Search

We perform the first investigation of the process $e^{+}e^{-}\to K^+K^-\psi(2S)$ and report its Born cross sections over a range of center-of-mass energies from 4.699 to 4.951~GeV. The measurements are carried out using several partial reconstruction techniques using data samples collected by the BESIII detector with a total integrated luminosity of 2.5~fb$^{-1}$. We search for new tetraquark candidates $Z_{cs}^\pm$ in the decays $Z_{cs}^\pm\to K^\pm\psi(2S)$. No significant $Z_{cs}^\pm$ signals are observed., Comment: 9 pages, 4 figures

The ground-breaking discovery of the first fully charmed tetraquark state $X(6900)$ in the $J/\psi J/\psi$ invariant mass distribution by the LHCb collaboration has inspired intensive theoretical studies. Various interpretations, such as molecular states, compact tetraquark states, and coupled-channel effects, have been proposed for these states. Of particular interest is the ongoing search for the triple-$J/\psi$ state--a fully-charmed hexaquark state. To deepen our understanding of the triple-$J/\psi$ state and to guide future experimental searches, we study the triple-$J/\psi$ system in this work employing the Gaussian expansion method and the $J/\psi J/\psi$ potential parameterized to yield a shallow bound state, as suggested in several theoretical works. Our results support a triple-$J/\psi$ bound state, even in cases where the attractive interaction between the two $J/\psi$ mesons is very weak. Moreover, our analysis implies the Efimov effect in the triple-$J/\psi$ system. In addition, we extend our investigation to the triple-$\Upsilon (1S)$ system and obtain results similar to those for the triple-$J/\psi$ system., Comment: 8 pages, 3 figures, 4 tables; comments welcome

The field of integrated circuit (IC) design is highly specialized, presenting significant barriers to entry and research and development challenges. Although large language models (LLMs) have achieved remarkable success in various domains, existing LLMs often fail to meet the specific needs of students, engineers, and researchers. Consequently, the potential of LLMs in the IC design domain remains largely unexplored. To address these issues, we introduce ChipExpert, the first open-source, instructional LLM specifically tailored for the IC design field. ChipExpert is trained on one of the current best open-source base model (Llama-3 8B). The entire training process encompasses several key stages, including data preparation, continue pre-training, instruction-guided supervised fine-tuning, preference alignment, and evaluation. In the data preparation stage, we construct multiple high-quality custom datasets through manual selection and data synthesis techniques. In the subsequent two stages, ChipExpert acquires a vast amount of IC design knowledge and learns how to respond to user queries professionally. ChipExpert also undergoes an alignment phase, using Direct Preference Optimization, to achieve a high standard of ethical performance. Finally, to mitigate the hallucinations of ChipExpert, we have developed a Retrieval-Augmented Generation (RAG) system, based on the IC design knowledge base. We also released the first IC design benchmark ChipICD-Bench, to evaluate the capabilities of LLMs across multiple IC design sub-domains. Through comprehensive experiments conducted on this benchmark, ChipExpert demonstrated a high level of expertise in IC design knowledge Question-and-Answer tasks.

Object detection on the edge (Edge-OD) is in growing demand thanks to its ever-broad application prospects. However, the development of this field is rigorously restricted by the deployment dilemma of simultaneously achieving high accuracy, excellent power efficiency, and meeting strict real-time requirements. To tackle this dilemma, we propose AyE-Edge, the first-of-this-kind development tool that explores automated algorithm-device deployment space search to realize Accurate yet power-Efficient real-time object detection on the Edge. Through a collaborative exploration of keyframe selection, CPU-GPU configuration, and DNN pruning strategy, AyE-Edge excels in extensive real-world experiments conducted on a mobile device. The results consistently demonstrate AyE-Edge's effectiveness, realizing outstanding real-time performance, detection accuracy, and notably, a remarkable 96.7% reduction in power consumption, compared to state-of-the-art (SOTA) competitors.

Superconducting circuits, like Adiabatic Quantum-Flux-Parametron (AQFP), offer exceptional energy efficiency but face challenges in physical design due to sophisticated spacing and timing constraints. Current design tools often neglect the importance of constraint adherence throughout the entire design flow. In this paper, we propose SuperFlow, a fully-customized RTL-to-GDS design flow tailored for AQFP devices. SuperFlow leverages a synthesis tool based on CMOS technology to transform any input RTL netlist to an AQFP-based netlist. Subsequently, we devise a novel place-and-route procedure that simultaneously considers wirelength, timing, and routability for AQFP circuits. The process culminates in the generation of the AQFP circuit layout, followed by a Design Rule Check (DRC) to identify and rectify any layout violations. Our experimental results demonstrate that SuperFlow achieves 12.8% wirelength improvement on average and 12.1% better timing quality compared with previous state-of-the-art placers for AQFP circuits., Comment: Accepted by DATE 2024

Evaluating causal effects in a primary population of interest with unmeasured confounders is challenging. Although instrumental variables (IVs) are widely used to address unmeasured confounding, they may not always be available in the primary population. Fortunately, IVs might have been used in previous observational studies on similar causal problems, and these auxiliary studies can be useful to infer causal effects in the primary population, even if they represent different populations. However, existing methods often assume homogeneity or equality of conditional average treatment effects between the primary and auxiliary populations, which may be limited in practice. This paper aims to remove the homogeneity requirement and establish a novel identifiability result allowing for different conditional average treatment effects across populations. We also construct a multiply robust estimator that remains consistent despite partial misspecifications of the observed data model and achieves local efficiency if all nuisance models are correct. The proposed approach is illustrated through simulation studies. We finally apply our approach by leveraging data from lower income individuals with cigarette price as a valid IV to evaluate the causal effect of smoking on physical functional status in higher income group where strong IVs are not available.

The decay behavior of an exotic state can be used to probe its internal structure. We note that the hidden-charm pentaquark states, $P_{\psi}^{N}(4312)$, $P_{\psi}^{N}(4440)$, and $P_{\psi}^{N}(4457)$, have only been observed in the $J/\psi p$ channel. In this work, we employ the effective Lagrangian approach to systematically investigate the two-body and three-body decays of the heavy quark spin symmetry multiplet of hadronic molecules $\bar{D}^{(*)}\Sigma_c^{(*)}$. Our results show that the partial decay widths of the hidden-charm pentaquark molecules into $\bar{D}^{(*)}\Lambda_c \pi$ are sizable so that $\bar{D}^{(*)}\Lambda_c \pi$ are promising channels to search for them, which can help clarify their molecular nature.

