Search

Stance detection is critical for understanding the underlying position or attitude expressed toward a topic. Large language models (LLMs) have demonstrated significant advancements across various natural language processing tasks including stance detection, however, their performance in stance detection is limited by biases and spurious correlations inherent due to their data-driven nature. Our statistical experiment reveals that LLMs are prone to generate biased stances due to sentiment-stance spurious correlations and preference towards certain individuals and topics. Furthermore, the results demonstrate a strong negative correlation between stance bias and stance detection performance, underscoring the importance of mitigating bias to enhance the utility of LLMs in stance detection. Therefore, in this paper, we propose a Counterfactual Augmented Calibration Network (FACTUAL), which a novel calibration network is devised to calibrate potential bias in the stance prediction of LLMs. Further, to address the challenge of effectively learning bias representations and the difficulty in the generalizability of debiasing, we construct counterfactual augmented data. This approach enhances the calibration network, facilitating the debiasing and out-of-domain generalization. Experimental results on in-target and zero-shot stance detection tasks show that the proposed FACTUAL can effectively mitigate biases of LLMs, achieving state-of-the-art results.

Two-dimensional (2D) crystals proved revolutionary soon after graphene was discovered in 2004. However, 2D amorphous materials only became accessible in 2020 and remain largely unexplored. In particular, the thermophysical properties of amorphous materials are of great interest upon transition from 3D to 2D. Here, we probe thermal transport in 2D amorphous carbon. A cross-plane thermal conductivity ($\kappa$) down to 0.079 $\rm{Wm}^{-1}K^{-1}$ is measured for van der Waals stacked multilayers at room temperature, which is among the lowest reported to date. Meanwhile, an unexpectedly high in-plane $\kappa$ is obtained for freestanding monolayers which is a few times larger than what is predicted by conventional wisdom for 3D amorphous carbon with similar $\rm{sp}^{2}$ fraction. Our molecular dynamics simulations reveal the role of disorder and highlight the impact of dimensionality. Amorphous materials at the 2D limit open up new avenues for understanding and manipulating heat at the atomic scale.

Most of the existing quantum neural network models, such as variational quantum circuits (VQCs), are limited in their ability to explore the non-linear relationships in input data. This gradually becomes the main obstacle for it to tackle realistic applications, such as natural language processing, medical image processing, and wireless communications. Recently, there have emerged research efforts that enable VQCs to perform non-linear operations. However, it is still unclear on the approximability of a given VQC (i.e., the order of non-linearity that can be handled by a specified design). In response to this issue, we developed an automated tool designed to benchmark the approximation of a given VQC. The proposed tool will generate a set of synthetic datasets with different orders of non-linearity and train the given VQC on these datasets to estimate their approximability. Our experiments benchmark VQCs with different designs, where we know their theoretic approximability. We then show that the proposed tool can precisely estimate the approximability, which is consistent with the theoretic value, indicating that the proposed tool can be used for benchmarking the approximability of a given quantum circuit for learning tasks.

We define $\Psi$-autoreducible sets given an autoreduction procedure $\Psi$. Then, we show that for any $\Psi$, a measurable class of $\Psi$-autoreducible sets has measure zero. Using this, we show that classes of cototal, uniformly introenumerable, introenumerable, and hyper-cototal enumeration degrees all have measure zero. By analyzing the arithmetical complexity of the classes of cototal sets and cototal enumeration degrees, we show that weakly 2-random sets cannot be cototal and weakly 3-random sets cannot be of cototal enumeration degree. Then, we see that this result is optimal by showing that there exists a 1-random cototal set and a 2-random set of cototal enumeration degree. For uniformly introenumerable degrees and introenumerable degrees, we utilize $\Psi$-autoreducibility again to show the optimal result that no weakly 3-random sets can have introenumerable enumeration degree. We also show that no 1-random set can be introenumerable.

