arXiv subjects

Zongyang Li

Publications and source records attributed to Zongyang Li.

6 recordsLinked to original sources

arXiv2026

Shaping the learning signal in a combined Q-learning rule to improve structured cooperation

Q-learning provides a standard reinforcement learning framework for studying cooperation by specifying how agents update action values from repeated local interactions outcomes. Although previous work has shown that reputation can promote cooperation in such systems, most models introduce reputation by modifying payoffs, encoding it directly in the state or changing partner selection, which makes it difficult to isolate the role of the learning signal itself. Here, we construct the reinforcement signal as a weighted combination of reputation and game payoffs, leaving the game and network structure unchanged. We find that increasing the weight on reputation generally promotes cooperation by consolidating clusters, but this effect is conditional on the learning dynamics. Specifically, this promoting effect vanishes in two regimes: when the learning rate is extremely small, which prevents effective information propagation and when the discount factor approaches one, as distant future expectations obscure the immediate reputational advantage. Outside these limiting cases, the efficacy of reputation in promoting cooperation is attenuated by higher learning rates but amplified by larger discount factors. These results advance the understanding of cooperative dynamics by demonstrating that cooperation can be stabilized through the reputational shaping of learning signals alone, providing critical insights into the interplay between social information and individual learning parameters.

physics.soc-ph↗

arXiv2025

DeCon: Detecting Incorrect Assertions via Postconditions Generated by a Large Language Model

Recently, given the docstring for the target problem and the target function signature, large language models (LLMs) have been used not only to generate source code, but also to generate test cases, consisting of test inputs and assertions (e.g., in the form of checking an actual output against the expected output). However, as shown by our empirical study on assertions generated by four LLMs for the HumanEval benchmark, over 62% of the generated assertions are incorrect (i.e., failed on the ground-truth problem solution). To detect incorrect assertions (given the docstring and the target function signature along with a sample of example inputs and outputs), in this paper, we propose a new approach named DeCon to effectively detect incorrect assertions via LLM-generated postconditions for the target problem (a postcondition is a predicate that must always be true just after the execution of the ground-truth problem solution). Our approach requires a small set of I/O examples (i.e., a sample of example inputs and outputs) for the target problem (e.g., the I/O examples included in the docstring for a target problem in HumanEval). We use the given I/O examples to filter out those LLM-generated postconditions that are violated by at least one given I/O example. We then use the remaining postconditions to detect incorrect assertions as those assertions that violate at least one remaining postcondition. Experimental results show that DeCon can detect averagely more than 64% (63% and 65.5% detected by GPT-3.5 and GPT-4, respectively) incorrect assertions generated by four state-of-the-art LLMs, and DeCon can also improve the effectiveness of these LLMs in code generation by 4% in terms of Pass@1. In addition, although DeCon might filter out correct assertions, the fault-finding ability of the remaining correct assertions decreases only slightly.

cs.SE↗

arXiv2023

VulLibGen: Generating Names of Vulnerability-Affected Packages via a Large Language Model

Security practitioners maintain vulnerability reports (e.g., GitHub Advisory) to help developers mitigate security risks. An important task for these databases is automatically extracting structured information mentioned in the report, e.g., the affected software packages, to accelerate the defense of the vulnerability ecosystem. However, it is challenging for existing work on affected package identification to achieve a high accuracy. One reason is that all existing work focuses on relatively smaller models, thus they cannot harness the knowledge and semantic capabilities of large language models. To address this limitation, we propose VulLibGen, the first method to use LLM for affected package identification. In contrast to existing work, VulLibGen proposes the novel idea to directly generate the affected package. To improve the accuracy, VulLibGen employs supervised fine-tuning (SFT), retrieval augmented generation (RAG) and a local search algorithm. The local search algorithm is a novel postprocessing algorithm we introduce for reducing the hallucination of the generated packages. Our evaluation results show that VulLibGen has an average accuracy of 0.806 for identifying vulnerable packages in the four most popular ecosystems in GitHub Advisory (Java, JS, Python, Go) while the best average accuracy in previous work is 0.721. Additionally, VulLibGen has high value to security practice: we submitted 60 pairs to GitHub Advisory (covers four ecosystems). 34 of them have been accepted and merged and 20 are pending approval. Our code and dataset can be found in the attachments.

cs.CR↗

arXiv2022

GDsmith: Detecting Bugs in Graph Database Engines

Graph database engines stand out in the era of big data for their efficiency of modeling and processing linked data. There is a strong need of testing graph database engines. However, random testing, the most practical way of automated test generation, faces the challenges of semantic validity, non-empty result, and behavior diversity to detect bugs in graph database engines. To address these challenges, in this paper, we propose GDsmith, the first black-box approach for testing graph database engines. It ensures that each randomly generated Cypher query satisfies the semantic requirements via skeleton generation and completion. GDsmith includes our technique to increase the probability of producing Cypher queries that return non-empty results by leveraging three types of structural mutation strategies. GDsmith also includes our technique to improve the behavior diversity of the generated Cypher queries by selecting property keys according to their previous frequencies when generating new queries. Our evaluation results demonstrate that GDsmith is effective and efficient for automated query generation and substantially outperforms the baseline. GDsmith successfully detects 27 previously unknown bugs on the released versions of three popular open-source graph database engines and receive positive feedback from their developers.

cs.DB↗

arXiv2020

3 m$\times$3 m heterolithic passive resonant gyroscope with cavity length stabilization

Large-scale high sensitivity laser gyroscopes have important applications for ground-based and space-based gravitational wave detection. We report on the development of a 3 m$\times$3 m heterolithic passive resonant gyroscope (HUST-1) which is installed on the ground of a cave laboratory. We operate the HUST-1 on different longitudinal cavity modes and the rotation sensitivity reaches $1.6\times10^{-9}$ rad/s/$\rm \sqrt{Hz}$ beyond 1 Hz. The drift of the cavity length is one of the major sensitivity limits for our gyroscope in the low frequency regime. By locking cavity length to an ultra-stable reference laser, we achieve a fractional cavity length stability of $5.6\times10^{-9}$ m$/\rm \sqrt{Hz}$ at 0.1 mHz, a four orders of magnitude improvement over the unconstrained cavity in the low frequency regime. We stabilize the cavity length of a large-scale heterolithic passive resonant gyroscope through active feedback and realize long-term operation. The rotation sensitivity reaches $1.7\times10^{-7}$ rad/s/$\sqrt{\rm{Hz}}$ at 0.1 mHz, a three orders of magnitude improvement, which is no longer limited by the cavity length drift in this frequency range.

physics.ins-det↗

arXiv2018

A Highly Parallel FPGA Implementation of Sparse Neural Network Training

We demonstrate an FPGA implementation of a parallel and reconfigurable architecture for sparse neural networks, capable of on-chip training and inference. The network connectivity uses pre-determined, structured sparsity to significantly reduce complexity by lowering memory and computational requirements. The architecture uses a notion of edge-processing, leading to efficient pipelining and parallelization. Moreover, the device can be reconfigured to trade off resource utilization with training time to fit networks and datasets of varying sizes. The combined effects of complexity reduction and easy reconfigurability enable significantly greater exploration of network hyperparameters and structures on-chip. As proof of concept, we show implementation results on an Artix-7 FPGA.

cs.DC↗