We consider the reconstruction of the vertex weight in the discrete Gel'fand's inverse boundary spectral problem for the graph Laplacian. Given the boundary vertex weight and the edge weight of the graph, we develop reconstruction procedures to recover the interior vertex weight from the Neumann boundary spectral data on a class of finite, connected and weighted graphs. The procedures are divided into two stages: the first stage reconstructs the Neumann-to-Dirichlet map for the graph wave equation from the Neumann boundary spectral data, and the second stage reconstructs the interior vertex weight from the Neumann-to-Dirichlet map using the boundary control method adapted to weighted graphs. For the second stage, we identify a class of weighted graphs where the unique continuation principle holds for the graph wave equation. The reconstruction procedures are further turned into an algorithm, which is implemented and validated on several numerical examples with quantitative performance reported., Comment: 39 pages, 15 figures

Using $(2.712\pm0.014)\times10^{9}$ $\psi(3686)$ events collected with the BESIII detector operating at the BEPCII, we find an evidence of the $\eta_{c}(2S)\to K^+ K^- \eta^{\prime}$ decay with a statistical significance of 3.1$\sigma$. Its decay branching fraction is measured to be $(12.24\pm4.60(\mathrm{stat.})\pm2.37(\mathrm{syst.})\pm4.68(\mathrm{extr.}))\times 10^{-4}$, where the first uncertainty is statistical, the second is systematic, and the third uncertainty is from the branching fraction of the $\psi(3686)\to\gamma\eta_{c}(2S)$ decay. The upper limit on the product branching fraction $B[\psi(3686)\to\gamma\eta_{c}(2S)] \times$ $B[\eta_{c}(2S)\to K^+ K^- \eta^{\prime}]$ is set to be $1.14 \times 10^{-6}$ at $90\%$ confidence level. In addition, the branching fractions of $\chi_{c1}\to K^+ K^- \eta^{\prime}$ and $\chi_{c2}\to K^+ K^- \eta^{\prime}$ are updated to be $(8.47\pm0.09(\mathrm{stat.})\pm0.47(\mathrm{syst.}))\times 10^{-4}$ and $(1.53\pm0.04(\mathrm{stat.})\pm0.08(\mathrm{syst.}))\times 10^{-4}$, respectively. The precision is improved by twofold.

Individual teaching is among the most successful ways to impart knowledge. Yet, this method is not always feasible due to large numbers of students per educator. Quantum computing serves as a prime example facing this issue, due to the hype surrounding it. Alleviating high workloads for teachers, often accompanied with individual teaching, is crucial for continuous high quality education. Therefore, leveraging Large Language Models (LLMs) such as GPT-4 to generate educational content can be valuable. We conducted two complementary studies exploring the feasibility of using GPT-4 to automatically generate tips for students. In the first one students (N=46) solved four multiple-choice quantum computing questions with either the help of expert-created or LLM-generated tips. To correct for possible biases towards LLMs, we introduced two additional conditions, making some participants believe that they were given expert-created tips, when they were given LLM-generated tips and vice versa. Our second study (N=23) aimed to directly compare the LLM-generated and expert-created tips, evaluating their quality, correctness and helpfulness, with both experienced educators and students participating. Participants in our second study found that the LLM-generated tips were significantly more helpful and pointed better towards relevant concepts than the expert-created tips, while being more prone to be giving away the answer. While participants in the first study performed significantly better in answering the quantum computing questions when given tips labeled as LLM-generated, even if they were created by an expert. This phenomenon could be a placebo effect induced by the participants' biases for LLM-generated content. Ultimately, we find that LLM-generated tips are good enough to be used instead of expert tips in the context of quantum computing basics.

Seismic tomography has long been an effective tool for constructing reliable subsurface structures. However, simultaneous inversion of P- and S-wave velocities presents a significant challenge for conventional seismic tomography methods, which depend on numerical algorithms to calculate traveltimes. A physics informed neural network (PINN)-based seismic tomography method (PINNtomo) has been proposed to solve the eikonal equation and construct the velocity model. Leveraging the powerful approximation capabilities of neural networks, we propose extending PINNtomo to perform multiparameter inversion of P- and S-wave velocities jointly, which we refer to as PINNPStomo. In PINNPStomo, we employ two neural networks: one for the P- and S-wave traveltimes, and another for the P- and S-wave velocities. By optimizing the misfits of P- and S-wave first-arrival traveltimes calculated from the eikonal equations, we can obtain the predicted P- and S-wave velocities that determine these traveltimes. Recognizing that the original PINNtomo utilizes a multiplicative factored eikonal equation, which depends on background traveltimes corresponding to a homogeneous velocity at the source location. We propose a new factored eikonal equation for PINNPStomo to eliminate this dependency. The proposed PINNPStomo, incorporating the new factored eikonal equation, demonstrates superior convergence speed and multiparameter inversion accuracy. We validate these improvements using 2D Marmousi and 2D/3D Overthrust elastic velocity models across three different seismic data acquisition geometries., Comment: submitted to Geophysics

With the widespread application of remote sensing technology in environmental monitoring, the demand for efficient and accurate remote sensing image change detection (CD) for natural environments is growing. We propose a novel deep learning framework named EfficientCD, specifically designed for remote sensing image change detection. The framework employs EfficientNet as its backbone network for feature extraction. To enhance the information exchange between bi-temporal image feature maps, we have designed a new Feature Pyramid Network module targeted at remote sensing change detection, named ChangeFPN. Additionally, to make full use of the multi-level feature maps in the decoding stage, we have developed a layer-by-layer feature upsampling module combined with Euclidean distance to improve feature fusion and reconstruction during the decoding stage. The EfficientCD has been experimentally validated on four remote sensing datasets: LEVIR-CD, SYSU-CD, CLCD, and WHUCD. The experimental results demonstrate that EfficientCD exhibits outstanding performance in change detection accuracy. The code and pretrained models will be released at https://github.com/dyzy41/mmrscd.

In recent years, the denoising diffusion model has achieved remarkable success in image segmentation modeling. With its powerful nonlinear modeling capabilities and superior generalization performance, denoising diffusion models have gradually been applied to medical image segmentation tasks, bringing new perspectives and methods to this field. However, existing methods overlook the uncertainty of segmentation boundaries and the fuzziness of regions, resulting in the instability and inaccuracy of the segmentation results. To solve this problem, a denoising diffusion fusion network based on fuzzy learning for 3D medical image segmentation (FDiff-Fusion) is proposed in this paper. By integrating the denoising diffusion model into the classical U-Net network, this model can effectively extract rich semantic information from input medical images, thus providing excellent pixel-level representation for medical image segmentation. ... Finally, to validate the effectiveness of FDiff-Fusion, we compare it with existing advanced segmentation networks on the BRATS 2020 brain tumor dataset and the BTCV abdominal multi-organ dataset. The results show that FDiff-Fusion significantly improves the Dice scores and HD95 distance on these two datasets, demonstrating its superiority in medical image segmentation tasks., Comment: This paper has been accepted by Information Fusion. Permission from Elsevier must be obtained for all other uses, in any current or future media. The final version is available at [doi:10.1016/J.INFFUS.2024.102540]

Uranium is considered as a very important nuclear energy material because of the huge amount of energy released. As the main products of spontaneous decay of uranium, helium is difficult to react with uranium for its chemical inertness. Therefore, bubbles will be formed inside uranium, which could greatly reduce the performance of uranium or cause the safety problems. Additionally, nuclear materials are usually operated in an environment of high-temperature and high-pressure, so it is necessary to figure out the exact state of helium inside uranium at extreme conditions. Here, we explored the structural stability of U-He system under high-pressure and high-temperature by using density functional theory calculations. Two metastable phases are found between 50 and 400 GPa: U4He with space group Fmmm and U6He with space group P-1. Both are metallic and adopt layered structures. Electron localization function calculation combined with charge density difference analysis indicate that there are covalent bonds between U and U atoms in both Fmmm-U4He and P-1-U6He. Compared with the elastic modulus of ${\alpha}$-U, the addition of helium has certain influence on the mechanical properties of uranium. Besides, first-principles molecular dynamics simulations were carried out to study the dynamical behavior of Fmmm-U4He and P-1-U6He at high-temperature. It is found that Fmmm-U4He and P-1-U6He undergo one-dimensional superionic phase transitions at 150 GPa. Our study revealed exotic structure of U-He compounds beyond the form of bubble under high-pressure and high-temperature, that might be relevant to the performance and safety issue of nuclear materials at extreme conditions., Comment: 8 pages, 4 figures, with Supplementary Information

