Search

Transformer-based models have become increasingly popular and have impacted speech-processing research owing to their exceptional performance in sequence modeling. Recently, a promising model architecture, Mamba, has emerged as a potential alternative to transformer-based models because of its efficient modeling of long sequences. In particular, models like SEMamba have demonstrated the effectiveness of the Mamba architecture in single-channel speech enhancement. This paper aims to adapt SEMamba for multi-channel applications with only a small increase in parameters. The resulting system, MC-SEMamba, achieved results on the CHiME3 dataset that were comparable or even superior to several previous baseline models. Additionally, we found that increasing the number of microphones from 1 to 6 improved the speech enhancement performance of MC-SEMamba.

Qudit-based quantum gates in high-dimensional Hilbert space can provide a viable route towards effectively accelerating the speed of quantum computing and performing complex quantum logic operations. In the paper, we propose a 2-qudit $4\times4$-dimensional controlled-not (CNOT) gate for four silicon-vacancy spins, in which the first two electron-spin states in silicon-vacancy centers are encoded as the control qudits, and the other ones as the target qudits. The proposed protocol is implemented with assistance of an ancillary photon that serves as a common-data bus linking four motionless silicon-vacancy spins placed in four independent single-sided optical nanocavities. Moreover, the CNOT gate works in a deterministic manner by performing the relational feed-forward operations corresponding to the diverse outcomes of the single-photon detectors to be directed against the ancillary photon. Further, it can be potentially generalized to other solid-state quantum system. Under current technological conditions, both the efficiency and fidelity of the 2-qudit CNOT gate are high.

The success of language models in code assistance has spurred the proposal of repository-level code completion as a means to enhance prediction accuracy, utilizing the context from the entire codebase. However, this amplified context can inadvertently increase inference latency, potentially undermining the developer experience and deterring tool adoption - a challenge we termed the Context-Latency Conundrum. This paper introduces REPOFUSE, a pioneering solution designed to enhance repository-level code completion without the latency trade-off. REPOFUSE uniquely fuses two types of context: the analogy context, rooted in code analogies, and the rationale context, which encompasses in-depth semantic relationships. We propose a novel rank truncated generation (RTG) technique that efficiently condenses these contexts into prompts with restricted size. This enables REPOFUSE to deliver precise code completions while maintaining inference efficiency. Through testing with the CrossCodeEval suite, REPOFUSE has demonstrated a significant leap over existing models, achieving a 40.90% to 59.75% increase in exact match (EM) accuracy for code completions and a 26.8% enhancement in inference speed. Beyond experimental validation, REPOFUSE has been integrated into the workflow of a large enterprise, where it actively supports various coding tasks.

In the domain of large-scale software development, the demands for dynamic and multifaceted static code analysis exceed the capabilities of traditional tools. To bridge this gap, we present CodeFuse-Query, a system that redefines static code analysis through the fusion of Domain Optimized System Design and Logic Oriented Computation Design. CodeFuse-Query reimagines code analysis as a data computation task, support scanning over 10 billion lines of code daily and more than 300 different tasks. It optimizes resource utilization, prioritizes data reusability, applies incremental code extraction, and introduces tasks types specially for Code Change, underscoring its domain-optimized design. The system's logic-oriented facet employs Datalog, utilizing a unique two-tiered schema, COREF, to convert source code into data facts. Through Godel, a distinctive language, CodeFuse-Query enables formulation of complex tasks as logical expressions, harnessing Datalog's declarative prowess. This paper provides empirical evidence of CodeFuse-Query's transformative approach, demonstrating its robustness, scalability, and efficiency. We also highlight its real-world impact and diverse applications, emphasizing its potential to reshape the landscape of static code analysis in the context of large-scale software development.Furthermore, in the spirit of collaboration and advancing the field, our project is open-sourced and the repository is available for public access

