance imaging instrument from scratch were confronted in a four-day hackathon at Singapore University of Technology and Design in spring 2024. One day was devoted to educational lectures and three days to system construction and testing. Seventy young researchers from all parts of the world formed six teams focusing on magnet, gradient coil, RF coil, console, system integration, and design, which together produced a working MRI instrument in three days. The different steps, encountered challenges, and their solutions are reported., Comment: 49 pages, 23 figures, comments welcome (this paper is meant to be useful to people constructing their own MRI systems)

Manipulating an environment remotely with a robotic teleoperator introduces novel electromechanical (EM) dynamics between the user and environment. While considerable effort has focused on minimizing these dynamics, there is limited research into understanding their impact on a user's internal model and resulting motor control strategy. Here we investigate to what degree the dynamics and kinesthetic feedback of the teleoperator influence task behavior and tool compensation. Our teleoperator testbed features a leader port controlled by user input via wrist rotation, a follower port connected to a virtual environment rendered by rotary motor, and three distinct transmissions (Rigid, Unilateral EM, Bilateral EM) in-between that can be engaged independently. 30 adult participants rotated a disk in a visco-elastic virtual environment through counterbalanced presentation of each transmission. Users tracked targets oscillating at 7 pre-defined random frequencies between 0.55 and 2.35 Hz. After session completion, trajectories of the target, leader, and follower were decomposed into components of gain and phase error for all frequencies. We found that while tracking performance at the follower port was similar across transmissions, users' adjustment at the leader port differed between Rigid and EM transmissions. Users applied different pinch forces between Rigid and Unilateral transmissions, suggesting that tracking strategy does change between dynamics and feedback. However, the users' ability to compensate dynamics diminished significantly as task speed got faster and more difficult. Therefore, there are limits to pursuit tracking at the human wrist when compensating teleoperator dynamics., Comment: 12 pages, 15 figures; A newer version of this work has been submitted to IEEE Transactions on Haptics for possible publication