Mn3TeO6 (MTO) has been experimentally found to adopt a P21/n structure under high pressure, which exhibits a significantly smaller band gap compared to the atmospheric R-3 phase. In this study, we systematically investigate the magnetism, structural phase transition and electronic properties of MTO under high pressure through first-principles calculations. Both R-3 and P21/n phases of MTO are antiferromagnetic at zero temperature. The R-3 phase transforms to the P21/n phase at 7.58 GPa, accompanied by a considerable volume collapse of about 6.47%. Employing the accurate method that combines DFT+U and G0W0, the calculated band gap of R-3 phase at zero pressure is very close to the experimental values, while that of the P21/n phase is significantly overestimated. The main reason for this difference is that the experimental study incorrectly used the Kubelka-Munk plot for the indirect band gap to obtain the band gap of the P21/n phase instead of the Kubelka-Munk plot for the direct band gap. Furthermore, our study reveals that the transition from the R-3 phase to the P21/n phase is accompanied by a slight reduction in the band gap., Comment: 17 pages, 11 figures

Gamma-ray bursts (GRBs) as the most energetic explosions in the modern universe have been studied over half a century, but the physics of the particle acceleration and radiation responsible for their observed spectral behaviors are still not well understood. Based on the comprehensive analysis of the pulse properties in both bright GRB~160625B and GRB~160509A, for the first time, we identify evidences of particle acceleration by relativistic magnetic reconnection from the evolutionary behavior of the two spectral breaks ($E_{\rm p}$ and $E_{\rm cut}$). Meanwhile, the adiabatic cooling process of the emitting particles in the magnetic reconnection regions produces a relation between the spectral index and the flux. We also discuss the physics behind spectral energy correlations. Finally, we argue that the identification of an anticorrelation between $E_{\rm cut}$ and $L_{\rm iso}$ may opens a new avenue for diagnostics of the physics of the particle acceleration and radiation in a variety of astrophysical sources., Comment: 17 pages, 8 figures. Accepted for publication in ApJ

We propose a novel method to identify the two-pole structure of the $\Lambda(1405)$. The two poles owe their origin to different quark flavor irreducible representations in the meson-baryon coupled-channel interactions, thus they should be individually manifested in reactions that provide good flavor eigenstate sources. Hadronic decays of charmonia into $\bar{\Lambda}\Sigma\pi$ and $\bar{\Lambda}(1520)\Sigma\pi$ are such reactions, and the flavor octet and singlet poles can be approximately singled out in these two decay modes. This SU(3) flavor filter works even considering the flavor symmetry breaking. With the huge charmonium data sets collected, it is therefore promising to solve the long-standing $\Lambda(1405)$ puzzle employing the proposed flavor filter., Comment: 6 pages, 4 figures

Continuous learning (CL) has emerged as one of the most popular deep learning paradigms deployed in modern cloud GPUs. Specifically, CL has the capability to continuously update the model parameters (through model retraining) and use the updated model (if available) to serve overtime arriving inference requests. It is generally beneficial to co-locate the retraining and inference together to enable timely model updates and avoid model transfer overheads. This brings the need for GPU sharing among retraining and inferences. Meanwhile, multiple CL workloads can share the modern GPUs in the cloud, leading to multi-tenancy execution. In this paper, we observe that prior GPU-sharing techniques are not optimized for multi-tenancy CL workloads. Specifically, they do not coherently consider the accuracy of the retraining model and the inference service level objective (SLO) attainment. Moreover, they cannot accommodate the overtime dynamics (e.g., inference arrival intensity) in CL execution. In this paper, we propose MIGRator, a novel GPU reconfiguration runtime that dynamically performs GPU reconfiguration for multi-tenancy CL workloads. MIGRator is based on the recent NVIDIA multi-instance GPU (MIG) to mitigate resource contention and formulates the reconfiguration optimization into Integer Linear Programming (ILP) to dynamically identify, reconfigure, and allocate the GPU instances. MIGRator leverages the "Goodput" metric in the ILP objective function to consider both inference SLO attainment and model accuracy in the reconfiguration exploration. We evaluate MIGRator using representative multi-tenancy CL workloads. The results show our approach outperforms the state-of-the-art GPU sharing techniques (i.e., Ekya, Astraea, and PARIS) by 17\%, 21\%, and 20\%, respectively.

The accurate diagnosis of pathological subtypes of lung cancer is of paramount importance for follow-up treatments and prognosis managements. Assessment methods utilizing deep learning technologies have introduced novel approaches for clinical diagnosis. However, the majority of existing models rely solely on single-modality image input, leading to limited diagnostic accuracy. To this end, we propose a novel deep learning network designed to accurately classify lung cancer subtype with multi-dimensional and multi-modality images, i.e., CT and pathological images. The strength of the proposed model lies in its ability to dynamically process both paired CT-pathological image sets as well as independent CT image sets, and consequently optimize the pathology-related feature extractions from CT images. This adaptive learning approach enhances the flexibility in processing multi-dimensional and multi-modality datasets and results in performance elevating in the model testing phase. We also develop a contrastive constraint module, which quantitatively maps the cross-modality associations through network training, and thereby helps to explore the "gold standard" pathological information from the corresponding CT scans. To evaluate the effectiveness, adaptability, and generalization ability of our model, we conducted extensive experiments on a large-scale multi-center dataset and compared our model with a series of state-of-the-art classification models. The experimental results demonstrated the superiority of our model for lung cancer subtype classification, showcasing significant improvements in accuracy metrics such as ACC, AUC, and F1-score.

On a compact Riemannian manifold $M,$ we show that the Riemannian distance function $d(x,y)$ can be explicitly reconstructed from suitable asymptotics of the expected signature of Brownian bridge from $x$ to $y$. In addition, by looking into the asymptotic expansion of the fourth level expected signature of the Brownian loop based at $x\in M$, one can explicitly reconstruct both intrinsic (Ricci curvature) and extrinsic (second fundamental form) curvature properties of $M$ at $x$. As independent interest, we also derive the intrinsic PDE for the expected Brownian signature dynamics on $M$ from the perspective of the Eells-Elworthy-Malliavin horizontal lifting.