The escalating complexity of software systems and accelerating development cycles pose a significant challenge in managing code errors and implementing business logic. Traditional techniques, while cornerstone for software quality assurance, exhibit limitations in handling intricate business logic and extensive codebases. To address these challenges, we introduce the Intelligent Code Analysis Agent (ICAA), a novel concept combining AI models, engineering process designs, and traditional non-AI components. The ICAA employs the capabilities of large language models (LLMs) such as GPT-3 or GPT-4 to automatically detect and diagnose code errors and business logic inconsistencies. In our exploration of this concept, we observed a substantial improvement in bug detection accuracy, reducing the false-positive rate to 66\% from the baseline's 85\%, and a promising recall rate of 60.8\%. However, the token consumption cost associated with LLMs, particularly the average cost for analyzing each line of code, remains a significant consideration for widespread adoption. Despite this challenge, our findings suggest that the ICAA holds considerable potential to revolutionize software quality assurance, significantly enhancing the efficiency and accuracy of bug detection in the software development process. We hope this pioneering work will inspire further research and innovation in this field, focusing on refining the ICAA concept and exploring ways to mitigate the associated costs.

Code Large Language Models (Code LLMs) have gained significant attention in the industry due to their wide applications in the full lifecycle of software engineering. However, the effectiveness of existing models in understanding non-English inputs for multi-lingual code-related tasks is still far from well studied. This paper introduces CodeFuse-13B, an open-sourced pre-trained code LLM. It is specifically designed for code-related tasks with both English and Chinese prompts and supports over 40 programming languages. CodeFuse achieves its effectiveness by utilizing a high quality pre-training dataset that is carefully filtered by program analyzers and optimized during the training process. Extensive experiments are conducted using real-world usage scenarios, the industry-standard benchmark HumanEval-x, and the specially designed CodeFuseEval for Chinese prompts. To assess the effectiveness of CodeFuse, we actively collected valuable human feedback from the AntGroup's software development process where CodeFuse has been successfully deployed. The results demonstrate that CodeFuse-13B achieves a HumanEval pass@1 score of 37.10%, positioning it as one of the top multi-lingual code LLMs with similar parameter sizes. In practical scenarios, such as code generation, code translation, code comments, and testcase generation, CodeFuse performs better than other models when confronted with Chinese prompts., Comment: Accepted by ICSE-SEIP 2024

The decoherence effect caused by the coupling between the system and the environment undoubtedly leads to the errors in efficient implementations of two (or three) qubit logical gates in quantum information processing. Fortunately, decoherence-free subspace (DFS) introduced can effectively decrease the influence of decoherence effect. In this paper, we propose some schemes for setting up a family of quantum control gates, including controlled-NOT (CNOT), Toffoli, and Fredkin gates for two or three logical qubits by means of cross-Kerr nonlinearities in DFS. These three logical gates require neither complicated quantum computational circuits nor auxiliary photons (or entangled states). The success probabilities of three logical gates are approximate 1 by performing the corresponding classical feed-forward operations based on the different measuring results of the X-homodyne detectors, and their fidelities are robust against the photon loss with the current technology. The proposed logical gates rely on only simple linear-optics elements, available single-qubit operations, and mature measurement methods, making our proposed gates be feasible and efficient in practical applications., Comment: 17 pages, 16 figures

This paper presents Squid, a new conjunctive query synthesis algorithm for searching code with target patterns. Given positive and negative examples along with a natural language description, Squid analyzes the relations derived from the examples by a Datalog-based program analyzer and synthesizes a conjunctive query expressing the search intent. The synthesized query can be further used to search for desired grammatical constructs in the editor. To achieve high efficiency, we prune the huge search space by removing unnecessary relations and enumerating query candidates via refinement. We also introduce two quantitative metrics for query prioritization to select the queries from multiple candidates, yielding desired queries for code search. We have evaluated Squid on over thirty code search tasks. It is shown that Squid successfully synthesizes the conjunctive queries for all the tasks, taking only 2.56 seconds on average., Comment: 32 pages, 7 figures, and 1 table. Accepted by ECOOP 2023

