Search

Neutral atom array has emerged as a promising platform for quantum computation owing to its high-fidelity two-qubit gate, arbitrary connectivity and overwhelming scalability. Nevertheless, fault-tolerant quantum computing on the neutral atom platform requires consideration of the types of errors that neutral atoms are prone to. One typical and major error is leakage error from Rydberg state when implementing multi-qubit gate. Such leakage error is harmful by propagating multiple pauli errors in quantum circuit. Researchers have proposed erasure conversion protocol, which utilizes fast leakage detection to convert leakage error to benign erasure error. This method has a favorable error distance d, but is limited to certain atom species. Here, we propose a new method to deal with such leakage error in measurement-based quantum computation (MBQC), to which we refer as "Leakage Tracking". We remove the demand for mid-circuit leakage detection but infer the probabilities and locations of pauli errors through gate sequence and final leakage detection. We show that this method has an error distance de = d and reaches a high threshold 1.7% per CZ gate for pure leakage error and perfect final leakage detection. In presence of atom loss and other pauli errors, we show the advantage in error distance over erasure conversion when the ratio of leakage error is close to one., Comment: 11 pages, 5 figures

Vision-language model (VLM) embeddings have been shown to encode biases present in their training data, such as societal biases that prescribe negative characteristics to members of various racial and gender identities. VLMs are being quickly adopted for a variety of tasks ranging from few-shot classification to text-guided image generation, making debiasing VLM embeddings crucial. Debiasing approaches that fine-tune the VLM often suffer from catastrophic forgetting. On the other hand, fine-tuning-free methods typically utilize a "one-size-fits-all" approach that assumes that correlation with the spurious attribute can be explained using a single linear direction across all possible inputs. In this work, we propose Bend-VLM, a nonlinear, fine-tuning-free approach for VLM embedding debiasing that tailors the debiasing operation to each unique input. This allows for a more flexible debiasing approach. Additionally, we do not require knowledge of the set of inputs a priori to inference time, making our method more appropriate for online, open-set tasks such as retrieval and text guided image generation.

The goal of our project is to use satellite data (including nighttime light data and remote sensing images) to give us some statistical estimation of the economic development level of a selected area (Singapore). Findings from the project could inform policymakers about areas needing intervention or support for economic development initiatives. Insights gained might aid in targeted policy formulation for infrastructure, agriculture, urban planning, or resource management.

In this project, we reviewed a paper that deals graph-structured convex optimization (GSCO) problem with the approximate Frank-Wolfe (FW) algorithm. We analyzed and implemented the original algorithm and introduced some extensions based on that. Then we conducted experiments to compare the results and concluded that our backtracking line-search method effectively reduced the number of iterations, while our new DMO method (Top-g+ optimal visiting) did not make satisfying enough improvements.

Differential absorption Lidar (DIAL) in the ultraviolet (UV) region is an effective approach for monitoring tropospheric ozone. 4H-SiC single-photon detectors (SPDs) are emergent devices for UV single-photon detection. Here, we demonstrate a 4H-SiC SPD-based ozone DIAL. We design and fabricate the 4H-SiC single-photon avalanche diode with a beveled mesa structure and optimized layer thickness. An active quenching circuit with a quenching time of 1.03 ns is developed to significantly mitigate the afterpulsing effect while enhancing the maximum count rate. After characterization, the SPD exhibits excellent performance with a photon detection efficiency of 16.6% at 266 nm, a dark count rate of 138 kcps, a maximum count rate of 13 Mcps, and an afterpulse probability of 2.7% at room temperature. Then, we apply two 4H-SiC SPDs in an ozone DIAL. The measured ozone concentrations at altitudes of 1-3.5 km agree well with the results of a commercial ozone DIAL. Our work provides an alternative solution for general UV Lidar applications., Comment: Accepted by Applied Physics Letters

Many nations are promoting the green transition in the energy sector to attain neutral carbon emissions by 2050. Smart Grid 2.0 (SG2) is expected to explore data-driven analytics and enhance communication technologies to improve the efficiency and sustainability of distributed renewable energy systems. These features are beyond smart metering and electric surplus distribution in conventional smart grids. Given the high dependence on communication networks to connect distributed microgrids in SG2, potential cascading failures of connectivity can cause disruption to data synchronization to the remote control systems. This paper reviews security threats and defense tactics for three stakeholders: power grid operators, communication network providers, and consumers. Through the survey, we found that SG2's stakeholders are particularly vulnerable to substation attacks/vandalism, malware/ransomware threats, blockchain vulnerabilities and supply chain breakdowns. Furthermore, incorporating artificial intelligence (AI) into autonomous energy management in distributed energy resources of SG2 creates new challenges. Accordingly, adversarial samples and false data injection on electricity reading and measurement sensors at power plants can fool AI-powered control functions and cause messy error-checking operations in energy storage, wrong energy estimation in electric vehicle charging, and even fraudulent transactions in peer-to-peer energy trading models. Scalable blockchain-based models, physical unclonable function, interoperable security protocols, and trustworthy AI models designed for managing distributed microgrids in SG2 are typical promising protection models for future research., Comment: 30 pages, 21 figures, 5 tables, accepted to appear in IEEE COMST

Dynamical quantum systems both driven by unitary evolutions and monitored through measurements have proved to be fertile ground for exploring new dynamical quantum matters. While the entanglement structure and symmetry properties of monitored systems have been intensively studied, the role of topology in monitored dynamics is much less explored. In this work, we investigate novel topological phenomena in the monitored dynamics through the lens of free-fermion systems. Free-fermion monitored dynamics were previously shown to be unified with the Anderson localization problem under the Altland-Zirnbauer symmetry classification. Guided by this unification, we identify the topological area-law-entangled phases in the former setting through the topological classification of disordered insulators and superconductors in the latter. As examples, we focus on 1+1D free-fermion monitored dynamics in two symmetry classes, DIII and A. We construct quantum circuit models to study different topological area-law phases and their domain walls in the respective symmetry classes. We find that the domain wall between topologically distinct area-law phases hosts dynamical topological modes whose entanglement is protected from being quenched by the measurements in the monitored dynamics. We demonstrate how to manipulate these topological modes by programming the domain-wall dynamics. In particular, for topological modes in class DIII, which behave as unmeasured Majorana modes, we devise a protocol to braid them and study the entanglement generated in the braiding process., Comment: 7 pages, 4 figures in the main text

In this paper, we describe the wall-crossing of the two parameter K-moduli space of pairs (P 2,aQ + bL), where Q is a plane quintic curve and L is a line., Comment: 29 Pages, comments are very welcome!