Based on $6.1~\mathrm{fb}^{-1}$ of $e^+e^-$ annihilation data collected at center-of-mass energies from 4.600~GeV to 4.843~GeV with the BESIII detector at the BEPCII collider, a partial wave analysis of $\Lambda_c^+\to\Lambda\pi^+\eta$ is performed, and branching fractions and decay asymmetry parameters of intermediate processes are determined. The process $\Lambda_c^+\to\Lambda a_0(980)^+$ is observed for the first time, and evidence for the pentaquark candidate $\Sigma(1380)^+$ decaying into $\Lambda\pi^+$ is found with statistical significance larger than $3\sigma$. The branching fraction product $\mathcal{B}(\Lambda_{c}^{+} \to \Lambda a_0(980)^+) \; \mathcal{B}( a_0(980)^+ \to \pi^{+}\eta)$ is determined to be $(1.05 \pm 0.16_{\mathrm{stat}} \pm 0.05_{\mathrm{syst}} \pm 0.07_{\mathrm{ext}})\%$, which is larger than theoretical calculations by $1 - 2$ orders of magnitude. Here the third (external) systematic is from $\mathcal{B}(\Lambda_{c}^{+} \to \Lambda \pi^+ \eta)$. Finally, we precisely obtain the absolute branching fraction $\mathcal{B}(\Lambda_{c}^{+} \to \Lambda \pi^+ \eta) = (1.94 \pm 0.07_{\mathrm{stat}} \pm 0.11_{\mathrm{syst}})\%$., Comment: 16 pages, 8 figures

Inhomogeneous random matrices with a non-trivial variance profile determined by a symmetric stochastic matrix and with independent symmetrically sub-Gaussian entries up to Hermitian symmetry, include many prominent examples, such as remarkable sparse Wigner matrices and random band matrices in dimension d, and have been of great interest recently. The maximum of entry variances as a natural proxy of sparsity is both a key feature and a significant obstacle. In this paper, we study low-rank additive perturbations of such random matrices, and establish a sharp BBP phase transition for extreme eigenvalues at the level of law of large numbers. Under suitable conditions on the variance profile and the finite-rank perturbation, we also establish the fluctuations of spectral outliers that may be characterized by the general inhomogeneous random matrices. This reveals the strong non-universality phenomena, which may depend on eigenvectors, sparsity or geometric structure. Our proofs rely on ribbon graph expansions, upper bounds for diagram functions, large moment estimates and counting of typical diagrams., Comment: 66 pages, 8 figures

The denominator conjecture, proposed by Fomin and Zelevinsky, says that for a cluster algebra, the cluster monomials are uniquely determined by their denominator vectors with respect to an initial cluster. In this paper, for a cluster algebra from a marked surface with at least three boundary marked points, we establish this conjecture with respect to a given strong admissible tagged triangulation., Comment: 28 pages, comments welcome

Based on $10.64~\mathrm{fb}^{-1}$ of $e^+e^-$ collision data taken at center-of-mass energies between 4.237 and 4.699 GeV with the BESIII detector, we study the leptonic $D^+_s$ decays using the $e^+e^-\to D^{*+}_{s} D^{*-}_{s}$ process. The branching fractions of $D_s^+\to\ell^+\nu_{\ell}\,(\ell=\mu,\tau)$ are measured to be $\mathcal{B}(D_s^+\to\mu^+\nu_\mu)=(0.547\pm0.026_{\rm stat}\pm0.016_{\rm syst})\%$ and $\mathcal{B}(D_s^+\to\tau^+\nu_\tau)=(5.60\pm0.16_{\rm stat}\pm0.20_{\rm syst})\%$, respectively. The product of the decay constant and Cabibbo-Kobayashi-Maskawa matrix element $|V_{cs}|$ is determined to be $f_{D_s^+}|V_{cs}|=(246.5\pm5.9_{\rm stat}\pm3.6_{\rm syst}\pm0.5_{\rm input})_{\mu\nu}~\mathrm{MeV}$ and $f_{D_s^+}|V_{cs}|=(252.7\pm3.6_{\rm stat}\pm4.5_{\rm syst}\pm0.6_{\rm input}))_{\tau \nu}~\mathrm{MeV}$, respectively. Taking the value of $|V_{cs}|$ from a global fit in the Standard Model, we obtain ${f_{D^+_s}}=(252.8\pm6.0_{\rm stat}\pm3.7_{\rm syst}\pm0.6_{\rm input})_{\mu\nu}$ MeV and ${f_{D^+_s}}=(259.2\pm3.6_{\rm stat}\pm4.5_{\rm syst}\pm0.6_{\rm input})_{\tau \nu}$ MeV, respectively. Conversely, taking the value for $f_{D_s^+}$ from the latest lattice quantum chromodynamics calculation, we obtain $|V_{cs}| =(0.986\pm0.023_{\rm stat}\pm0.014_{\rm syst}\pm0.003_{\rm input})_{\mu\nu}$ and $|V_{cs}| = (1.011\pm0.014_{\rm stat}\pm0.018_{\rm syst}\pm0.003_{\rm input})_{\tau \nu}$, respectively., Comment: 27 pages, 13 figures

We propose an $\alpha$-separable graph Hamiltonian network ($\alpha$-SGHN) that reveals complex interaction patterns between particles in lattice systems. Utilizing trajectory data, $\alpha$-SGHN infers potential interactions without prior knowledge about particle coupling, overcoming the limitations of traditional graph neural networks that require predefined links. Furthermore, $\alpha$-SGHN preserves all conservation laws during trajectory prediction. Experimental results demonstrate that our model, incorporating structural information, outperforms baseline models based on conventional neural networks in predicting lattice systems. We anticipate that the results presented will be applicable beyond the specific onsite and inter-site interaction lattices studied, including the Frenkel-Kontorova model, the rotator lattice, and the Toda lattice., Comment: 17pages

Machine unlearning (MU) seeks to remove knowledge of specific data samples from trained models without the necessity for complete retraining, a task made challenging by the dual objectives of effective erasure of data and maintaining the overall performance of the model. Despite recent advances in this field, balancing between the dual objectives of unlearning remains challenging. From a fresh perspective of generalization, we introduce a novel Learning-to-Unlearn (LTU) framework, which adopts a meta-learning approach to optimize the unlearning process to improve forgetting and remembering in a unified manner. LTU includes a meta-optimization scheme that facilitates models to effectively preserve generalizable knowledge with only a small subset of the remaining set, while thoroughly forgetting the specific data samples. We also introduce a Gradient Harmonization strategy to align the optimization trajectories for remembering and forgetting via mitigating gradient conflicts, thus ensuring efficient and effective model updates. Our approach demonstrates improved efficiency and efficacy for MU, offering a promising solution to the challenges of data rights and model reusability., Comment: Accepted by ECCV 2024

Flat bands in magic-angle twisted bilayer graphene serve as the arena where exotic correlation physics unfolds. Previous studies have shown that phonons, through mediating an effective electron-electron interaction, can play a crucial role in determining various electronic phases. In this study, we project the full electron-phonon coupling vertex, derived from microscopic tight-binding lattice calculations, onto the basis of the topological heavy fermion model [Song and Bernevig, PRL 129, 047601 (2022)], and identify the significance of each phonon mode. With phonon fields integrated out, an on-site anti-Hund's interaction $\hat{H}_{\rm A}$ on the moir\'e-scale local $f$-orbitals is obtained, with strengths 1 to 4 meV. We solve the phonon-induced multiplet splittings, and then elaborate on phonon-favored symmetry-breaking orders at even-integer fillings. Through systematic self-consistent Hartree-Fock calculations, we uncover a tight competition between $\Gamma$-phonon-favored orbital orders, $K$-phonon-favored inter-valley coherent orders, and the kinetic and Coulomb-favored orders. A Hund's interaction $\hat{H}_{\rm H}$ with strengths 1 to 3 meV, which originates from the carbon atom Hubbard, and partly counteracts the effect of $\hat{H}_{\rm A}$, is also discussed. In the end, we explore the possibility of finding an exotic Dirac semi-metal at the charge-neutrality point which is formed solely by $c$-electrons, while $f$-impurities exhibit a symmetric Mott gap by forming non-degenerate singlets under $\hat{H}_{\rm A,H}$. Experimental features that distinguish such a state are discussed.