Data constraints are widely used in FinTech systems for monitoring data consistency and diagnosing anomalous data manipulations. However, many equivalent data constraints are created redundantly during the development cycle, slowing down the FinTech systems and causing unnecessary alerts. We present EqDAC, an efficient decision procedure to determine the data constraint equivalence. We first propose the symbolic representation for semantic encoding and then introduce two light-weighted analyses to refute and prove the equivalence, respectively, which are proved to achieve in polynomial time. We evaluate EqDAC upon 30,801 data constraints in a FinTech system. It is shown that EqDAC detects 11,538 equivalent data constraints in three hours. It also supports efficient equivalence searching with an average time cost of 1.22 seconds, enabling the system to check new data constraints upon submission., Comment: 14 pages, 11 figures, accepted by ICSE 2023

High-efficiency quantum information processing is equivalent to the fewest quantum resources and the simplest operations by means of logic qubit gates. Based on the reflection geometry of a single photon interacting with a three-level $\Lambda$-typle atom-cavity system, we present some refined protocols for realizing controlled-not (CNOT), Fredkin, and Toffoli gates on hybrid systems. The first control qubit of our gates is encoded on a flying photon, and the rest qubits are encoded on the atoms in optical cavity. Moreover, these quantum gates can be extended to the optimal synthesis of multi-qubit CNOT, Fredkin and Toffoli gates with O(n) optical elements without auxiliary photons or atoms. Further, the simplest single-qubit operations are applied to the photon only, which make these logic gates experimentally feasible with current technology.

The emergence of metaverse brings tremendous evolution to Non-Fungible Tokens (NFTs), which could certify the ownership the unique digital asset in the cyber world. The NFT market has garnered unprecedented attention from investors and created billions of dollars in transaction volume. Meanwhile, securing NFT is still a challenging issue. Recently, numerous incidents of NFT theft have been reported, leading to incalculable losses for holders. We propose a decentralized NFT anti-theft mechanism called TokenPatronus, which supports the general ERC-721 standard and provide the holders with strong property protection. TokenPatronus contains pre-event protection, in-event interruption, and post-event replevin enhancements for the complete NFTs transactions stages. Four modules are designed to make up the decentralized anti-theft mechanism, including the decentralized access control (DAC), the decentralized risk management (DRM), the decentralized arbitration system (DAS) and the ERC-721G standard smart contract. TokenPatronus is performing on the Turtlecase NFT project of Ethereum and will support more blockchains in the future., Comment: submitted to CESC 2022 as a work-in-progress paper

How is information processed in the brain during perception? Mechanistic insight is achieved only when experiments are employed to test formal or computational models. In analogy to lesion studies, phantom perception may serve as a vehicle to understand the fundamental processing principles underlying auditory perception. With a special focus on tinnitus -- as the prime example of auditory phantom perception -- we review recent work at the intersection of artificial intelligence, psychology, and neuroscience. In particular, we discuss why everyone with tinnitus suffers from hearing loss, but not everyone with hearing loss suffers from tinnitus. We argue that the increase of sensory precision due to Bayesian inference could be caused by intrinsic neural noise and lead to a prediction error in the cerebral cortex. Hence, two fundamental processing principles - being ubiquitous in the brain - provide the most explanatory power for the emergence of tinnitus: predictive coding as a top-down, and stochastic resonance as a complementary bottom-up mechanism. We conclude that both principles play a crucial role in healthy auditory perception., Comment: arXiv admin note: substantial text overlap with arXiv:2010.01914

With an increasing number of value-flow properties to check, existing static program analysis still tends to have scalability issues when high precision is required. We observe that the key design flaw behind the scalability problem is that the core static analysis engine is oblivious of the mutual synergies among different properties being checked and, thus, inevitably loses many optimization opportunities. Our approach is inter-property-aware and able to capture possible overlaps and inconsistencies among different properties. Thus, before analyzing a program, we can make optimization plans which decide how to reuse the specific analysis results of a property to speed up checking other properties. Such a synergistic interaction among the properties significantly improves the analysis performance. We have evaluated our approach by checking twenty value-flow properties in standard benchmark programs and ten real-world software systems. The results demonstrate that our approach is more than 8x faster than existing ones but consumes only 1/7 memory. Such a substantial improvement in analysis efficiency is not achieved by sacrificing the effectiveness: at the time of writing, 39 bugs found by our approach have been fixed by developers and four of them have been assigned CVE IDs due to their security impact.