The rapid development of generative Artificial Intelligence (AI) continually unveils the potential of Semantic Communication (SemCom). However, current talking-face SemCom systems still encounter challenges such as low bandwidth utilization, semantic ambiguity, and diminished Quality of Experience (QoE). This study introduces a Large Generative Model-assisted Talking-face Semantic Communication (LGM-TSC) System tailored for the talking-face video communication. Firstly, we introduce a Generative Semantic Extractor (GSE) at the transmitter based on the FunASR model to convert semantically sparse talking-face videos into texts with high information density. Secondly, we establish a private Knowledge Base (KB) based on the Large Language Model (LLM) for semantic disambiguation and correction, complemented by a joint knowledge base-semantic-channel coding scheme. Finally, at the receiver, we propose a Generative Semantic Reconstructor (GSR) that utilizes BERT-VITS2 and SadTalker models to transform text back into a high-QoE talking-face video matching the user's timbre. Simulation results demonstrate the feasibility and effectiveness of the proposed LGM-TSC system.

Classical density functional theory (cDFT) provides a systematic approach to predict the structure and thermodynamic properties of chemical systems through the single-molecule density profiles. Whereas the statistical-mechanical framework is theoretically rigorous, its practical applications are often constrained by challenges in formulating a reliable free-energy functional and the complexity of solving multidimensional integro-differential equations. In this work, we established an optimized operator learning method that effectively separates the high-dimensional molecular density profile into two lower-dimensional components, thereby exponentially reducing the vast input space. The convoluted operator learning network demonstrates exceptional learning capabilities, accurately mapping the relationship between the density profile of a carbon dioxide system to its one-body direct correlation function using an atomistic polarizable model. The neural operator model can be generalized to more complex systems, offering high-precision cDFT calculations at low computational cost., Comment: 23 pages, 7 figures

Advanced Air Mobility (AAM) operations are expected to transform air transportation while challenging current air traffic management practices. By introducing a novel market-based mechanism, we address the problem of on-demand allocation of capacity-constrained airspace to AAM vehicles with heterogeneous and private valuations. We model airspace and air infrastructure as a collection of contiguous regions with constraints on the number of vehicles that simultaneously enter, stay, or exit each region. Vehicles request access to the airspace with trajectories spanning multiple regions at different times. We use the graph structure of our airspace model to formulate the allocation problem as a path allocation problem on a time-extended graph. To ensure the cost information of AAM vehicles remains private, we introduce a novel mechanism that allocates each vehicle a budget of "air-credits" and anonymously charges prices for traversing the edges of the time-extended graph. We seek to compute a competitive equilibrium that ensures that: (i) capacity constraints are satisfied, (ii) a strictly positive resource price implies that the sector capacity is fully utilized, and (iii) the allocation is integral and optimal for each AAM vehicle given current prices, without requiring access to individual vehicle utilities. However, a competitive equilibrium with integral allocations may not always exist. We provide sufficient conditions for the existence and computation of a fractional-competitive equilibrium, where allocations can be fractional. Building on these theoretical insights, we propose a distributed, iterative, two-step algorithm that: 1) computes a fractional competitive equilibrium, and 2) derives an integral allocation from this equilibrium. We validate the effectiveness of our approach in allocating trajectories for two emerging urban air mobility services: drone delivery and air taxis., Comment: 31 pages, 7 figures, 3 tables

Electromagnetic field simulation is central to designing, optimizing, and validating photonic devices and circuits. However, costly computation associated with numerical simulation poses a significant bottleneck, hindering scalability and turnaround time in the photonic circuit design process. Neural operators offer a promising alternative, but existing SOTA approaches, NeurOLight, struggle with predicting high-fidelity fields for real-world complicated photonic devices, with the best reported 0.38 normalized mean absolute error in NeurOLight. The inter-plays of highly complex light-matter interaction, e.g., scattering and resonance, sensitivity to local structure details, non-uniform learning complexity for full-domain simulation, and rich frequency information, contribute to the failure of existing neural PDE solvers. In this work, we boost the prediction fidelity to an unprecedented level for simulating complex photonic devices with a novel operator design driven by the above challenges. We propose a novel cross-axis factorized PACE operator with a strong long-distance modeling capacity to connect the full-domain complex field pattern with local device structures. Inspired by human learning, we further divide and conquer the simulation task for extremely hard cases into two progressively easy tasks, with a first-stage model learning an initial solution refined by a second model. On various complicated photonic device benchmarks, we demonstrate one sole PACE model is capable of achieving 73% lower error with 50% fewer parameters compared with various recent ML for PDE solvers. The two-stage setup further advances high-fidelity simulation for even more intricate cases. In terms of runtime, PACE demonstrates 154-577x and 11.8-12x simulation speedup over numerical solver using scipy or highly-optimized pardiso solver, respectively. We open sourced the code and dataset., Comment: Accepeted by Neurips 2024, 21 pages

An amplitude analysis of the $D_{s1}(2460)^+\to D_{s}^{+}\pi^{+}\pi^{-}$ transition is performed simultaneously in $B^{0}\to D^{-}D_{s}^{+}\pi^{+}\pi^{-}$, $B^{+}\to{\bar{D}}^{0} D_{s}^{+}\pi^{+}\pi^{-}$, and $B^{0}\to D^{*-}D_{s}^{+}\pi^{+}\pi^{-}$ decays. The study is based on a data sample of proton-proton collisions recorded with the LHCb detector at centre-of-mass energies of $\sqrt{s}=7,8,$ and $13\,$TeV, corresponding to a total integrated luminosity of $9\,\rm{fb}^{-1}$. A clear double-peak structure is observed in the $m(\pi^{+}\pi^{-})$ spectrum of the $D_{s1}(2460)^{+}\to D_{s}^{+}\pi^{+}\pi^{-}$ decay. The data can be described either with a model including $f_0(500)$, $f_0(980)$ and $f_2(1270)$ resonances, in which the contributions of $f_0(980)$ and $f_2(1270)$ are unexpectedly large, or with a model including $f_0(500)$, a doubly charged open-charm tetraquark state $T_{c\bar{s}}^{++}$ and its isospin partner $T_{c\bar{s}}^{0}$. If the former is considered implausible, the $T_{c\bar{s}}$ states are observed with high significance, and the data are consistent with isospin symmetry. When imposing isospin constraints between the two $T_{c\bar{s}}$ states, their mass and width are determined to be $2327\pm13\pm13\,$MeV and $96\pm16\,^{+170}_{-23}\,$MeV, respectively, where the first uncertainty is statistical and the second is systematic. The mass is slightly below the $DK$ threshold, and a spin-parity of $0^+$ is favoured with high significance., Comment: All figures and tables, along with machine-readable versions and any supplementary material and additional information, are available at https://lbfence.cern.ch/alcm/public/analysis/full-details/3280/ (LHCb public pages)