Controlled fusion energy is deemed pivotal for the advancement of human civilization. In this study, we introduce $\textbf{Fusion-LLM}$, a novel integration of Large Language Models (LLMs) with classical reservoir computing paradigms tailored to address challenges in Inertial Confinement Fusion ($\texttt{ICF}$). Our approach offers several key contributions: Firstly, we propose the $\textit{LLM-anchored Reservoir}$, augmented with a fusion-specific prompt, enabling accurate forecasting of hot electron dynamics during implosion. Secondly, we develop $\textit{Signal-Digesting Channels}$ to temporally and spatially describe the laser intensity across time, capturing the unique characteristics of $\texttt{ICF}$ inputs. Lastly, we design the $\textit{Confidence Scanner}$ to quantify the confidence level in forecasting, providing valuable insights for domain experts to design the $\texttt{ICF}$ process. Extensive experiments demonstrate the superior performance of our method, achieving 1.90 CAE, 0.14 $\texttt{top-1}$ MAE, and 0.11 $\texttt{top-5}$ MAE in predicting Hard X-ray ($\texttt{HXR}$) energies of $\texttt{ICF}$ tasks, which presents state-of-the-art comparisons against concurrent best systems. Additionally, we present $\textbf{Fusion4AI}$, the first $\texttt{ICF}$ benchmark based on physical experiments, aimed at fostering novel ideas in plasma physics research and enhancing the utility of LLMs in scientific exploration. Overall, our work strives to forge an innovative synergy between AI and plasma science for advancing fusion energy.

The PandaX-4T liquid xenon detector at the China Jinping Underground Laboratory is used to measure the solar $^8$B neutrino flux by detecting neutrinos through coherent scattering with xenon nuclei. Data samples requiring the coincidence of scintillation and ionization signals (paired), as well as unpaired ionization-only signals (US2), are selected with energy threshold of approximately 1.1 keV (0.33 keV) nuclear recoil energy. Combining the commissioning run and the first science run of PandaX-4T, a total exposure of 1.20 and 1.04 tonne$\cdot$year are collected for the paired and US2, respectively. After unblinding, 3 and 332 events are observed with an expectation of 2.8$\pm$0.5 and 251$\pm$32 background events, for the paired and US2 data, respectively. A combined analysis yields a best-fit $^8$B neutrino signal of 3.5 (75) events from the paired (US2) data sample, with $\sim$37\% uncertainty, and the background-only hypothesis is disfavored at 2.64$\sigma$ significance. This gives a solar $^8$B neutrino flux of ($8.4\pm3.1$)$\times$10$^6$ cm$^{-2}$s$^{-1}$, consistent with the standard solar model prediction. It is also the first indication of solar $^8$B neutrino ``fog'' in a dark matter direct detection experiment., Comment: Accepted by Physical Review Letters

Rotating Radio Transients (RRATs) are neutron stars emitting sporadic radio pulses. The unique emission of RRATs has been proposed to resemble those of known pulsar types, such as extreme nulling pulsars or pulsars with giant pulses. However, the presence of additional radiation beyond these sporadic pulses remains unclear. Through high-sensitivity observations and extended tracking, we detected the sequential weak emissions in two RRATs with relatively high surface magnetic fields (Bs > 10^13 G): J1846-0257 and J1854+0306. These emissions show peak flux densities of 0.15 and 0.41 mJy, up to 687 and 512 times weaker than our detected RRAT single pulses, respectively. The weak emissions contribute small fractions (~ 16% and 5%) to the total radio pulse energy releases, contrasting significantly with giant-pulse pulsars where normal pulses dominate. Polarization analysis of J1854+0306 suggests that its sporadic RRAT pulses may originate from intermittent enhanced sparking processes due to magnetospheric evolution. Our findings indicate that some RRATs may represent a novel class of pulsars, distinct from any previously known subclass. Further observations of sources with similar rotational properties using high-sensitivity instruments could validate the generality of these hidden emissions., Comment: 10 pages, 1 table, 6 figures

Due to flexibility and low-cost, unmanned aerial vehicles (UAVs) are increasingly crucial for enhancing coverage and functionality of wireless networks. However, incorporating UAVs into next-generation wireless communication systems poses significant challenges, particularly in sustaining high-rate and long-range secure communications against eavesdropping attacks. In this work, we consider a UAV swarm-enabled secure surveillance network system, where a UAV swarm forms a virtual antenna array to transmit sensitive surveillance data to a remote base station (RBS) via collaborative beamforming (CB) so as to resist mobile eavesdroppers. Specifically, we formulate an aerial secure communication and energy efficiency multi-objective optimization problem (ASCEE-MOP) to maximize the secrecy rate of the system and to minimize the flight energy consumption of the UAV swarm. To address the non-convex, NP-hard and dynamic ASCEE-MOP, we propose a generative diffusion model-enabled twin delayed deep deterministic policy gradient (GDMTD3) method. Specifically, GDMTD3 leverages an innovative application of diffusion models to determine optimal excitation current weights and position decisions of UAVs. The diffusion models can better capture the complex dynamics and the trade-off of the ASCEE-MOP, thereby yielding promising solutions. Simulation results highlight the superior performance of the proposed approach compared with traditional deployment strategies and some other deep reinforcement learning (DRL) benchmarks. Moreover, performance analysis under various parameter settings of GDMTD3 and different numbers of UAVs verifies the robustness of the proposed approach., Comment: This paper has been submitted to IEEE Transactions on Mobile Computing

Materials with topological flat bands can serve as a promising platform to investigate strongly interacting phenomena. However, experimental realization of ideal flat bands is mostly limited to artificial lattices or moir\'e systems. Here we report a general way to construct one-dimensional (1D) flat bands in phosphorene nanoribbons (PNRs) with pentagonal nature: penta-hexa-PNRs and penta-dodeca-PNRs, wherein the corresponding flat bands are directly verified by using angle-resolved photoemission spectroscopy. We confirm that the observed 1D flat bands originate from the electronic 1D sawtooth and Lieb lattices, respectively, as revealed by the combination of bond-resolved scanning tunneling microscopy, scanning tunneling spectroscopy, tight-binding models, and first-principles calculations. Our study demonstrates a general way to construct 1D flat bands in 1D solid materials system, which provides a robust platform to explore strongly interacting phases of matter., Comment: 13 pages, 4 figures

The $e^+e^-\rightarrow D_s^+D_{s1}(2536)^-$ and $e^+e^-\rightarrow D_s^+D^*_{s2}(2573)^-$ processes are studied using data samples collected with the BESIII detector at center-of-mass energies from 4.530 to 4.946~GeV. The absolute branching fractions of $D_{s1}(2536)^- \rightarrow \bar{D}^{*0}K^-$ and $D_{s2}^*(2573)^- \rightarrow \bar{D}^0K^-$ are measured for the first time to be $(35.9\pm 4.8\pm 3.5)\%$ and $(37.4\pm 3.1\pm 4.6)\%$, respectively. The measurements are in tension with predictions based on the assumption that the $D_{s1}(2536)$ and $D_{s2}^*(2573)$ are dominated by a bare $c\bar{s}$ component. The $e^+e^-\rightarrow D_s^+D_{s1}(2536)^-$ and $e^+e^-\rightarrow D_s^+D^*_{s2}(2573)^-$ cross sections are measured, and a resonant structure at around 4.6~GeV with a width of 50~MeV is observed for the first time with a statistical significance of $15\sigma$ in the $e^+e^-\rightarrow D_s^+D^*_{s2}(2573)^-$ process. It could be the $Y(4626)$ found by the Belle collaboration in the $D_s^+D_{s1}(2536)^{-}$ final state, since they have similar masses and widths. There is also evidence for a structure at around 4.75~GeV in both processes.