The rapid integration of renewable energy resources presents formidable challenges in managing power grids. While advanced computing and machine learning techniques offer some solutions for accelerating grid modeling and simulation, there remain complex problems that classical computers cannot effectively address. Quantum computing, a promising technology, has the potential to fundamentally transform how we manage power systems, especially in scenarios with a higher proportion of renewable energy sources. One critical aspect is solving large-scale linear systems of equations, crucial for power system applications like power flow analysis, for which the Harrow-Hassidim-Lloyd (HHL) algorithm is a well-known quantum solution. However, HHL quantum circuits often exhibit excessive depth, making them impractical for current Noisy-Intermediate-Scale-Quantum (NISQ) devices. In this paper, we introduce a versatile framework, powered by NWQSim, that bridges the gap between power system applications and quantum linear solvers available in Qiskit. This framework empowers researchers to efficiently explore power system applications using quantum linear solvers. Through innovative gate fusion strategies, reduced circuit depth, and GPU acceleration, our simulator significantly enhances resource efficiency. Power flow case studies have demonstrated up to a eight-fold speedup compared to Qiskit Aer, all while maintaining comparable levels of accuracy., Comment: 5 pages, 5 figures

Across a broad range of qubits, a pervasive trade-off becomes obvious: increased coherence seems to be only possible at the cost of qubit speed. This is consistent with the notion that protecting a qubit from its noisy surroundings also limits the control over it. Indeed, from ions to atoms, to superconductors and spins, the leading qubits share a similar Q-factor - the product of speed and coherence time - even though the speed and coherence of various qubits can differ by up to 8 orders of magnitude. This is the qubit speed-coherence dilemma: qubits are either coherent but slow or fast but short-lived. Here, we demonstrate a qubit for which we can triple the speed while simultaneously quadrupling the Hahn-echo coherence time when tuning a local electric field. In this way, the qubit speed and coherence scale together without compromise on either quantity, boosting the Q-factor by over an order of magnitude. Our qubit is a hole spin in a Ge/Si core/shell nanowire providing strong 1D confinement, resulting in the direct Rashba spin-orbit interaction. Due to Heavy-hole light-hole mixing a maximum of the spin-orbit strength is reached at finite electrical field. At the local maximum, charge fluctuations are decoupled from the qubit and coherence is enhanced, yet the drive speed becomes maximal. Our proof-of-concept experiment shows that a properly engineered qubit can be made faster and simultaneously more coherent, removing an important roadblock. Further, it demonstrates that through all-electrical control a qubit can be sped up, without coupling more strongly to the electrical noise environment. As charge fluctuators are unavoidable in semiconductors and all-electrical control is highly scalable, our results improve the prospects for quantum computing in Si and Ge., Comment: Main: 6 pages with 3 display items plus 2 pages for references and methods Supplementary: 12 pages with 7 display items

The understanding of neutron star equation of state hinges on a comprehensive analysis of multi-messenger, multi-wavelength data. The recent scrutiny of PSR J0030+0451 data by NICER introduces complexities, unveiling a tension with another X-ray observation of the central compact object in HESS J1731-347, specifically concerning the mass-radius constraint of low-mass neutron stars. This tension persists when integrating NICER's updated data with LIGO/Virgo's gravitational-wave data from the GW170817 binary neutron star merger. Despite attempts to reconcile these disparate observations, the current combined data still can not distinguish different types of neutron stars -- whether they are pure neutron stars or hybrid stars. Bayesian inference indicates only modest changes in the posterior ranges of parameters related to the nuclear matter and deconfinement phase transition. This ongoing exploration underscores the intricate challenges in precisely characterizing neutron stars. It also points out that it is possible to probe the equation of state at different density regimes from future more accurate radii of neutron stars with various masses., Comment: 12 pages, 6 figures, 3 tables, To appear in Phys. Rev. D (2024)