The detection of satellite thermal emission at millimeter wavelengths is presented using data from the 3rd-Generation receiver on the South Pole Telescope (SPT-3G). This represents the first reported detection of thermal emission from artificial satellites at millimeter wavelengths. Satellite thermal emission is shown to be detectable at high signal-to-noise on timescales as short as a few tens of milliseconds. An algorithm for downloading orbital information and tracking known satellites given observer constraints and time-ordered observatory pointing is described. Consequences for cosmological surveys and short-duration transient searches are discussed, revealing that the integrated thermal emission from all large satellites does not contribute significantly to the SPT-3G survey intensity map. Measured satellite positions are found to be discrepant from their two-line element (TLE) derived ephemerides up to several arcminutes which may present a difficulty in cross-checking or masking satellites from short-duration transient searches.

This paper investigates semantic communications between a transmitter and a receiver, where original data, such as videos of interest to the receiver, is stored at the transmitter. Although significant process has been made in semantic communications, a fundamental design problem is that the semantic information is extracted based on certain criteria at the transmitter alone, without considering the receiver's specific information needs. As a result, critical information of primary concern to the receiver may be lost. In such cases, the semantic transmission becomes meaningless to the receiver, as all received information is irrelevant to its interests. To solve this problem, this paper presents a receiver-centric generative semantic communication system, where each transmission is initialized by the receiver. Specifically, the receiver first sends its request for the desired semantic information to the transmitter at the start of each transmission. Then, the transmitter extracts the required semantic information accordingly. A key challenge is how the transmitter understands the receiver's requests for semantic information and extracts the required semantic information in a reasonable and robust manner. We address this challenge by designing a well-structured framework and leveraging off-the-shelf generative AI products, such as GPT-4, along with several specialized tools for detection and estimation. Evaluation results demonstrate the feasibility and effectiveness of the proposed new semantic communication system., Comment: Demo video has been made available at: https://goo.su/dUnAT

TSE(Target Speaker Extraction) aims to extract the clean speech of the target speaker in an audio mixture, thus eliminating irrelevant background noise and speech. While prior work has explored various auxiliary cues including pre-recorded speech, visual information (e.g., lip motions and gestures), and spatial information, the acquisition and selection of such strong cues are infeasible in many practical scenarios. Unlike all existing work, in this paper, we condition the TSE algorithm on semantic cues extracted from limited and unaligned text content, such as condensed points from a presentation slide. This method is particularly useful in scenarios like meetings, poster sessions, or lecture presentations, where acquiring other cues in real-time is challenging. To this end, we design two different networks. Specifically, our proposed TPE fuses audio features with content-based semantic cues to facilitate time-frequency mask generation to filter out extraneous noise, while another proposal, namely TSR, employs the contrastive learning technique to associate blindly separated speech signals with semantic cues. The experimental results show the efficacy in accurately identifying the target speaker by utilizing semantic cues derived from limited and unaligned text, resulting in SI-SDRi of 12.16 dB, SDRi of 12.66 dB, PESQi of 0.830 and STOIi of 0.150, respectively. Dataset and source code will be publicly available. Project demo page: https://slideTSE.github.io/.

Speech separation seeks to separate individual speech signals from a speech mixture. Typically, most separation models are trained on synthetic data due to the unavailability of target reference in real-world cocktail party scenarios. As a result, there exists a domain gap between real and synthetic data when deploying speech separation models in real-world applications. In this paper, we propose a self-supervised domain-invariant pretrained (DIP) frontend that is exposed to mixture data without the need for target reference speech. The DIP frontend utilizes a Siamese network with two innovative pretext tasks, mixture predictive coding (MPC) and mixture invariant coding (MIC), to capture shared contextual cues between real and synthetic unlabeled mixtures. Subsequently, we freeze the DIP frontend as a feature extractor when training the downstream speech separation models on synthetic data. By pretraining the DIP frontend with the contextual cues, we expect that the speech separation skills learned from synthetic data can be effectively transferred to real data. To benefit from the DIP frontend, we introduce a novel separation pipeline to align the feature resolution of the separation models. We evaluate the speech separation quality on standard benchmarks and real-world datasets. The results confirm the superiority of our DIP frontend over existing speech separation models. This study underscores the potential of large-scale pretraining to enhance the quality and intelligibility of speech separation in real-world applications., Comment: IEEE/ACM Transactions on Audio, Speech, and Language Processing

Worst-case fairness with off-the-shelf demographics achieves group parity by maximizing the model utility of the worst-off group. Nevertheless, demographic information is often unavailable in practical scenarios, which impedes the use of such a direct max-min formulation. Recent advances have reframed this learning problem by introducing the lower bound of minimal partition ratio, denoted as $\alpha$, as side information, referred to as ``$\alpha$-sized worst-case fairness'' in this paper. We first justify the practical significance of this setting by presenting noteworthy evidence from the data privacy perspective, which has been overlooked by existing research. Without imposing specific requirements on loss functions, we propose reweighting the training samples based on their intrinsic importance to fairness. Given the global nature of the worst-case formulation, we further develop a stochastic learning scheme to simplify the training process without compromising model performance. Additionally, we address the issue of outliers and provide a robust variant to handle potential outliers during model training. Our theoretical analysis and experimental observations reveal the connections between the proposed approaches and existing ``fairness-through-reweighting'' studies, with extensive experimental results on fairness benchmarks demonstrating the superiority of our methods.