We consider the challenging problem of estimating causal effects from purely observational data in the bi-directional Mendelian randomization (MR), where some invalid instruments, as well as unmeasured confounding, usually exist. To address this problem, most existing methods attempt to find proper valid instrumental variables (IVs) for the target causal effect by expert knowledge or by assuming that the causal model is a one-directional MR model. As such, in this paper, we first theoretically investigate the identification of the bi-directional MR from observational data. In particular, we provide necessary and sufficient conditions under which valid IV sets are correctly identified such that the bi-directional MR model is identifiable, including the causal directions of a pair of phenotypes (i.e., the treatment and outcome). Moreover, based on the identification theory, we develop a cluster fusion-like method to discover valid IV sets and estimate the causal effects of interest. We theoretically demonstrate the correctness of the proposed algorithm. Experimental results show the effectiveness of our method for estimating causal effects in bi-directional MR., Comment: 27 pages, 6 tables, 7 figures

Halide perovskites have emerged as promising photonic materials for fundamental physics studies and technological applications. Their potential for nonlinear optics has also drawn great interest recently; yet, to date, continuous-wave (CW) nonlinearities have remained elusive. Here we demonstrate CW nonlinear phenomena in a CsPbBr$_3$ perovskite cavity. We first demonstrate optical bistability -- the hallmark of single-mode coherent nonlinear optics. Next we exploit the interplay of nonlinearity and birefringence to demonstrate nonlinear control over the polarization of light. Finally, by measuring the optical hysteresis of our cavity as a function of temperature, we find a dramatic enhancement of the nonlinearity around 65 K. This enhancement is indicative of a phase transition in CsPbBr$_3$. Our results position CsPbBr$_3$ cavities as an exceptional platform for nonlinear optics, offering strong CW nonlinearity and birefringence which are furthermore tunable. In addition, our approach to uncover a phase transition of matter via optical hysteresis measurements is promising for exploring strongly correlated states of light-matter systems., Comment: Main: pages 1-11, including 4 figures. Supplemental: pages 12-17, including 10 supplemental figures

The application of data-intensive automatic speech recognition (ASR) technologies to dysarthric and elderly adult speech is confronted by their mismatch against healthy and nonaged voices, data scarcity and large speaker-level variability. To this end, this paper proposes two novel data-efficient methods to learn homogeneous dysarthric and elderly speaker-level features for rapid, on-the-fly test-time adaptation of DNN/TDNN and Conformer ASR models. These include: 1) speaker-level variance-regularized spectral basis embedding (VR-SBE) features that exploit a special regularization term to enforce homogeneity of speaker features in adaptation; and 2) feature-based learning hidden unit contributions (f-LHUC) transforms that are conditioned on VR-SBE features. Experiments are conducted on four tasks across two languages: the English UASpeech and TORGO dysarthric speech datasets, the English DementiaBank Pitt and Cantonese JCCOCC MoCA elderly speech corpora. The proposed on-the-fly speaker adaptation techniques consistently outperform baseline iVector and xVector adaptation by statistically significant word or character error rate reductions up to 5.32% absolute (18.57% relative) and batch-mode LHUC speaker adaptation by 2.24% absolute (9.20% relative), while operating with real-time factors speeding up to 33.6 times against xVectors during adaptation. The efficacy of the proposed adaptation techniques is demonstrated in a comparison against current ASR technologies including SSL pre-trained systems on UASpeech, where our best system produces a state-of-the-art WER of 23.33%. Analyses show VR-SBE features and f-LHUC transforms are insensitive to speaker-level data quantity in testtime adaptation. T-SNE visualization reveals they have stronger speaker-level homogeneity than baseline iVectors, xVectors and batch-mode LHUC transforms., Comment: In submission to IEEE/ACM Transactions on Audio, Speech, and Language Processing

Aerial manipulation has gained interest in completing high-altitude tasks that are challenging for human workers, such as contact inspection and defect detection, etc. Previous research has focused on maintaining static contact points or forces. This letter addresses a more general and dynamic task: simultaneously tracking time-varying contact force in the surface normal direction and motion trajectories on tangential surfaces. We propose a pipeline that includes a contact-aware trajectory planner to generate dynamically feasible trajectories, and a hybrid motion-force controller to track such trajectories. We demonstrate the approach in an aerial calligraphy task using a novel sponge pen design as the end-effector, whose stroke width is proportional to the contact force. Additionally, we develop a touchscreen interface for flexible user input. Experiments show our method can effectively draw diverse letters, achieving an IoU of 0.59 and an end-effector position (force) tracking RMSE of 2.9 cm (0.7 N). Website: https://xiaofeng-guo.github.io/flying-calligrapher/, Comment: 8 pages, 9 figures, 1 table

Adiabatic mode evolution waveguides (AMEWs) are widely utilized in integrated photonics, including tapered waveguides, edge couplers, mode converters, splitters, etc. An analytical theory and a novel AMEW design algorithm are developed to create shortcuts to adiabaticity (STA). This new algorithm is effective in shortening the total length of the AMEW while maintaining the desired wavelength range. Moreover, this analytical algorithm requires much fewer computing resources than traditional numerical algorithms. With the new algorithm, we demonstrate a broadband and highly efficient polarization splitter-rotator (PSR) on a lithium-niobate-on-insulator (LNOI) platform with an LN thickness of 500 nm. According to our simulation, the length of the PSR is shortened by 3.5 times compared to the linear design. The fabricated PSR, with a total length of 2 mm, exhibits an insertion loss (IL) of 0.8 dB and a polarization extinction ratio (ER) of 12.2 dB over a wavelength range exceeding 76 nm., Comment: 16 pages, 6 figures, 2 tables

DLRM is a state-of-the-art recommendation system model that has gained widespread adoption across various industry applications. The large size of DLRM models, however, necessitates the use of multiple devices/GPUs for efficient training. A significant bottleneck in this process is the time-consuming all-to-all communication required to collect embedding data from all devices. To mitigate this, we introduce a method that employs error-bounded lossy compression to reduce the communication data size and accelerate DLRM training. We develop a novel error-bounded lossy compression algorithm, informed by an in-depth analysis of embedding data features, to achieve high compression ratios. Moreover, we introduce a dual-level adaptive strategy for error-bound adjustment, spanning both table-wise and iteration-wise aspects, to balance the compression benefits with the potential impacts on accuracy. We further optimize our compressor for PyTorch tensors on GPUs, minimizing compression overhead. Evaluation shows that our method achieves a 1.38$\times$ training speedup with a minimal accuracy impact., Comment: camera-ready version for SC '24

