Search

We introduce AutoCoder, the first Large Language Model to surpass GPT-4 Turbo (April 2024) and GPT-4o in pass@1 on the Human Eval benchmark test ($\mathbf{90.9\%}$ vs. $\mathbf{90.2\%}$). In addition, AutoCoder offers a more versatile code interpreter compared to GPT-4 Turbo and GPT-4o. It's code interpreter can install external packages instead of limiting to built-in packages. AutoCoder's training data is a multi-turn dialogue dataset created by a system combining agent interaction and external code execution verification, a method we term \textbf{\textsc{AIEV-Instruct}} (Instruction Tuning with Agent-Interaction and Execution-Verified). Compared to previous large-scale code dataset generation methods, \textsc{AIEV-Instruct} reduces dependence on proprietary large models and provides execution-validated code dataset. The code and the demo video is available in \url{https://github.com/bin123apple/AutoCoder}.

Recent advancements in large language models, such as GPT-4, have demonstrated remarkable capabilities in processing standard queries. Despite these advancements, their performance substantially declines in \textbf{advanced mathematical problems requiring complex, multi-step logical reasoning}. To enhance their inferential capabilities, current research has delved into \textit{prompting engineering}, exemplified by methodologies such as the Tree of Thought and Graph of Thought. Nonetheless, these existing approaches encounter two significant limitations. Firstly, their effectiveness in tackling complex mathematical problems is somewhat constrained. Secondly, the necessity to design distinct prompts for individual problems hampers their generalizability. In response to these limitations, this paper introduces the \textit{Multi-Agent System for conditional Mining} (\textbf{MACM}) prompting method. It not only resolves intricate mathematical problems but also demonstrates strong generalization capabilities across various mathematical contexts. With the assistance of MACM, the accuracy of GPT-4 Turbo on the most challenging level five mathematical problems in the MATH dataset increase from $\mathbf{54.68\%} \text{ to } \mathbf{76.73\%}$. The code is available in \url{https://github.com/bin123apple/MACM}.

As a quasi-layered ferrimagnetic material, Mn$_3$Si$_2$Te$_6$ nanoflakes exhibit magnetoresistance behaviour that is fundamentally different from their bulk crystal counterparts. They offer three key properties crucial for spintronics. Firstly, at least 10^6 times faster response comparing to that exhibited by bulk crystals has been observed in current-controlled resistance and magnetoresistance. Secondly, ultra-low current density is required for resistance modulation (~ 5 A/cm$^2$). Thirdly, electrically gate-tunable magnetoresistance has been realized. Theoretical calculations reveal that the unique magnetoresistance behaviour in the Mn$_3$Si$_2$Te$_6$ nanoflakes arises from a magnetic field induced band gap shift across the Fermi level. The rapid current induced resistance variation is attributed to spin-orbit torque, an intrinsically ultra-fast process (~nanoseconds). This study suggests promising avenues for spintronic applications. In addition, it highlights Mn$_3$Si$_2$Te$_6$ nanoflakes as a suitable platform for investigating the intriguing physics underlying chiral orbital moments, magnetic field induced band variation and spin torque., Comment: 22 pages,4 figures

In the evolving field of machine learning, video generation has witnessed significant advancements with autoregressive-based transformer models and diffusion models, known for synthesizing dynamic and realistic scenes. However, these models often face challenges with prolonged inference times, even for generating short video clips such as GIFs. This paper introduces FlashVideo, a novel framework tailored for swift Text-to-Video generation. FlashVideo represents the first successful adaptation of the RetNet architecture for video generation, bringing a unique approach to the field. Leveraging the RetNet-based architecture, FlashVideo reduces the time complexity of inference from $\mathcal{O}(L^2)$ to $\mathcal{O}(L)$ for a sequence of length $L$, significantly accelerating inference speed. Additionally, we adopt a redundant-free frame interpolation method, enhancing the efficiency of frame interpolation. Our comprehensive experiments demonstrate that FlashVideo achieves a $\times9.17$ efficiency improvement over a traditional autoregressive-based transformer model, and its inference speed is of the same order of magnitude as that of BERT-based transformer models.