This paper investigates block-level interference exploitation (IE) precoding for multi-user multiple-input single-output (MU-MISO) downlink systems. To overcome the need for symbol-level IE precoding to frequently update the precoding matrix, we propose to jointly optimize all the precoders or transmit signals within a transmission block. The resultant precoders only need to be updated once per block, and while not necessarily constant over all the symbol slots, we refer to the technique as block-level slot-variant IE precoding. Through a careful examination of the optimal structure and the explicit duality inherent in block-level power minimization (PM) and signal-to-interference-plus-noise ratio (SINR) balancing (SB) problems, we discover that the joint optimization can be decomposed into subproblems with smaller variable sizes. As a step further, we propose block-level slot-invariant IE precoding by adding a structural constraint on the slot-variant IE precoding to maintain a constant precoder throughout the block. A novel linear precoder for IE is further presented, and we prove that the proposed slot-variant and slot-invariant IE precoding share an identical solution when the number of symbol slots does not exceed the number of users. Numerical simulations demonstrate that the proposed precoders achieve a significant complexity reduction compared against benchmark schemes, without sacrificing performance., Comment: Submitted to IEEE

Large uncertainties in the determinations of the equation of state of dense stellar matter allow the intriguing possibility that the bulk quark matter in beta equilibrium might be the true ground state of the matter at zero pressure. And quarks will form Cooper pairs very readily since the dominant interaction between quarks is attractive in some channels. As a result, quark matter will generically exhibit color superconductivity, with the favored pairing pattern at intermediately high densities being two-flavor pairing. In the light of several possible candidates for such self-bound quark stars, including the very low-mass central compact object in supernova remnant HESS J1731-347 reported recently, we carry out one field-theoretic model, the Nambu-Jona-Lasinio model, of investigation on the stability of beta-stable two-flavor color superconducting (2SC) phase of quark matter, nevertheless find no physically-allowed parameter space for the existence of 2SC quark stars., Comment: 13 pages, 6 figures, with appendix; ApJ (2024) accepted

Spin period distribution provides important clues to understand the formation of millisecond pulsars (MSPs). To uncover the intrinsic period distribution, we analyze three samples of radio MSPs in the Galactic field and in globular clusters. The selection bias due to pulse broadening has been corrected but turns out to be negligible. We find that all the samples can be well described by a Weibull distribution of spin frequencies. Considering MSPs in the Galactic field or in globular clusters, and in isolation or in binary systems, we find no significant difference in the spin distribution among these subpopulations. Based on the current known population of MSPs, we find that sub-millisecond pulsars are unlikely to be discovered by the Square Kilometer Array, although up to $\sim10$ discoveries of pulsars that spin faster than the current record holder of $P=1.4$~ms are expected., Comment: 14 pages, 7 figures. Accepted by the ApJ for publication

Generating time series data is a promising approach to address data deficiency problems. However, it is also challenging due to the complex temporal properties of time series data, including local correlations as well as global dependencies. Most existing generative models have failed to effectively learn both the local and global properties of time series data. To address this open problem, we propose a novel time series generative model named 'Time-Transformer AAE', which consists of an adversarial autoencoder (AAE) and a newly designed architecture named 'Time-Transformer' within the decoder. The Time-Transformer first simultaneously learns local and global features in a layer-wise parallel design, combining the abilities of Temporal Convolutional Networks and Transformer in extracting local features and global dependencies respectively. Second, a bidirectional cross attention is proposed to provide complementary guidance across the two branches and achieve proper fusion between local and global features. Experimental results demonstrate that our model can outperform existing state-of-the-art models in 5 out of 6 datasets, specifically on those with data containing both global and local properties. Furthermore, we highlight our model's advantage on handling this kind of data via an artificial dataset. Finally, we show our model's ability to address a real-world problem: data augmentation to support learning with small datasets and imbalanced datasets., Comment: 15 pages, 7 figures and 16 tables. SDM24

Computational models are an essential tool for the design, characterization, and discovery of novel materials. Hard computational tasks in materials science stretch the limits of existing high-performance supercomputing centers, consuming much of their simulation, analysis, and data resources. Quantum computing, on the other hand, is an emerging technology with the potential to accelerate many of the computational tasks needed for materials science. In order to do that, the quantum technology must interact with conventional high-performance computing in several ways: approximate results validation, identification of hard problems, and synergies in quantum-centric supercomputing. In this paper, we provide a perspective on how quantum-centric supercomputing can help address critical computational problems in materials science, the challenges to face in order to solve representative use cases, and new suggested directions., Comment: 65 pages, 15 figures; comments welcome