This work proposes a retrieve-and-transfer framework for zero-shot robotic manipulation, dubbed RAM, featuring generalizability across various objects, environments, and embodiments. Unlike existing approaches that learn manipulation from expensive in-domain demonstrations, RAM capitalizes on a retrieval-based affordance transfer paradigm to acquire versatile manipulation capabilities from abundant out-of-domain data. First, RAM extracts unified affordance at scale from diverse sources of demonstrations including robotic data, human-object interaction (HOI) data, and custom data to construct a comprehensive affordance memory. Then given a language instruction, RAM hierarchically retrieves the most similar demonstration from the affordance memory and transfers such out-of-domain 2D affordance to in-domain 3D executable affordance in a zero-shot and embodiment-agnostic manner. Extensive simulation and real-world evaluations demonstrate that our RAM consistently outperforms existing works in diverse daily tasks. Additionally, RAM shows significant potential for downstream applications such as automatic and efficient data collection, one-shot visual imitation, and LLM/VLM-integrated long-horizon manipulation. For more details, please check our website at https://yxkryptonite.github.io/RAM/.

Self-supervised learning (SSL) based speech foundation models have been applied to a wide range of ASR tasks. However, their application to dysarthric and elderly speech via data-intensive parameter fine-tuning is confronted by in-domain data scarcity and mismatch. To this end, this paper explores a series of approaches to integrate domain fine-tuned SSL pre-trained models and their features into TDNN and Conformer ASR systems for dysarthric and elderly speech recognition. These include: a) input feature fusion between standard acoustic frontends and domain fine-tuned SSL speech representations; b) frame-level joint decoding between TDNN systems separately trained using standard acoustic features alone and those with additional domain fine-tuned SSL features; and c) multi-pass decoding involving the TDNN/Conformer system outputs to be rescored using domain fine-tuned pre-trained ASR models. In addition, fine-tuned SSL speech features are used in acoustic-to-articulatory (A2A) inversion to construct multi-modal ASR systems. Experiments are conducted on four tasks: the English UASpeech and TORGO dysarthric speech corpora; and the English DementiaBank Pitt and Cantonese JCCOCC MoCA elderly speech datasets. The TDNN systems constructed by integrating domain-adapted HuBERT, wav2vec2-conformer or multi-lingual XLSR models and their features consistently outperform the standalone fine-tuned SSL pre-trained models. These systems produced statistically significant WER or CER reductions of 6.53%, 1.90%, 2.04% and 7.97% absolute (24.10%, 23.84%, 10.14% and 31.39% relative) on the four tasks respectively. Consistent improvements in Alzheimer's Disease detection accuracy are also obtained using the DementiaBank Pitt elderly speech recognition outputs., Comment: IEEE/ACM Transactions on Audio, Speech, and Language Processing

A high precision measurement of the branching fraction of the decay $J/\psi \to p \bar{p} \eta$ is performed using $(10 087 \pm 44) \times 10^6$ $J/\psi$ events recorded by the {BESIII} detector at the {BEPCII} storage ring. The branching fractions of the two decays $J/\psi \to p \bar{p} \eta(\eta \to \gamma\gamma)$ and $J/\psi \to p \bar{p} \eta(\eta \to \pi^+ \pi^- \pi^0)$ are measured individually to be $\mathcal{B}(J/\psi \to p \bar{p} \eta(\eta \to \gamma\gamma)) = (1.480 \pm 0.001 \pm 0.024)\times\,10^{-3}$ and $\mathcal{B}(J/\psi \to p \bar{p} \eta(\eta \to \pi^+ \pi^- \pi^0)) = (1.557 \pm 0.003 \pm 0.038)\times\,10^{-3}$, where the first uncertainties are statistical and the second systematic. Both results are compatible within their uncorrelated systematic uncertainties. The combined result is $\mathcal{B}(J/\psi \to p \bar{p} \eta)=(1.495 \pm 0.001 \pm 0.023)\times\,10^{-3}$ where the first uncertainty is the combined statistical uncertainty and the second one the combined systematic uncertainty of both analyses, incorporating correlations between them. In addition, the $p \bar{p}$ threshold region is investigated for a potential threshold enhancement, and no evidence for one is observed.

The knob tuning aims to optimize database performance by searching for the most effective knob configuration under a certain workload. Existing works suffer two significant problems. On the one hand, there exist multiple similar even useless evaluations of knob tuning even with the diverse searching methods because of the different sensitivities of knobs on a certain workload. On the other hand, the single evaluation of knob configurations may bring overestimation or underestimation because of the query uncertainty performance. To solve the above problems, we propose a decoupled query uncertainty-aware knob classifier, called KnobCF, to enhance the knob tuning. Our method has three significant contributions: (1) We propose a novel concept of the uncertainty-aware knob configuration estimation to enhance the knob tuning process. (2) We provide an effective few-shot uncertainty knob estimator without extra time consumption in training data collection, which has a high time efficiency in practical tuning tasks. (3) Our method provides a general framework that could be easily deployed in any knob tuning task because we make no changes to the knob tuners and the database management system. Our experiments on four open-source benchmarks demonstrate that our method effectively reduces useless evaluations and improves the tuning results. Especially in TPCC, our method achieves competitive tuning results with only 60% to 70% time consumption compared to the full workload evaluations.

The increasing complexity of modern very-large-scale integration (VLSI) design highlights the significance of Electronic Design Automation (EDA) technologies. Chip placement is a critical step in the EDA workflow, which positions chip modules on the canvas with the goal of optimizing performance, power, and area (PPA) metrics of final chip designs. Recent advances have demonstrated the great potential of AI-based algorithms in enhancing chip placement. However, due to the lengthy workflow of chip design, the evaluations of these algorithms often focus on intermediate surrogate metrics, which are easy to compute but frequently reveal a substantial misalignment with the end-to-end performance (i.e., the final design PPA). To address this challenge, we introduce ChiPBench, which can effectively facilitate research in chip placement within the AI community. ChiPBench is a comprehensive benchmark specifically designed to evaluate the effectiveness of existing AI-based chip placement algorithms in improving final design PPA metrics. Specifically, we have gathered 20 circuits from various domains (e.g., CPU, GPU, and microcontrollers). These designs are compiled by executing the workflow from the verilog source code, which preserves necessary physical implementation kits, enabling evaluations for the placement algorithms on their impacts on the final design PPA. We executed six state-of-the-art AI-based chip placement algorithms on these designs and plugged the results of each single-point algorithm into the physical implementation workflow to obtain the final PPA results. Experimental results show that even if intermediate metric of a single-point algorithm is dominant, while the final PPA results are unsatisfactory. We believe that our benchmark will serve as an effective evaluation framework to bridge the gap between academia and industry., Comment: A comprehensive benchmark for AI-based chip placement algorithms using end-to-end performance metrics