The increasing use of Advanced Language Models (ALMs) in diverse sectors, particularly due to their impressive capability to generate top-tier content following linguistic instructions, forms the core of this investigation. This study probes into ALMs' deployment in electronic hardware design, with a specific emphasis on the synthesis and enhancement of Verilog programming. We introduce an innovative framework, crafted to assess and amplify ALMs' productivity in this niche. The methodology commences with the initial crafting of Verilog programming via ALMs, succeeded by a distinct dual-stage refinement protocol. The premier stage prioritizes augmenting the code's operational and linguistic precision, while the latter stage is dedicated to aligning the code with Power-Performance-Area (PPA) benchmarks, a pivotal component in proficient hardware design. This bifurcated strategy, merging error remediation with PPA enhancement, has yielded substantial upgrades in the caliber of ALM-created Verilog programming. Our framework achieves an 81.37% rate in linguistic accuracy and 62.0% in operational efficacy in programming synthesis, surpassing current leading-edge techniques, such as 73% in linguistic accuracy and 46% in operational efficacy. These findings illuminate ALMs' aptitude in tackling complex technical domains and signal a positive shift in the mechanization of hardware design operations.

Large language models (LLMs) have become increasingly prominent in academia and industry due to their remarkable performance in diverse applications. As these models evolve with increasing parameters, they excel in tasks like sentiment analysis and machine translation. However, even models with billions of parameters face challenges in tasks demanding multi-step reasoning. Code generation and comprehension, especially in C and C++, emerge as significant challenges. While LLMs trained on code datasets demonstrate competence in many tasks, they struggle with rectifying non-compilable C and C++ code. Our investigation attributes this subpar performance to two primary factors: the quality of the training dataset and the inherent complexity of the problem which demands intricate reasoning. Existing "Chain of Thought" (CoT) prompting techniques aim to enhance multi-step reasoning. This approach, however, retains the limitations associated with the latent drawbacks of LLMs. In this work, we propose CompCodeVet, a compiler-guided CoT approach to produce compilable code from non-compilable ones. Diverging from the conventional approach of utilizing larger LLMs, we employ compilers as a teacher to establish a more robust zero-shot thought process. The evaluation of CompCodeVet on two open-source code datasets shows that CompCodeVet has the ability to improve the training dataset quality for LLMs.

Biologically-inspired Spiking Neural Networks (SNNs), processing information using discrete-time events known as spikes rather than continuous values, have garnered significant attention due to their hardware-friendly and energy-efficient characteristics. However, the training of SNNs necessitates a considerably large memory footprint, given the additional storage requirements for spikes or events, leading to a complex structure and dynamic setup. In this paper, to address memory constraint in SNN training, we introduce an innovative framework, characterized by a remarkably low memory footprint. We \textbf{(i)} design a reversible SNN node that retains a high level of accuracy. Our design is able to achieve a $\mathbf{58.65\times}$ reduction in memory usage compared to the current SNN node. We \textbf{(ii)} propose a unique algorithm to streamline the backpropagation process of our reversible SNN node. This significantly trims the backward Floating Point Operations Per Second (FLOPs), thereby accelerating the training process in comparison to current reversible layer backpropagation method. By using our algorithm, the training time is able to be curtailed by $\mathbf{23.8\%}$ relative to existing reversible layer architectures.

Recent advancements in large-scale models, such as GPT-4, have showcased remarkable capabilities in addressing standard queries. However, when facing complex problems that require multi-step logical reasoning, their accuracy dramatically decreases. Current research has explored the realm of \textit{prompting engineering} to bolster the inferential capacities of these models. Our paper unveils a pioneering prompting technique, dubbed \textit{Graph of Thoughts (GoT)}. Through testing on a trio of escalating challenges: the 24-point game, resolution of high-degree polynomial equations, and derivation of formulas for recursive sequences, our method outperformed GPT-4, achieving accuracy improvements of $89.7\%$, $86\%$, and $56\%$ for each respective task. Moreover, when juxtaposed with the state-of-the-art (SOTA) prompting method, \textit{Tree of Thought (ToT)}, our approach registered an average accuracy boost of $23\%$, $24\%$, and $15\%$.