The rapid advancement of quantum computing has pushed classical designs into the quantum domain, breaking physical boundaries for computing-intensive and data-hungry applications. Given its immense potential, quantum-based computing systems have attracted increasing attention with the hope that some systems may provide a quantum speedup. For example, variational quantum algorithms have been proposed for quantum neural networks to train deep learning models on qubits, achieving promising results. Existing quantum learning architectures and systems rely on single, monolithic quantum machines with abundant and stable resources, such as qubits. However, fabricating a large, monolithic quantum device is considerably more challenging than producing an array of smaller devices. In this paper, we investigate a distributed quantum system that combines multiple quantum machines into a unified system. We propose DQuLearn, which divides a quantum learning task into multiple subtasks. Each subtask can be executed distributively on individual quantum machines, with the results looping back to classical machines for subsequent training iterations. Additionally, our system supports multiple concurrent clients and dynamically manages their circuits according to the runtime status of quantum workers. Through extensive experiments, we demonstrate that DQuLearn achieves similar accuracies with significant runtime reduction, by up to 68.7% and an increase per-second circuit processing speed, by up to 3.99 times, in a 4-worker multi-tenant setting., Comment: IEEE BigData 2023

Hybrid quantum-classical approaches offer potential solutions to quantum chemistry problems, yet they also introduce challenges. These challenges include addressing the barren plateau and ensuring the accuracy of the ans\"{a}tze, which often manifest as constrained optimization problems. In this work, we explore the interconnection between constrained optimization and generalized eigenvalue problems through \textcolor{black}{the Unitary Coupled Cluster (UCC) excitation generators. These generators often serve as building blocks constituting the ans\"{a}tze in variational quantum eigensolver (VQE) and adaptive derivative-assembled pseudo-Trotter VQE (ADAPT-VQE) simulations. Here, inspired by the generator coordinate method, we employ these UCC excitation generators to construct non-orthogonal, overcomplete many-body generating functions, projecting the system Hamiltonian into a practical working subspace. This approach results in a generalized eigenvalue problem that provides rigorous lower bounds to VQE/ADAPT-VQE energies, effectively bypassing issues related to barren plateaus and heuristic numerical minimizers typical in standard VQE methods. Diverging from conventional quantum subspace expansion methods, we introduce an adaptive scheme that robustly constructs many-body basis sets from a pool of the UCC excitation generators. This scheme supports the development of a hierarchical ADAPT quantum-classical strategy, enabling a balanced interplay between subspace expansion and ansatz optimization to address complex, strongly correlated quantum chemical systems efficiently and cost-effectively. The effective Hamiltonian generated by our approach also supports the computation of excited states and dynamic properties, setting the stage for more advanced quantum simulations in chemistry.

Gatemon qubits are the electrically tunable cousins of superconducting transmon qubits. In this work, we demonstrate the full coherent control of a gatemon qubit based on hole carriers in a Ge/Si core/shell nanowire, with the longest coherence times in group IV material gatemons to date. The key to these results is a high-quality Josephson junction obtained in a straightforward and reproducible annealing technique. We demonstrate that the transport through the narrow junctions is dominated by only two quantum channels, with transparencies up to unity. This novel qubit platform holds great promise for quantum information applications, not only because it incorporates technologically relevant materials, but also because it provides new opportunities, like an ultrastrong spin-orbit coupling in the few-channel regime of Josephson junctions., Comment: 15 pages, 11 figures