Graph neural networks (GNNs) are gaining popularity for processing graph-structured data. In real-world scenarios, graph data within the same dataset can vary significantly in scale. This variability leads to depth-sensitivity, where the optimal depth of GNN layers depends on the scale of the graph data. Empirically, fewer layers are sufficient for message passing in smaller graphs, while larger graphs typically require deeper networks to capture long-range dependencies and global features. However, existing methods generally use a fixed number of GNN layers to generate representations for all graphs, overlooking the depth-sensitivity issue in graph structure data. To address this challenge, we propose the depth adaptive mixture of expert (DA-MoE) method, which incorporates two main improvements to GNN backbone: \textbf{1)} DA-MoE employs different GNN layers, each considered an expert with its own parameters. Such a design allows the model to flexibly aggregate information at different scales, effectively addressing the depth-sensitivity issue in graph data. \textbf{2)} DA-MoE utilizes GNN to capture the structural information instead of the linear projections in the gating network. Thus, the gating network enables the model to capture complex patterns and dependencies within the data. By leveraging these improvements, each expert in DA-MoE specifically learns distinct graph patterns at different scales. Furthermore, comprehensive experiments on the TU dataset and open graph benchmark (OGB) have shown that DA-MoE consistently surpasses existing baselines on various tasks, including graph, node, and link-level analyses. The code are available at \url{https://github.com/Celin-Yao/DA-MoE}., Comment: 8pages

We explore the entanglement dynamics of two detectors undergoing uniform acceleration and circular motion within a massive scalar field, while also investigating the influence of the anti-Unruh effect on entanglement harvesting. Contrary to the conventional understanding of the weak anti-Unruh effect, where entanglement typically increases, we observe that the maximum entanglement between detectors does not exhibit a strict monotonic dependence on detector acceleration. Particularly at low accelerations, fluctuations in the entanglement maxima show a strong correlation with fluctuations in detector transition rates.We also find that the maximum entanglement of detectors tends to increase with smaller field mass. Novelly, our findings indicate the absence of a strong anti-Unruh effect in (3+1)-dimensional massive scalar fields. Instead, thermal effects arising from acceleration contribute to a decrease in the detector entanglement maximum.

With the development of large language models (LLMs), the ability to handle longer contexts has become a key capability for Web applications such as cross-document understanding and LLM-powered search systems. However, this progress faces two major challenges: performance degradation due to sequence lengths out-of-distribution, and excessively long inference times caused by the quadratic computational complexity of attention. These issues hinder the application of LLMs in long-context scenarios. In this paper, we propose Dynamic Token-Level KV Cache Selection (TokenSelect), a model-agnostic, training-free method for efficient and accurate long-context inference. TokenSelect builds upon the observation of non-contiguous attention sparsity, using Query-Key dot products to measure per-head KV Cache criticality at token-level. By per-head soft voting mechanism, TokenSelect selectively involves a small number of critical KV cache tokens in the attention calculation without sacrificing accuracy. To further accelerate TokenSelect, we designed the Selection Cache based on observations of consecutive Query similarity and implemented efficient dot product kernel, significantly reducing the overhead of token selection. A comprehensive evaluation of TokenSelect demonstrates up to 23.84x speedup in attention computation and up to 2.28x acceleration in end-to-end latency, while providing superior performance compared to state-of-the-art long-context inference methods.

We present a thorough analysis of the use of CXL-based heterogeneous systems. We built a cluster of server systems that combines different vendor's CPUs and various types of CXL devices. We further developed a heterogeneous memory benchmark suite, Heimdall, to profile the performance of such heterogeneous systems. By leveraging Heimdall, we unveiled the detailed architecture design in these systems, drew observations on optimizing performance for workloads, and pointed out directions for future development of CXL-based heterogeneous systems.

In this work, we demonstrate the equivalency of the Rotating Parallel Ray Omnidirectional Integration (RPR-ODI) and the Pressure Poisson Equation (PPE) for pressure field reconstruction from corrupted image velocimetry data. Building on the work by Zigunov and Charonko (2024b), we show that performing the ODI is equivalent to pursuing the minimum norm least square solution to a Poisson equation with all Neumann boundary conditions, which is an ill-posed problem. Looking through the lenses of the well-posedness of the Poisson equation, linear algebra, as well as regression and optimization, we provide a comprehensive and integrated framework to analyze ODI/PPE-based pressure field reconstruction methods. The new comprehensions on the equivalence of ODI and PPE not only can reduce the immense computational cost of ODI to that of PPE, but more importantly, unveil their shared strengths and limitations. This paves the way for further improvements in ODI/PPE-based pressure field reconstruction by utilizing the extensive literature on fast, robust elliptic solvers and their associated regularization methods. Throughout this work, we include remarks and notes offering theoretical and computational insights valuable to experimentalists. Some of these notes illustrate a ``minimalist" regularization strategy, serving as ``minimal reproducible examples" that provide a foundation for further refinement. Numerical experiments are presented to support and illustrate these arguments.

Texturing is a crucial step in the 3D asset production workflow, which enhances the visual appeal and diversity of 3D assets. Despite recent advancements in Text-to-Texture (T2T) generation, existing methods often yield subpar results, primarily due to local discontinuities, inconsistencies across multiple views, and their heavy dependence on UV unwrapping outcomes. To tackle these challenges, we propose a novel generation-refinement 3D texturing framework called MVPaint, which can generate high-resolution, seamless textures while emphasizing multi-view consistency. MVPaint mainly consists of three key modules. 1) Synchronized Multi-view Generation (SMG). Given a 3D mesh model, MVPaint first simultaneously generates multi-view images by employing an SMG model, which leads to coarse texturing results with unpainted parts due to missing observations. 2) Spatial-aware 3D Inpainting (S3I). To ensure complete 3D texturing, we introduce the S3I method, specifically designed to effectively texture previously unobserved areas. 3) UV Refinement (UVR). Furthermore, MVPaint employs a UVR module to improve the texture quality in the UV space, which first performs a UV-space Super-Resolution, followed by a Spatial-aware Seam-Smoothing algorithm for revising spatial texturing discontinuities caused by UV unwrapping. Moreover, we establish two T2T evaluation benchmarks: the Objaverse T2T benchmark and the GSO T2T benchmark, based on selected high-quality 3D meshes from the Objaverse dataset and the entire GSO dataset, respectively. Extensive experimental results demonstrate that MVPaint surpasses existing state-of-the-art methods. Notably, MVPaint could generate high-fidelity textures with minimal Janus issues and highly enhanced cross-view consistency., Comment: Project Page: https://mvpaint.github.io