In this study, we present a novel dataset for training machine learning models translating between OpenMP Fortran and C++ code. To ensure reliability and applicability, the dataset is created from a range of representative open-source OpenMP benchmarks. It is also refined using a meticulous code similarity test. The effectiveness of our dataset is assessed using both quantitative (CodeBLEU) and qualitative (human evaluation) methods. We showcase how this dataset significantly elevates the translation competencies of large language models (LLMs). Specifically, models without prior coding knowledge experienced a boost of $\mathbf{\times~5.1}$ in their CodeBLEU scores, while models with some coding familiarity saw an impressive $\mathbf{\times~9.9}$-fold increase. The best fine-tuned model using our dataset outperforms GPT-4. It is also reaching human-level accuracy. This work underscores the immense potential of our dataset in propelling advancements in the domain of code translation for high-performance computing. The dataset is accessible at \href{https://github.com/bin123apple/Fortran-CPP-HPC-code-translation-dataset}{OpenMP-Fortran-CPP-Translation}., Comment: This paper was accepted by the HPEC 2023 conference and received the Outstanding Student Paper Award

Biologically inspired Spiking Neural Networks (SNNs) have attracted significant attention for their ability to provide extremely energy-efficient machine intelligence through event-driven operation and sparse activities. As artificial intelligence (AI) becomes ever more democratized, there is an increasing need to execute SNN models on edge devices. Existing works adopt weight pruning to reduce SNN model size and accelerate inference. However, these methods mainly focus on how to obtain a sparse model for efficient inference, rather than training efficiency. To overcome these drawbacks, in this paper, we propose a Neurogenesis Dynamics-inspired Spiking Neural Network training acceleration framework, NDSNN. Our framework is computational efficient and trains a model from scratch with dynamic sparsity without sacrificing model fidelity. Specifically, we design a new drop-and-grow strategy with decreasing number of non-zero weights, to maintain extreme high sparsity and high accuracy. We evaluate NDSNN using VGG-16 and ResNet-19 on CIFAR-10, CIFAR-100 and TinyImageNet. Experimental results show that NDSNN achieves up to 20.52\% improvement in accuracy on Tiny-ImageNet using ResNet-19 (with a sparsity of 99\%) as compared to other SOTA methods (e.g., Lottery Ticket Hypothesis (LTH), SET-SNN, RigL-SNN). In addition, the training cost of NDSNN is only 40.89\% of the LTH training cost on ResNet-19 and 31.35\% of the LTH training cost on VGG-16 on CIFAR-10.

Traffic state prediction in a transportation network is paramount for effective traffic operations and management, as well as informed user and system-level decision-making. However, long-term traffic prediction (beyond 30 minutes into the future) remains challenging in current research. In this work, we integrate the spatio-temporal dependencies in the transportation network from network modeling, together with the graph convolutional network (GCN) and graph attention network (GAT). To further tackle the dramatic computation and memory cost caused by the giant model size (i.e., number of weights) caused by multiple cascaded layers, we propose sparse training to mitigate the training cost, while preserving the prediction accuracy. It is a process of training using a fixed number of nonzero weights in each layer in each iteration. We consider the problem of long-term traffic speed forecasting for a real large-scale transportation network data from the California Department of Transportation (Caltrans) Performance Measurement System (PeMS). Experimental results show that the proposed GCN-STGT and GAT-STGT models achieve low prediction errors on short-, mid- and long-term prediction horizons, of 15, 30 and 45 minutes in duration, respectively. Using our sparse training, we could train from scratch with high sparsity (e.g., up to 90%), equivalent to 10 times floating point operations per second (FLOPs) reduction on computational cost using the same epochs as dense training, and arrive at a model with very small accuracy loss compared with the original dense training