Making liquid droplets move spontaneously on solid surfaces is a key challenge in lab-on-chip and heat exchanger technologies. The best-known mechanism, a wettability gradient, does not generally move droplets rapidly enough and cannot drive droplets smaller than a critical size. Here we report how a curvature gradient is particularly effective at accelerating small droplets, and works for both hydrophilic and hydrophobic surfaces. Experiments for water droplets on tapered surfaces with curvature radii in the sub-millimeter range show a maximum speed of 0.28 m/s, two orders of magnitude higher than obtained by wettability gradient. We show that the force exerted on a droplet scales as the surface curvature gradient. Using molecular dynamics simulations, we observe nanoscale droplets moving spontaneously at over 100 m/s on tapered surfaces., Comment: 18 pages, 6 figures. arXiv admin note: substantial text overlap with arXiv:1202.6582

How to make small liquid droplets move spontaneously and directionally on solid surfaces is a challenge in lab-on-chip technologies, DNA analysis, and heat exchangers. The best-known mechanism, a wettability gradient, does not move droplets rapidly enough for most purposes and cannot move droplets smaller than a critical size defined by the contact angle hysteresis. Here we report on a mechanism using curvature gradients, which we show is particularly effective at accelerating small droplets, and works for both hydrophilic and hydrophobic surfaces. Experiments for water droplets on glass cones in the sub-millimeter range show a maximum speed of 0.28 m/s, two orders of magnitude higher than obtained by wettability gradient. From simple considerations of droplet surface area change, we show that the force exerted on a droplet on a conical surface scales as the curvature gradient. This force therefore diverges for small droplets near the tip of a cone. We illustrate this using molecular dynamics simulations, and describe nanometer-scale droplets moving spontaneously at over 100 m/s on nano-cones., Comment: 18 pages, 7 figures

We study the indentation of a free-standing lipid membrane suspended over a nanopore on a hydrophobic substrate by means of molecular dynamics simulations. We find that in the course of indentation, the membrane bends at the point of contact, and the fringes of the membrane glide downward intermittently along the pore edges and stop gliding when the fringes reach the edge bottoms. The bending continues afterwards, and the large strain eventually induces a phase transition in the membrane, transformed from a bilayered structure to an interdigitated structure. The membrane is finally ruptured when the indentation goes deep enough. Several local physical quantities in the pore regions are calculated, which include the tilt angle of lipid molecules, the nematic order, the included angle and the distance between neighboring lipids. The variations of these quantities reveal many detailed, not-yet-specified local structural transitions of lipid molecules under indentation. The force-indentation curve is also studied and discussed. The results make connection between the microscopic structure and the macroscopic properties, and provide deep insight in the understanding of the stability of a lipid membrane spanning over a nanopore., Comment: 45 pages, 13 figures, accepted for publication in Langmuir

We report experimental observation of a kind of fast spontaneous movements of water drops on surfaces of cones with diameters from 0.1 to 1.5 mm. The observed maximum speed (0.22 m/s) under ambient conditions were at least two orders of magnitude higher than that resulting from any known single spontaneous movement mechanism, for example, Marangoni effect due to gradient of surface tension. We trapped even higher spontaneous movement speeds (up to 125 m/s) in virtual experiments for drops on nanoscale cones by using molecular dynamics simulations. The underlying mechanism is found to be universally effective - drops on any surface either hydrophilic or hydrophobic with varying mean curvature are subject to driving forces toward the gradient direction of the mean curvature. The larger the mean curvature of the surface and the lower the contact angle of the liquid are, the stronger the driving force will be. This discovery can lead to more effective techniques for transporting droplets., Comment: 11 pages, 4 figures (supplementary information: 5 pages, 2 figures)

Earlier works found out spontaneous directional motion of liquid droplets on hydrophilic conical surfaces, however, not hydrophobic case. Here we show that droplets on any surface may take place spontaneous directional motion without considering contact angle property. The driving force is found to be proportional to the curvature gradient of the surface. Fast motion can be lead at surfaces with small curvature radii. The above discovery can help to create more effective transportation technology of droplets, and better understand some observed natural phenomena., Comment: 18 pages, 7 figures