Directed acyclic graphs (DAGs) serve as crucial data representations in domains such as hardware synthesis and compiler/program optimization for computing systems. DAG generative models facilitate the creation of synthetic DAGs, which can be used for benchmarking computing systems while preserving intellectual property. However, generating realistic DAGs is challenging due to their inherent directional and logical dependencies. This paper introduces LayerDAG, an autoregressive diffusion model, to address these challenges. LayerDAG decouples the strong node dependencies into manageable units that can be processed sequentially. By interpreting the partial order of nodes as a sequence of bipartite graphs, LayerDAG leverages autoregressive generation to model directional dependencies and employs diffusion models to capture logical dependencies within each bipartite graph. Comparative analyses demonstrate that LayerDAG outperforms existing DAG generative models in both expressiveness and generalization, particularly for generating large-scale DAGs with up to 400 nodes-a critical scenario for system benchmarking. Extensive experiments on both synthetic and real-world flow graphs from various computing platforms show that LayerDAG generates valid DAGs with superior statistical properties and benchmarking performance. The synthetic DAGs generated by LayerDAG enhance the training of ML-based surrogate models, resulting in improved accuracy in predicting performance metrics of real-world DAGs across diverse computing platforms., Comment: Code available at https://github.com/Graph-COM/LayerDAG

We explore optimally training protein language models, an area of significant interest in biological research where guidance on best practices is limited. Most models are trained with extensive compute resources until performance gains plateau, focusing primarily on increasing model sizes rather than optimizing the efficient compute frontier that balances performance and compute budgets. Our investigation is grounded in a massive dataset consisting of 939 million protein sequences. We trained over 300 models ranging from 3.5 million to 10.7 billion parameters on 5 to 200 billion unique tokens, to investigate the relations between model sizes, training token numbers, and objectives. First, we observed the effect of diminishing returns for the Causal Language Model (CLM) and that of overfitting for the Masked Language Model~(MLM) when repeating the commonly used Uniref database. To address this, we included metagenomic protein sequences in the training set to increase the diversity and avoid the plateau or overfitting effects. Second, we obtained the scaling laws of CLM and MLM on Transformer, tailored to the specific characteristics of protein sequence data. Third, we observe a transfer scaling phenomenon from CLM to MLM, further demonstrating the effectiveness of transfer through scaling behaviors based on estimated Effectively Transferred Tokens. Finally, to validate our scaling laws, we compare the large-scale versions of ESM-2 and PROGEN2 on downstream tasks, encompassing evaluations of protein generation as well as structure- and function-related tasks, all within less or equivalent pre-training compute budgets., Comment: NeurIPS 2024 (Spotlight); Code: https://github.com/cxysteven/ScalingProteinLM. Additional resources are available here

We demonstrate a dual wavelength optical frequency standard based on the dual optical transition modulation transfer spectroscopy (DOTMTS) between different quantum transitions of the rubidium D1 (795 nm) and D2 (780 nm) lines. In a single rubidium atomic ensemble, modulation frequency sidebands from the 780 nm pump beam are simultaneously transferred to both the 780 nm and 795 nm probe lasers. The DOTMTS enables the simultaneous stabilization of 780 nm and 795 nm lasers on a single vapor cell. Both lasers exhibit a frequency instability in the low 10 ^(-14) range at 1 s of averaging, as estimated from the residual error signal. A theoretical model is developed based on the V type atomic level structure to illustrate the dual-wavelength spectroscopy. This approach can be extended to develop a multiwavelength optical frequency standard within a single atomic ensemble, broadening its applicability in fields such as precision metrology, wavelength standards, optical networks, and beyond.

Zero-shot voice conversion (VC) aims to transform the timbre of a source speaker into any previously unseen target speaker, while preserving the original linguistic content. Despite notable progress, attaining a degree of speaker similarity and naturalness on par with ground truth recordings continues to pose great challenge. In this paper, we propose CTEFM-VC, a zero-shot VC framework that leverages Content-aware Timbre Ensemble modeling and Flow Matching. Specifically, CTEFM-VC disentangles utterances into linguistic content and timbre representations, subsequently utilizing a conditional flow matching model and a vocoder to reconstruct the mel-spectrogram and waveform. To enhance its timbre modeling capability and the naturalness of generated speech, we propose a context-aware timbre ensemble modeling approach that adaptively integrates diverse speaker verification embeddings and enables the joint utilization of linguistic and timbre features through a cross-attention module. Experiments show that our CTEFM-VC system surpasses state-of-the-art VC methods in both speaker similarity and naturalness by at least 18.5% and 7.0%., Comment: Work in progress; 5 pages

We present two cases of Ly$\alpha$ changing-look (CL) quasars (J1306 and J1512) along with two additional candidates (J1511 and J1602), all discovered serendipitously at $z >2$ through the Dark Energy Spectroscopic Instrument (DESI) and the Sloan Digital Sky Survey (SDSS). It is the first time to capture CL events in Ly$\alpha$ at high redshift, which is crucial for understanding underlying mechanisms driving the CL phenomenon and the evolution of high-redshift quasars and galaxies. The variability of all four sources is confirmed by the significant change of amplitude in the $r$ band ($|r_{\rm DESI}-r_{\rm SDSS}| >0.5 \ \rm mag$). We find that the accretion rate in the dim state for these CL objects corresponds to a relatively low value ($\mathscr{\dot M} \approx 2\times10^{-3}$), which suggests that the inner region of the accretion disk might be in transition between the Advection Dominated Accretion Flow ($\mathscr{\dot M}<10^{-3}\sim 10^{-2}$) and the canonical accretion disk (optically thick, geometrically thin). However, unlike in C {\sc iv} CL quasars in which broad Ly$\alpha$ remained, the broad C {\sc iv} may still persist after a CL event occurs in Ly$\alpha$, making the physical origin of the CL and ionization mechanism event more puzzling and interesting.

Bright dipolar excitons, which contain electrical dipoles and have high oscillator strength, are an ideal platform for studying correlated quantum phenomena. They usually rely on carrier tunneling between two quantum wells or two layers to hybridize with nondipolar excitons to gain oscillator strength. In this work, we uncovered a new type of bright infrared dipolar exciton by stacking 90{\deg}-twisted black phosphorus (BP) structures. These excitons, inherent to the reconstructed band structure, exhibit high oscillator strength. Most importantly, they inherit the linear polarization from BP, which allows light polarization to be used to select the dipole direction. Moreover, the dipole moment and resonance energy can be widely tuned by the thickness of the BP. Our results demonstrate a useful platform for exploring tunable correlated dipolar excitons.

This paper establishes the equivalence between synchronous and asynchronous coordination mechanisms in dynamic games with strategic complementarities and common interests. Synchronous coordination, characterized by simultaneous commitments, and asynchronous coordination, defined by sequential action timing, are both prevalent in economic contexts such as crowdfunding and fund management. We introduce Monotone Subgame Perfect Nash Equilibrium, MSPNE, to analyze least favorable equilibrium outcomes. We provide a recursive characterization for synchronous coordination and a graph-theoretic representation for asynchronous coordination, demonstrating their equivalence in terms of the greatest implementable outcome. Our results show that the structure of commitment, whether simultaneous or sequential, does not affect the achievable welfare outcome under certain conditions. Additionally, we discuss computational aspects, highlighting the general NP-Hardness of the problem but identifying a significant class of games that are computationally tractable. These findings offer valuable insights for the optimal design of coordination mechanisms.