Kagome lattice composed of transition-metal ions provides a great opportunity to explore the intertwining between geometry, electronic orders and band topology. The discovery of multiple competing orders that connect intimately with the underlying topological band structure in nonmagnetic kagome metals $A$V$_3$Sb$_5$ ($A$ = K, Rb, Cs) further pushes this topic to the quantum frontier. Here we report the discovery and characterization of a new class of vanadium-based compounds with kagome bilayers, namely $A$V$_6$Sb$_6$ ($A$ = K, Rb, Cs) and V$_6$Sb$_4$, which, together with $A$V$_3$Sb$_5$, compose a series of kagome compounds with a generic chemical formula ($A_{m-1}$Sb$_{2m}$)(V$_3$Sb)$_n$ (m = 1, 2; n = 1, 2). Theoretical calculations combined with angle-resolved photoemission measurements reveal that these compounds feature Dirac nodal lines in close vicinity to the Fermi level. Pressure-induced superconductivity in $A$V$_6$Sb$_6$ further suggests promising emergent phenomena in these materials. The establishment of a new family of layered kagome materials paves the way for designer of fascinating kagome systems with diverse topological nontrivialities and collective ground states., Comment: 16 pages, 4 figures

The classification of large-scale high-resolution SAR land cover images acquired by satellites is a challenging task, facing several difficulties such as semantic annotation with expertise, changing data characteristics due to varying imaging parameters or regional target area differences, and complex scattering mechanisms being different from optical imaging. Given a large-scale SAR land cover dataset collected from TerraSAR-X images with a hierarchical three-level annotation of 150 categories and comprising more than 100,000 patches, three main challenges in automatically interpreting SAR images of highly imbalanced classes, geographic diversity, and label noise are addressed. In this letter, a deep transfer learning method is proposed based on a similarly annotated optical land cover dataset (NWPU-RESISC45). Besides, a top-2 smooth loss function with cost-sensitive parameters was introduced to tackle the label noise and imbalanced classes' problems. The proposed method shows high efficiency in transferring information from a similarly annotated remote sensing dataset, a robust performance on highly imbalanced classes, and is alleviating the over-fitting problem caused by label noise. What's more, the learned deep model has a good generalization for other SAR-specific tasks, such as MSTAR target recognition with a state-of-the-art classification accuracy of 99.46%.

The FeSe-based superconductors exhibit a wide range of critical temperature Tc under a variety of material and physical conditions, but extensive studies to date have yet to produce a consensus view on the underlying mechanism. Here we report on a systematic Raman scattering work on intercalated FeSe superconductors Lix(NH3)yFe2Se2 and (Li,Fe)OHFeSe compared to pristine FeSe. All three crystals show an anomalous power-law temperature dependence of phonon linewidths, deviating from the standard anharmonic behavior. This intriguing phenomenon is attributed to electron-phonon coupling effects enhanced by electron correlation, as evidenced by the evolution of the A1g Raman mode. Meanwhile, an analysis of the B1g mode, which probes the out-of-plane vibration of Fe, reveals a lack of influence by previously suggested structural parameters, and instead indicates a crucial role of the joint density of states in determining Tc. These findings identify carrier doping as the direct factor driving and modulating superconductivity in FeSe-based compounds., Comment: 6 pages, 4 figures

Deep convolutional neural networks (DCNNs) have attracted much attention in remote sensing recently. Compared with the large-scale annotated dataset in natural images, the lack of labeled data in remote sensing becomes an obstacle to train a deep network very well, especially in SAR image interpretation. Transfer learning provides an effective way to solve this problem by borrowing the knowledge from the source task to the target task. In optical remote sensing application, a prevalent mechanism is to fine-tune on an existing model pre-trained with a large-scale natural image dataset, such as ImageNet. However, this scheme does not achieve satisfactory performance for SAR application because of the prominent discrepancy between SAR and optical images. In this paper, we attempt to discuss three issues that are seldom studied before in detail: (1) what network and source tasks are better to transfer to SAR targets, (2) in which layer are transferred features more generic to SAR targets and (3) how to transfer effectively to SAR targets recognition. Based on the analysis, a transitive transfer method via multi-source data with domain adaptation is proposed in this paper to decrease the discrepancy between the source data and SAR targets. Several experiments are conducted on OpenSARShip. The results indicate that the universal conclusions about transfer learning in natural images cannot be completely applied to SAR targets, and the analysis of what and where to transfer in SAR target recognition is helpful to decide how to transfer more effectively.