Facilitating the ability to achieve logical qubit error rates below physical qubit error rates, error correction is anticipated to play an important role in scaling quantum computers. While many algorithms require millions of physical qubits to be executed with error correction, current superconducting qubit systems contain only hundreds of physical qubits. One of the most promising codes on the superconducting qubit platform is the surface code, requiring a realistically attainable error threshold and the ability to perform universal fault-tolerant quantum computing with local operations via lattice surgery and magic state injection. Surface code architectures easily generalize to single-chip planar layouts, however space and control hardware constraints point to limits on the number of qubits that can fit on one chip. Additionally, the planar routing on single-chip architectures leads to serialization of commuting gates and strain on classical decoding caused by large ancilla patches. A distributed multi-chip architecture utilizing the surface code can potentially solve these problems if one can optimize inter-chip gates, manage collisions in networking between chips, and minimize routing hardware costs. We propose QuIRC, a superconducting Quantum Interface Routing Card for Lattice Surgery between surface code modules inside of a single dilution refrigerator. QuIRC improves scaling by allowing connection of many modules, increases ancilla connectivity of surface code lattices, and offers improved transpilation of Pauli-based surface code circuits. QuIRC employs in-situ Entangled Pair (EP) generation protocols for communication. We explore potential topological layouts of QuIRC based on superconducting hardware fabrication constraints, and demonstrate reductions in ancilla patch size by up to 77.8%, and in layer transpilation size by 51.9% when compared to the single-chip case.

Smoothed Particle Hydrodynamics (SPH) is essential for modeling complex large-deformation problems across various applications, requiring significant computational power. A major portion of SPH computation time is dedicated to the Nearest Neighboring Particle Search (NNPS) process. While advanced NNPS algorithms have been developed to enhance SPH efficiency, the potential efficiency gains from modern computation hardware remain underexplored. This study investigates the impact of GPU parallel architecture, low-precision computing on GPUs, and GPU memory management on NNPS efficiency. Our approach employs a GPU-accelerated mixed-precision SPH framework, utilizing low-precision float-point 16 (FP16) for NNPS while maintaining high precision for other components. To ensure FP16 accuracy in NNPS, we introduce a Relative Coordinated-based Link List (RCLL) algorithm, storing FP16 relative coordinates of particles within background cells. Our testing results show three significant speedup rounds for CPU-based NNPS algorithms. The first comes from parallel GPU computations, with up to a 1000x efficiency gain. The second is achieved through low-precision GPU computing, where the proposed FP16-based RCLL algorithm offers a 1.5x efficiency improvement over the FP64-based approach on GPUs. By optimizing GPU memory bandwidth utilization, the efficiency of the FP16 RCLL algorithm can be further boosted by 2.7x, as demonstrated in an example with 1 million particles. Our code is released at https://github.com/pnnl/lpNNPS4SPH.

Emerging deep learning workloads urgently need fast general matrix multiplication (GEMM). To meet such demand, one of the critical features of machine-learning-specific accelerators such as NVIDIA Tensor Cores, AMD Matrix Cores, and Google TPUs is the support of mixed-precision enabled GEMM. For DNN models, lower-precision FP data formats and computation offer acceptable correctness but significant performance, area, and memory footprint improvement. While promising, the mixed-precision computation on error resilience remains unexplored. To this end, we develop a fault injection framework that systematically injects fault into the mixed-precision computation results. We investigate how the faults affect the accuracy of machine learning applications. Based on the error resilience characteristics, we offer lightweight error detection and correction solutions that significantly improve the overall model accuracy if the models experience hardware faults. The solutions can be efficiently integrated into the accelerator's pipelines.

The relentless advancement of artificial intelligence (AI) and machine learning (ML) applications necessitates the development of specialized hardware accelerators capable of handling the increasing complexity and computational demands. Traditional computing architectures, based on the von Neumann model, are being outstripped by the requirements of contemporary AI/ML algorithms, leading to a surge in the creation of accelerators like the Graphcore Intelligence Processing Unit (IPU), Sambanova Reconfigurable Dataflow Unit (RDU), and enhanced GPU platforms. These hardware accelerators are characterized by their innovative data-flow architectures and other design optimizations that promise to deliver superior performance and energy efficiency for AI/ML tasks. This research provides a preliminary evaluation and comparison of these commercial AI/ML accelerators, delving into their hardware and software design features to discern their strengths and unique capabilities. By conducting a series of benchmark evaluations on common DNN operators and other AI/ML workloads, we aim to illuminate the advantages of data-flow architectures over conventional processor designs and offer insights into the performance trade-offs of each platform. The findings from our study will serve as a valuable reference for the design and performance expectations of research prototypes, thereby facilitating the development of next-generation hardware accelerators tailored for the ever-evolving landscape of AI/ML applications. Through this analysis, we aspire to contribute to the broader understanding of current accelerator technologies and to provide guidance for future innovations in the field., Comment: ICPE 2024 accepted publication