Large language models (LLMs) are emerging as few-shot learners capable of handling a variety of tasks, including comprehension, planning, reasoning, question answering, arithmetic calculations, and more. At the core of these capabilities is LLMs' proficiency in representing and understanding structural or semi-structural data, such as tables and graphs. Numerous studies have demonstrated that reasoning on tabular data or graphs is not only feasible for LLMs but also gives a promising research direction which treats these data as in-context data. The lightweight and human readable characteristics of in-context database can potentially make it an alternative for the traditional database in typical RAG (Retrieval Augmented Generation) settings. However, almost all current work focuses on static in-context data, which does not allow dynamic update. In this paper, to enable dynamic database update, delta encoding of database is proposed. We explore how data stored in traditional RDBMS can be encoded as in-context text and evaluate LLMs' proficiency for CRUD (Create, Read, Update and Delete) operations on in-context databases. A benchmark named InConDB is presented and extensive experiments are conducted to show the performance of different language models in enabling in-context database by varying the database encoding method, prompting method, operation type and input data distribution, revealing both the proficiency and limitations.

In this work, we focus on two important aspects of modern cosmology: reheating and Hubble constant tension within the framework of a unified model, namely, quintessential inflation connecting the early inflationary era and late-time cosmic acceleration. In the context of reheating, we use instant preheating and gravitational reheating, two viable reheating mechanisms when the evolution of the universe is not affected by an oscillating regime. After obtaining the reheating temperature, we analyze the number of $e$-folds and establish its relationship with the reheating temperature. This allows us to connect, for different quintessential inflation models, the reheating temperature with the spectral index of scalar perturbations, thereby enabling us to constrain its values. In the second part of this article, we explore various alternatives to address the $H_0$ tension, a discrepancy which indicates a possible revision of the $\Lambda$CDM model. Initially, we establish that quintessential inflation alone cannot mitigate the Hubble tension by solely deviating from the concordance model at low redshifts. The introduction of a phantom fluid, capable of increasing the Hubble rate at the present time, becomes a crucial element in alleviating the Hubble tension, resulting in a deviation from the $\Lambda$CDM model only at low redshifts. On a different note, by utilizing quintessential inflation as a source of early dark energy, thereby diminishing the physical size of the sound horizon close to the baryon-photon decoupling redshift, we observe a reduction in the Hubble tension. This alternative avenue, which has the same effect of a cosmological constant changing its scale close to the recombination, sheds light on the nuanced interplay between the quintessential inflation and the Hubble tension, offering a distinct perspective on addressing this cosmological challenge., Comment: 13 pages including bibliography, 5 figures; Invited article from Symmetry; Abstract has been shortened, but the full abstract is kept in the journal version; published version

A plethora of text-guided image editing methods has recently been developed by leveraging the impressive capabilities of large-scale diffusion-based generative models especially Stable Diffusion. Despite the success of diffusion models in producing high-quality images, their application to small object generation has been limited due to difficulties in aligning cross-modal attention maps between text and these objects. Our approach offers a training-free method that significantly mitigates this alignment issue with local and global attention guidance , enhancing the model's ability to accurately render small objects in accordance with textual descriptions. We detail the methodology in our approach, emphasizing its divergence from traditional generation techniques and highlighting its advantages. What's more important is that we also provide~\textit{SOEBench} (Small Object Editing), a standardized benchmark for quantitatively evaluating text-based small object generation collected from \textit{MSCOCO} and \textit{OpenImage}. Preliminary results demonstrate the effectiveness of our method, showing marked improvements in the fidelity and accuracy of small object generation compared to existing models. This advancement not only contributes to the field of AI and computer vision but also opens up new possibilities for applications in various industries where precise image generation is critical. We will release our dataset on our project page: \href{https://soebench.github.io/}{https://soebench.github.io/}., Comment: 9 pages, 8 figures, Accepted by ACMMM 2024

Diffusion models are pivotal for generating high-quality images and videos. Inspired by the success of OpenAI's Sora, the backbone of diffusion models is evolving from U-Net to Transformer, known as Diffusion Transformers (DiTs). However, generating high-quality content necessitates longer sequence lengths, exponentially increasing the computation required for the attention mechanism, and escalating DiTs inference latency. Parallel inference is essential for real-time DiTs deployments, but relying on a single parallel method is impractical due to poor scalability at large scales. This paper introduces xDiT, a comprehensive parallel inference engine for DiTs. After thoroughly investigating existing DiTs parallel approaches, xDiT chooses Sequence Parallel (SP) and PipeFusion, a novel Patch-level Pipeline Parallel method, as intra-image parallel strategies, alongside CFG parallel for inter-image parallelism. xDiT can flexibly combine these parallel approaches in a hybrid manner, offering a robust and scalable solution. Experimental results on two 8xL40 GPUs (PCIe) nodes interconnected by Ethernet and an 8xA100 (NVLink) node showcase xDiT's exceptional scalability across five state-of-the-art DiTs. Notably, we are the first to demonstrate DiTs scalability on Ethernet-connected GPU clusters. xDiT is available at https://github.com/xdit-project/xDiT.

In this article we calculate the reheating temperature in the cosmological scenarios where heavy scalar particles are gravitationally produced, due to a conformally coupled interaction between a massive scalar quantum field and the Ricci scalar, during the oscillations of the inflaton field. We explore two distinct cases, namely the one in which these particles decay during the domination of the inflaton's energy density and the other one where the decay occurs after this phase. For each scenario, we have derived formulas to calculate the reheating temperatures based on the energy density of the produced particles and their decay rate. We establish bounds for the maximum reheating temperature, defined as the temperature reached by the universe when the decay of gravitationally produced particles concludes at the onset of the radiation-dominated epoch. Finally, we use the Born approximation to find analytic formulas for the reheating temperature., Comment: 15 pages including bibliography and 1 figure; Accepted for publication in Phys. Rev. D

In this paper, we pave the way to six-generation (6G) by investigating the outage probability (OP) of fluid antenna system (FAS)-active reconfigurable intelligent surface (ARIS) communication systems. We consider a FAS-ARIS setup consisting of a base station (BS) with a single fixed-position antenna and a receiver equipped with a fluid antenna (FA). Utilizing the block-correlation model, we derive a closed-form expression for the OP. Our analysis, supported by numerical results, confirms the accuracy and effectiveness of the derivation. Furthermore, the results demonstrate that the FAS-ARIS system significantly outperforms other configurations in terms of OP, highlighting its potential to enhance communication performance and reliability in future 6G networks.