Machine Learning Force Fields (MLFFs) are of great importance for chemistry, physics, materials science, and many other related fields. The Clebsch-Gordan Transform (CG transform) effectively encodes many-body interactions and is thus an important building block for many models of MLFFs. However, the permutation-equivariance requirement of MLFFs limits the design space of CG transform, that is, intensive CG transform has to be conducted for each neighboring edge and the operations should be performed in the same manner for all edges. This constraint results in reduced expressiveness of the model while simultaneously increasing computational demands. To overcome this challenge, we first implement the CG transform layer on the permutation-invariant abstract edges generated from real edge information. We show that this approach allows complete freedom in the design of the layer without compromising the crucial symmetry. Developing on this free design space, we further propose group CG transform with sparse path, abstract edges shuffling, and attention enhancer to form a powerful and efficient CG transform layer. Our method, known as FreeCG, achieves state-of-the-art (SOTA) results in force prediction for MD17, rMD17, MD22, and is well extended to property prediction in QM9 datasets with several improvements greater than 15% and the maximum beyond 20%. The extensive real-world applications showcase high practicality. FreeCG introduces a novel paradigm for carrying out efficient and expressive CG transform in future geometric neural network designs. To demonstrate this, the recent SOTA, QuinNet, is also enhanced under our paradigm. Code will be publicly available., Comment: 25 pages, 8 tables, 11 figures

Applying deep neural networks to 3D point cloud processing has attracted increasing attention due to its advanced performance in many areas, such as AR/VR, autonomous driving, and robotics. However, as neural network models and 3D point clouds expand in size, it becomes a crucial challenge to reduce the computational and memory overhead to meet latency and energy constraints in real-world applications. Although existing approaches have proposed to reduce both computational cost and memory footprint, most of them only address the spatial redundancy in inputs, i.e. removing the redundancy of background points in 3D data. In this paper, we propose a novel post-training weight pruning scheme for 3D object detection that is (1) orthogonal to all existing point cloud sparsifying methods, which determines redundant parameters in the pretrained model that lead to minimal distortion in both locality and confidence (detection distortion); and (2) a universal plug-and-play pruning framework that works with arbitrary 3D detection model. This framework aims to minimize detection distortion of network output to maximally maintain detection precision, by identifying layer-wise sparsity based on second-order Taylor approximation of the distortion. Albeit utilizing second-order information, we introduced a lightweight scheme to efficiently acquire Hessian information, and subsequently perform dynamic programming to solve the layer-wise sparsity. Extensive experiments on KITTI, Nuscenes and ONCE datasets demonstrate that our approach is able to maintain and even boost the detection precision on pruned model under noticeable computation reduction (FLOPs). Noticeably, we achieve over 3.89x, 3.72x FLOPs reduction on CenterPoint and PVRCNN model, respectively, without mAP decrease, significantly improving the state-of-the-art.

Vision transformers have emerged as a promising alternative to convolutional neural networks for various image analysis tasks, offering comparable or superior performance. However, one significant drawback of ViTs is their resource-intensive nature, leading to increased memory footprint, computation complexity, and power consumption. To democratize this high-performance technology and make it more environmentally friendly, it is essential to compress ViT models, reducing their resource requirements while maintaining high performance. In this paper, we introduce a new block-structured pruning to address the resource-intensive issue for ViTs, offering a balanced trade-off between accuracy and hardware acceleration. Unlike unstructured pruning or channel-wise structured pruning, block pruning leverages the block-wise structure of linear layers, resulting in more efficient matrix multiplications. To optimize this pruning scheme, our paper proposes a novel hardware-aware learning objective that simultaneously maximizes speedup and minimizes power consumption during inference, tailored to the block sparsity structure. This objective eliminates the need for empirical look-up tables and focuses solely on reducing parametrized layer connections. Moreover, our paper provides a lightweight algorithm to achieve post-training pruning for ViTs, utilizing second-order Taylor approximation and empirical optimization to solve the proposed hardware-aware objective. Extensive experiments on ImageNet are conducted across various ViT architectures, including DeiT-B and DeiT-S, demonstrating competitive performance with other pruning methods and achieving a remarkable balance between accuracy preservation and power savings. Especially, we achieve up to 3.93x and 1.79x speedups on dedicated hardware and GPUs respectively for DeiT-B, and also observe an inference power reduction by 1.4x on real-world GPUs.

In this work, a phase-field model is developed for the dendritic growth with gas bubbles in the solidification of binary alloys. In this model, a total free energy for the complex gas-liquid-dendrite system is proposed through considering the interactions of gas bubbles, liquid melt and solid dendrites, and it can reduce to the energy for gas-liquid flows in the region far from the solid phase, while degenerate to the energy for thermosolutal dendritic growth when the gas bubble disappears. The governing equations are usually obtained by minimizing the total free energy, but here some modifications are made to improve the capacity of the conservative phase-field equation for gas bubbles and convection-diffusion equation for solute transfer. Additionally, through the asymptotic analysis of the thin-interface limit, the present general phase-field model for alloy solidification can match the corresponding free boundary problem, and it is identical to the commonly used models under a specific choice of model parameters. Furthermore, to describe the fluid flow, the incompressible Navier-Stokes equations are adopted in the entire domain including gas, liquid, and solid regions, where the fluid-structure interaction is considered by a simple diffuse-interface method. To test the present phase-field model, the lattice Boltzmann method is used to study several problems of gas-liquid flows, dendritic growth as well as the solidification in presence of gas bubbles, and a good performance of the present model for such complex problems is observed., Comment: 29 pages, 23 figures

Training latency is critical for the success of numerous intrigued applications ignited by federated learning (FL) over heterogeneous mobile devices. By revolutionarily overlapping local gradient transmission with continuous local computing, FL can remarkably reduce its training latency over homogeneous clients, yet encounter severe model staleness, model drifts, memory cost and straggler issues in heterogeneous environments. To unleash the full potential of overlapping, we propose, FedEx, a novel \underline{fed}erated learning approach to \underline{ex}pedite FL training over mobile devices under data, computing and wireless heterogeneity. FedEx redefines the overlapping procedure with staleness ceilings to constrain memory consumption and make overlapping compatible with participation selection (PS) designs. Then, FedEx characterizes the PS utility function by considering the latency reduced by overlapping, and provides a holistic PS solution to address the straggler issue. FedEx also introduces a simple but effective metric to trigger overlapping, in order to avoid model drifts. Experimental results show that compared with its peer designs, FedEx demonstrates substantial reductions in FL training latency over heterogeneous mobile devices with limited memory cost., Comment: 21 pages, 10 figures, Submitted to Sensys2024

This paper addresses the problem of modeling and estimating dynamic multi-valued mappings. While most mathematical models provide a unique solution for a given input, real-world applications often lack deterministic solutions. In such scenarios, estimating dynamic multi-valued mappings is necessary to suggest different reasonable solutions for each input. This paper introduces a deep neural network framework incorporating a generative network and a classification component. The objective is to model the dynamic multi-valued mapping between the input and output by providing a reliable uncertainty measurement. Generating multiple solutions for a given input involves utilizing a discrete codebook comprising finite variables. These variables are fed into a generative network along with the input, producing various output possibilities. The discreteness of the codebook enables efficient estimation of the output's conditional probability distribution for any given input using a classifier. By jointly optimizing the discrete codebook and its uncertainty estimation during training using a specially designed loss function, a highly accurate approximation is achieved. The effectiveness of our proposed framework is demonstrated through its application to various imaging problems, using both synthetic and real imaging data. Experimental results show that our framework accurately estimates the dynamic multi-valued mapping with uncertainty estimation.