Topic modeling has emerged as a valuable tool for discovering patterns and topics within large collections of documents. However, when cross-analysis involves multiple parties, data privacy becomes a critical concern. Federated topic modeling has been developed to address this issue, allowing multiple parties to jointly train models while protecting pri-vacy. However, there are communication and performance challenges in the federated sce-nario. In order to solve the above problems, this paper proposes a method to establish a federated topic model while ensuring the privacy of each node, and use neural network model pruning to accelerate the model, where the client periodically sends the model neu-ron cumulative gradients and model weights to the server, and the server prunes the model. To address different requirements, two different methods are proposed to determine the model pruning rate. The first method involves slow pruning throughout the entire model training process, which has limited acceleration effect on the model training process, but can ensure that the pruned model achieves higher accuracy. This can significantly reduce the model inference time during the inference process. The second strategy is to quickly reach the target pruning rate in the early stage of model training in order to accelerate the model training speed, and then continue to train the model with a smaller model size after reaching the target pruning rate. This approach may lose more useful information but can complete the model training faster. Experimental results show that the federated topic model pruning based on the variational autoencoder proposed in this paper can greatly accelerate the model training speed while ensuring the model's performance., Comment: 8 pages

Academic networks in the real world can usually be described by heterogeneous information networks composed of multi-type nodes and relationships. Some existing research on representation learning for homogeneous information networks lacks the ability to explore heterogeneous information networks in heterogeneous information networks. It cannot be applied to heterogeneous information networks. Aiming at the practical needs of effectively identifying and discovering scientific research teams from the academic heterogeneous information network composed of massive and complex scientific and technological big data, this paper proposes a scientific research team identification method based on representation learning of academic heterogeneous information networks. The attention mechanism at node level and meta-path level learns low-dimensional, dense and real-valued vector representations on the basis of retaining the rich topological information of nodes in the network and the semantic information based on meta-paths, and realizes effective identification and discovery of scientific research teams and important team members in academic heterogeneous information networks based on maximizing node influence. Experimental results show that our proposed method outperforms the comparative methods., Comment: 19 pages

The existence of adversarial examples has been a mystery for years and attracted much interest. A well-known theory by \citet{ilyas2019adversarial} explains adversarial vulnerability from a data perspective by showing that one can extract non-robust features from adversarial examples and these features alone are useful for classification. However, the explanation remains quite counter-intuitive since non-robust features are mostly noise features to humans. In this paper, we re-examine the theory from a larger context by incorporating multiple learning paradigms. Notably, we find that contrary to their good usefulness under supervised learning, non-robust features attain poor usefulness when transferred to other self-supervised learning paradigms, such as contrastive learning, masked image modeling, and diffusion models. It reveals that non-robust features are not really as useful as robust or natural features that enjoy good transferability between these paradigms. Meanwhile, for robustness, we also show that naturally trained encoders from robust features are largely non-robust under AutoAttack. Our cross-paradigm examination suggests that the non-robust features are not really useful but more like paradigm-wise shortcuts, and robust features alone might be insufficient to attain reliable model robustness. Code is available at \url{https://github.com/PKU-ML/AdvNotRealFeatures}., Comment: NeurIPS 2023