We study the sample median of independently generated quasi-Monte Carlo estimators based on randomized digital nets and prove it approximates the target integral value at almost the optimal convergence rate for various function spaces. Contrast to previous methods, the algorithm does not require a prior knowledge of underlying function spaces or even an input of pre-designed $(t,m,s)$-digital nets, and is therefore easier to implement. This study provides further evidence that quasi-Monte Carlo estimators are heavy-tailed when applied to smooth integrands and taking the median can significantly improve the error by filtering out the outliers.

For high dimensional sparse linear regression problems, we propose a sequential convex relaxation algorithm (iSCRA-TL1) by solving inexactly a sequence of truncated $\ell_1$-norm regularized minimization problems, in which the working index sets are constructed iteratively with an adaptive strategy. We employ the robust restricted null space property and sequential restricted null space property (rRNSP and rSRNSP) to provide the theoretical certificates of iSCRA-TL1. Specifically, under a mild rRNSP or rSRNSP, iSCRA-TL1 is shown to identify the support of the true $r$-sparse vector by solving at most $r$ truncated $\ell_1$-norm regularized problems, and the $\ell_1$-norm error bound of its iterates from the oracle solution is also established. As a consequence, an oracle estimator of high-dimensional linear regression problems can be achieved by solving at most $r\!+\!1$ truncated $\ell_1$-norm regularized problems. To the best of our knowledge, this is the first sequential convex relaxation algorithm to produce an oracle estimator under a weaker NSP condition within a specific number of steps, provided that the Lasso estimator lacks high quality, say, the supports of its first $r$ largest (in modulus) entries do not coincide with those of the true vector., Comment: 38 pages, 4 figures

Alongside the rapid development of Large Language Models (LLMs), there has been a notable increase in efforts to integrate LLM techniques in information retrieval (IR) and search engines (SE). Recently, an additional post-ranking stage is suggested in SE to enhance user satisfaction in practical applications. Nevertheless, research dedicated to enhancing the post-ranking stage through LLMs remains largely unexplored. In this study, we introduce a novel paradigm named Large Language Models for Post-Ranking in search engine (LLM4PR), which leverages the capabilities of LLMs to accomplish the post-ranking task in SE. Concretely, a Query-Instructed Adapter (QIA) module is designed to derive the user/item representation vectors by incorporating their heterogeneous features. A feature adaptation step is further introduced to align the semantics of user/item representations with the LLM. Finally, the LLM4PR integrates a learning to post-rank step, leveraging both a main task and an auxiliary task to fine-tune the model to adapt the post-ranking task. Experiment studies demonstrate that the proposed framework leads to significant improvements and exhibits state-of-the-art performance compared with other alternatives.

Retrieval-augmented generation methods often neglect the quality of content retrieved from external knowledge bases, resulting in irrelevant information or potential misinformation that negatively affects the generation results of large language models. In this paper, we propose an end-to-end model with adaptive filtering for retrieval-augmented generation (E2E-AFG), which integrates answer existence judgment and text generation into a single end-to-end framework. This enables the model to focus more effectively on relevant content while reducing the influence of irrelevant information and generating accurate answers. We evaluate E2E-AFG on six representative knowledge-intensive language datasets, and the results show that it consistently outperforms baseline models across all tasks, demonstrating the effectiveness and robustness of the proposed approach., Comment: 13 pages, 3 figures, 5 tables

Recent advancements in quantum computing have led to significant research into applying quantum algorithms to combinatorial optimization problems. Among these challenges, the Total Domination Problem (TDP) is particularly noteworthy, representing a classic and critical example in the field. Since the last century, research efforts have focused on establishing its NP-completeness and developing algorithms for its resolution, which have been fundamental to combinatorial mathematics. Despite this rich history, the application of quantum algorithms to the TDP remains largely unexplored. In this study, we present a pioneering application of the Quantum Approximate Optimization Algorithm (QAOA) to tackle the TDP, evaluating its efficacy across a diverse array of parameters. Our experimental findings indicate that QAOA is effective in addressing the TDP; under most parameter combinations, it successfully computes the correct total dominating set (TDS). However, the algorithm's performance in identifying the optimal TDS is contingent upon the specific parameter choices, revealing a significant bias in the distribution of effective parameter points. This research contributes valuable insights into the potential of quantum algorithms for addressing the TDP and lays the groundwork for future investigations in this area., Comment: 22 pages, 11 figures

Traditional methods for optimizing light source emissions rely on a time-consuming trial-and-error approach. While in-situ optimization of light source gain media emission during growth is ideal, it has yet to be realized. In this work, we integrate in-situ reflection high-energy electron diffraction (RHEED) with machine learning (ML) to correlate the surface reconstruction with the photoluminescence (PL) of InAs/GaAs quantum dots (QDs), which serve as the active region of lasers. A lightweight ResNet-GLAM model is employed for the real-time processing of RHEED data as input, enabling effective identification of optical performance. This approach guides the dynamic optimization of growth parameters, allowing real-time feedback control to adjust the QDs emission for lasers. We successfully optimized InAs QDs on GaAs substrates, with a 3.2-fold increase in PL intensity and a reduction in full width at half maximum (FWHM) from 36.69 meV to 28.17 meV under initially suboptimal growth conditions. Our automated, in-situ self-optimized lasers with 5-layer InAs QDs achieved electrically pumped continuous-wave operation at 1240 nm with a low threshold current of 150 A/cm2 at room temperature, an excellent performance comparable to samples grown through traditional manual multi-parameter optimization methods. These results mark a significant step toward intelligent, low-cost, and reproductive light emitters production., Comment: 5 figures

In recent times, Vision-Language Models (VLMs) have been trained under two predominant paradigms. Generative training has enabled Multimodal Large Language Models (MLLMs) to tackle various complex tasks, yet issues such as hallucinations and weak object discrimination persist. Discriminative training, exemplified by models like CLIP, excels in zero-shot image-text classification and retrieval, yet struggles with complex scenarios requiring fine-grained semantic differentiation. This paper addresses these challenges by proposing a unified approach that integrates the strengths of both paradigms. Considering interleaved image-text sequences as the general format of input samples, we introduce a structure-induced training strategy that imposes semantic relationships between input samples and the MLLM's hidden state. This approach enhances the MLLM's ability to capture global semantics and distinguish fine-grained semantics. By leveraging dynamic sequence alignment within the Dynamic Time Warping framework and integrating a novel kernel for fine-grained semantic differentiation, our method effectively balances generative and discriminative tasks. Extensive experiments demonstrate the effectiveness of our approach, achieving state-of-the-art results in multiple generative tasks, especially those requiring cognitive and discrimination abilities. Additionally, our method surpasses discriminative benchmarks in interleaved and fine-grained retrieval tasks. By employing a retrieval-augmented generation strategy, our approach further enhances performance in some generative tasks within one model, offering a promising direction for future research in vision-language modeling.