Mixture-of-Experts (MoE) has emerged as a favorable architecture in the era of large models due to its inherent advantage, i.e., enlarging model capacity without incurring notable computational overhead. Yet, the realization of such benefits often results in ineffective GPU memory utilization, as large portions of the model parameters remain dormant during inference. Moreover, the memory demands of large models consistently outpace the memory capacity of contemporary GPUs. Addressing this, we introduce SiDA-MoE ($\textbf{S}$parsity-$\textbf{i}$nspired $\textbf{D}$ata-$\textbf{A}$ware), an efficient inference approach tailored for large MoE models. SiDA-MoE judiciously exploits both the system's main memory, which is now abundant and readily scalable, and GPU memory by capitalizing on the inherent sparsity on expert activation in MoE models. By adopting a data-aware perspective, SiDA-MoE achieves enhanced model efficiency with a neglectable performance drop. Specifically, SiDA-MoE attains a remarkable speedup in MoE inference with up to $3.93\times$ throughput increasing, up to $72\%$ latency reduction, and up to $80\%$ GPU memory saving with down to $1\%$ performance drop. This work paves the way for scalable and efficient deployment of large MoE models, even with constrained resources. Code is available at: https://github.com/timlee0212/SiDA-MoE., Comment: Published on MLSys24. https://openreview.net/forum?id=q26ydTFF5j}

Numerical simulation is an important method for verifying the quantum circuits used to simulate low-energy nuclear states. However, real-world applications of quantum computing for nuclear theory often generate deep quantum circuits that place demanding memory and processing requirements on conventional simulation methods. Here, we present advances in high-performance numerical simulations of deep quantum circuits to efficiently verify the accuracy of low-energy nuclear physics applications. Our approach employs several novel methods for accelerating the numerical simulation including 1- and 2-qubit gate fusion techniques as well as management of simulated mid-circuit measurements to verify state preparation circuits. We test these methods across a variety of high-performance computing systems and our results show that circuits up to 21 qubits and more than 115,000,000 gates can be efficiently simulated.

Scoliosis is a three-dimensional spinal deformity, which may lead to abnormal morphologies, such as thoracic deformity, and pelvic tilt. Severe patients may suffer from nerve damage and urinary abnormalities. At present, the number of scoliosis patients in primary and secondary schools has exceeded five million in China, the incidence rate is about 3% to 5% which is growing every year. The research on scoliosis, therefore, has important clinical value. This paper systematically introduces computer-assisted scoliosis screening and diagnosis as well as analyzes the advantages and limitations of different algorithm models in the current issue field. Moreover, the paper also discusses the current development bottlenecks in this field and looks forward to future development trends., Comment: 8 pages, review paper

Large Language Models (LLMs) have shown remarkable success in various tasks, yet their safety and the risk of generating harmful content remain pressing concerns. In this paper, we delve into the potential of In-Context Learning (ICL) to modulate the alignment of LLMs. Specifically, we propose the In-Context Attack (ICA) which employs harmful demonstrations to subvert LLMs, and the In-Context Defense (ICD) which bolsters model resilience through examples that demonstrate refusal to produce harmful responses. We offer theoretical insights to elucidate how a limited set of in-context demonstrations can pivotally influence the safety alignment of LLMs. Through extensive experiments, we demonstrate the efficacy of ICA and ICD in respectively elevating and mitigating the success rates of jailbreaking prompts. Our findings illuminate the profound influence of ICL on LLM behavior, opening new avenues for improving the safety of LLMs.

This paper has delved into the pressing need for intelligent emergency control in large-scale power systems, which are experiencing significant transformations and are operating closer to their limits with more uncertainties. Learning-based control methods are promising and have shown effectiveness for intelligent power system control. However, when they are applied to large-scale power systems, there are multifaceted challenges such as scalability, adaptiveness, and security posed by the complex power system landscape, which demand comprehensive solutions. The paper first proposes and instantiates a convergence framework for integrating power systems physics, machine learning, advanced computing, and grid control to realize intelligent grid control at a large scale. Our developed methods and platform based on the convergence framework have been applied to a large (more than 3000 buses) Texas power system, and tested with 56000 scenarios. Our work achieved a 26% reduction in load shedding on average and outperformed existing rule-based control in 99.7% of the test scenarios. The results demonstrated the potential of the proposed convergence framework and DRL-based intelligent control for the future grid., Comment: submitted to PSCC 2024

Despite significant results achieved by Contrastive Language-Image Pretraining (CLIP) in zero-shot image recognition, limited effort has been made exploring its potential for zero-shot video recognition. This paper presents Open-VCLIP++, a simple yet effective framework that adapts CLIP to a strong zero-shot video classifier, capable of identifying novel actions and events during testing. Open-VCLIP++ minimally modifies CLIP to capture spatial-temporal relationships in videos, thereby creating a specialized video classifier while striving for generalization. We formally demonstrate that training Open-VCLIP++ is tantamount to continual learning with zero historical data. To address this problem, we introduce Interpolated Weight Optimization, a technique that leverages the advantages of weight interpolation during both training and testing. Furthermore, we build upon large language models to produce fine-grained video descriptions. These detailed descriptions are further aligned with video features, facilitating a better transfer of CLIP to the video domain. Our approach is evaluated on three widely used action recognition datasets, following a variety of zero-shot evaluation protocols. The results demonstrate that our method surpasses existing state-of-the-art techniques by significant margins. Specifically, we achieve zero-shot accuracy scores of 88.1%, 58.7%, and 81.2% on UCF, HMDB, and Kinetics-600 datasets respectively, outpacing the best-performing alternative methods by 8.5%, 8.2%, and 12.3%. We also evaluate our approach on the MSR-VTT video-text retrieval dataset, where it delivers competitive video-to-text and text-to-video retrieval performance, while utilizing substantially less fine-tuning data compared to other methods. Code is released at https://github.com/wengzejia1/Open-VCLIP., Comment: arXiv admin note: substantial text overlap with arXiv:2302.00624

Weight decay is a standard technique to improve generalization performance in modern deep neural network optimization, and is also widely adopted in federated learning (FL) to prevent overfitting in local clients. In this paper, we first explore the choices of weight decay and identify that weight decay value appreciably influences the convergence of existing FL algorithms. While preventing overfitting is crucial, weight decay can introduce a different optimization goal towards the global objective, which is further amplified in FL due to multiple local updates and heterogeneous data distribution. To address this challenge, we develop {\it Federated optimization with Normalized Annealing Regularization} (FedNAR), a simple yet effective and versatile algorithmic plug-in that can be seamlessly integrated into any existing FL algorithms. Essentially, we regulate the magnitude of each update by performing co-clipping of the gradient and weight decay. We provide a comprehensive theoretical analysis of FedNAR's convergence rate and conduct extensive experiments on both vision and language datasets with different backbone federated optimization algorithms. Our experimental results consistently demonstrate that incorporating FedNAR into existing FL algorithms leads to accelerated convergence and heightened model accuracy. Moreover, FedNAR exhibits resilience in the face of various hyperparameter configurations. Specifically, FedNAR has the ability to self-adjust the weight decay when the initial specification is not optimal, while the accuracy of traditional FL algorithms would markedly decline. Our codes are released at \href{https://github.com/ljb121002/fednar}{https://github.com/ljb121002/fednar}., Comment: Thirty-seventh Conference on Neural Information Processing Systems

The theoretical landscape of federated learning (FL) undergoes rapid evolution, but its practical application encounters a series of intricate challenges, and hyperparameter optimization is one of these critical challenges. Amongst the diverse adjustments in hyperparameters, the adaptation of the learning rate emerges as a crucial component, holding the promise of significantly enhancing the efficacy of FL systems. In response to this critical need, this paper presents FedHyper, a novel hypergradient-based learning rate adaptation algorithm specifically designed for FL. FedHyper serves as a universal learning rate scheduler that can adapt both global and local rates as the training progresses. In addition, FedHyper not only showcases unparalleled robustness to a spectrum of initial learning rate configurations but also significantly alleviates the necessity for laborious empirical learning rate adjustments. We provide a comprehensive theoretical analysis of FedHyper's convergence rate and conduct extensive experiments on vision and language benchmark datasets. The results demonstrate that FEDHYPER consistently converges 1.1-3x faster than FedAvg and the competing baselines while achieving superior final accuracy. Moreover, FedHyper catalyzes a remarkable surge in accuracy, augmenting it by up to 15% compared to FedAvg under suboptimal initial learning rate settings.