Current agricultural data management and analysis paradigms are to large extent traditional, in which data collecting, curating, integration, loading, storing, sharing and analyzing still involve too much human effort and know-how. The experts, researchers and the farm operators need to understand the data and the whole process of data management pipeline to make fully use of the data. The essential problem of the traditional paradigm is the lack of a layer of orchestrational intelligence which can understand, organize and coordinate the data processing utilities to maximize data management and analysis outcome. The emerging reasoning and tool mastering abilities of large language models (LLM) make it a potentially good fit to this position, which helps a shift from the traditional user-driven paradigm to AI-driven paradigm. In this paper, we propose and explore the idea of a LLM based copilot for autonomous agricultural data management and analysis. Based on our previously developed platform of Agricultural Data Management and Analytics (ADMA), we build a proof-of-concept multi-agent system called ADMA Copilot, which can understand user's intent, makes plans for data processing pipeline and accomplishes tasks automatically, in which three agents: a LLM based controller, an input formatter and an output formatter collaborate together. Different from existing LLM based solutions, by defining a meta-program graph, our work decouples control flow and data flow to enhance the predictability of the behaviour of the agents. Experiments demonstrates the intelligence, autonomy, efficacy, efficiency, extensibility, flexibility and privacy of our system. Comparison is also made between ours and existing systems to show the superiority and potential of our system.

Code translation transforms programs from one programming language (PL) to another. Several rule-based transpilers have been designed to automate code translation between different pairs of PLs. However, the rules can become obsolete as the PLs evolve and cannot generalize to other PLs. Recent studies have explored the automation of code translation using Large Language Models (LLMs). One key observation is that such techniques may work well for crafted benchmarks but fail to generalize to the scale and complexity of real-world projects with dependencies, custom types, PL-specific features, etc. We propose AlphaTrans, a neuro-symbolic approach to automate repository-level code translation. AlphaTrans translates both source and test code, and employs multiple levels of validation to ensure the translation preserves the functionality of the source program. To break down the problem for LLMs, AlphaTrans leverages program analysis to decompose the program into fragments and translates them in the reverse call order. We leveraged AlphaTrans to translate ten real-world open-source projects consisting of <836, 8575, 2719> classes, methods, and tests. AlphaTrans translated the entire repository of these projects consisting of 6899 source code fragments. 99.1% of the translated code fragments are syntactically correct, and AlphaTrans validates the translations' runtime behavior and functional correctness for 25.8%. On average, the integrated translation and validation take 36 hours to translate a project, showing its scalability in practice. For the syntactically or semantically incorrect translations, AlphaTrans generates a report including existing translation, stack trace, test errors, or assertion failures. We provided these artifacts to two developers to fix the translation bugs in four projects. They were able to fix the issues in 20.1 hours on average and achieve all passing tests.

In this paper, we investigate the Hilbert space factorisation problem of two-sided black holes in high dimensions. We demonstrate that the Hilbert space of two-sided black holes can be factorized into the tensor product of two one-sided bulk Hilbert spaces when the effect of non-perturbative replica wormholes is taken into account. We further interpret the one-sided bulk Hilbert space as the Hilbert space of a one-sided black hole. Therefore, since the Hilbert space of a two-sided black hole can be obtained from the tensor product of two single-sided black hole Hilbert spaces, we consider this as an embodiment of the ER=EPR conjecture, and we show when the entanglement between the two single-sided black holes is sufficiently strong, the (Lorentzian) geometry of a two-sided black hole will emerge., Comment: 19 pages, 3 figures

When explaining black-box machine learning models, it's often important for explanations to have certain desirable properties. Most existing methods `encourage' desirable properties in their construction of explanations. In this work, we demonstrate that these forms of encouragement do not consistently create explanations with the properties that are supposedly being targeted. Moreover, they do not allow for any control over which properties are prioritized when different properties are at odds with each other. We propose to directly optimize explanations for desired properties. Our direct approach not only produces explanations with optimal properties more consistently but also empowers users to control trade-offs between different properties, allowing them to create explanations with exactly what is needed for a particular task.

Muons, which play a crucial role in both fundamental and applied physics, have traditionally been generated through proton accelerators or from cosmic rays. With the advent of ultra-short high-intensity lasers capable of accelerating electrons to GeV levels, it has become possible to generate muons in laser laboratories. In this work, we show the first proof of principle experiment for novel muon production with an ultra-short, high-intensity laser device through GeV electron beam bombardment on a lead converter target. The muon physical signal is confirmed by measuring its lifetime which is the first clear demonstration of laser-produced muons. Geant4 simulations were employed to investigate the photo-production, electro-production, and Bethe-Heitler processes response for muon generation and their subsequent detection. The results show that the dominant contributions of muons are attributed to the photo-production/electro-production and a significant yield of muons up to 0.01 $\mu$/$e^-$ out of the converter target could be achieved. This laser muon source features compact, ultra-short pulse and high flux. Moreover, its implementation in a small laser laboratory is relatively straightforward, significantly reducing the barriers to entry for research in areas such as muonic X-ray elemental analysis, muon spin spectroscopy and so on.

Self-occlusion is common when capturing people in the wild, where the performer do not follow predefined motion scripts. This challenges existing monocular human reconstruction systems that assume full body visibility. We introduce Self-Occluded Avatar Recovery (SOAR), a method for complete human reconstruction from partial observations where parts of the body are entirely unobserved. SOAR leverages structural normal prior and generative diffusion prior to address such an ill-posed reconstruction problem. For structural normal prior, we model human with an reposable surfel model with well-defined and easily readable shapes. For generative diffusion prior, we perform an initial reconstruction and refine it using score distillation. On various benchmarks, we show that SOAR performs favorably than state-of-the-art reconstruction and generation methods, and on-par comparing to concurrent works. Additional video results and code are available at https://soar-avatar.github.io/.