29 citations · 50 across the 20 of their papers we have counts for
20 papers
From Reasoning Strings to Partial Orders: Verifier-Certified Rule Transport through Quotient Policy Optimization
Bang Xie, Hao Liu, Zhiyuan Peng +5
Many computations admit several valid execution orders because independent subgoals or disjoint state updates can commute. Reinforcement learning with verifiable rewards usually tr…
PonyEval: Evaluating LLM-Based Program Repair for Capability-Safe and Actor-Oriented Pony Software
Bang Xie, Hao Liu, Zhenyu Shi +8
Repository-level issue-resolution benchmarks have made executable evaluation central to software-engineering agents, but their language coverage remains concentrated in mainstream…
OdinEval: A Reproducible Benchmark for LLM-Based Program Repair in the Odin Programming Language
Bang Xie, Hao Liu, Zhiyuan Peng +8
Repository-level repair benchmarks still center on a few mainstream languages, leaving systems languages such as Odin largely untested. We present OdinEval, a reproducible benchmar…
AppEval: A Unified Benchmark for LLM-Based Mobile Application Repair in ArkTS, Swift, and Kotlin
Bang Xie, Hao Liu, Zhenyu Shi +11
Repository-level LLM agents are typically evaluated on projects whose tests run on the build host. It remains unclear whether their repairs survive the mobile build-install-launch-…
KQFuzz: Knowledge-Guided Fuzzing for Quantum Libraries via Large Language Models
Fuyuan Xia, Qixin Zhang, Chenhao Ying +5
As quantum computing continually improves, ensuring the reliability and correctness of quantum libraries has become increasingly critical. To this end, many LLM-based fuzzing appro…
EvoClawBench: Can Agents Learn Reusable Skills from Their Own Runs?
Zhiyuan Peng, Xin Yin, Chenhao Ying +5
Existing agent benchmarks primarily test task completion, tool use, or skill utility, but do not isolate whether a runtime can convert evidence from its own runs into reusable skil…
PlayCoder: Making LLM-Generated GUI Code Playable
Zhiyuan Peng, Wei Tao, Xin Yin +3
Large language models (LLMs) have achieved strong results in code generation, but their ability to generate GUI applications, especially games, remains insufficiently studied. Exis…
ArkEval: Benchmarking and Evaluating Automated CodeRepair for ArkTS
Bang Xie, Senjian Zhang, Zhiyuan Peng +3
Large language models have transformed code generation, enabling unprecedented automation in software development. As mobile ecosystems evolve, HarmonyOS has emerged as a critical…
SolAgent: A Specialized Multi-Agent Framework for Solidity Code Generation
Wei Chen, Zhiyuan Peng, Xin Yin +4
Smart contracts are the backbone of the decentralized web, yet ensuring their functional correctness and security remains a critical challenge. While Large Language Models (LLMs) h…
A Preference-Driven Methodology for High-Quality Solidity Code Generation
Zhiyuan Peng, Xin Yin, Chenhao Ying +2
While Large Language Models (LLMs) have demonstrated remarkable progress in generating functionally correct Solidity code, they continue to face critical challenges in producing ga…
Domain Generalization via Discrete Codebook Learning
Shaocong Long, Qianyu Zhou, Xikun Jiang +3
Domain generalization (DG) strives to address distribution shifts across diverse environments to enhance model's generalizability. Current DG approaches are confined to acquiring r…
Generative Classifier for Domain Generalization
Shaocong Long, Qianyu Zhou, Xiangtai Li +7
Domain generalization (DG) aims to improve the generalizability of computer vision models toward distribution shifts. The mainstream DG methods predominantly focus on learning doma…
MulChain: Enabling Advanced Cross-Modal Queries in Hybrid-Storage Blockchains
Zhiyuan Peng, Xin Yin, Gang Wang +5
With its decentralization and immutability, blockchain has emerged as a trusted foundation for data management and querying. Because blockchain storage space is limited, large mult…
SolEval: Benchmarking Large Language Models for Repository-level Solidity Code Generation
Zhiyuan Peng, Xin Yin, Rui Qian +5
Large language models (LLMs) have transformed code generation. However, most existing approaches focus on mainstream languages such as Python and Java, neglecting the Solidity lang…
Privacy-Preserving UCB Decision Process Verification via zk-SNARKs
Xikun Jiang, He Lyu, Chenhao Ying +3
With the increasingly widespread application of machine learning, how to strike a balance between protecting the privacy of data and algorithm parameters and ensuring the verifiabi…
DGMamba: Domain Generalization via Generalized State Space Model
Shaocong Long, Qianyu Zhou, Xiangtai Li +5
Domain generalization~(DG) aims at solving distribution shift problems in various scenes. Existing approaches are based on Convolution Neural Networks (CNNs) or Vision Transformers…
Rethinking Domain Generalization: Discriminability and Generalizability
Shaocong Long, Qianyu Zhou, Chenhao Ying +2
Domain generalization(DG) endeavors to develop robust models that possess strong generalizability while preserving excellent discriminability. Nonetheless, pivotal DG techniques te…
Diverse Target and Contribution Scheduling for Domain Generalization
Shaocong Long, Qianyu Zhou, Chenhao Ying +2
Generalization under the distribution shift has been a great challenge in computer vision. The prevailing practice of directly employing the one-hot labels as the training targets…
Incentive Mechanism for Uncertain Tasks under Differential Privacy
Xikun Jiang, Chenhao Ying, Lei Li +4
Mobile crowd sensing (MCS) has emerged as an increasingly popular sensing paradigm due to its cost-effectiveness. This approach relies on platforms to outsource tasks to participat…
Constructions of Binary Optimal Locally Repairable Codes via Intersection Subspaces
Wenqin Zhang, Deng Tang, Chenhao Ying +1
Locally repairable codes (LRCs), which can recover any symbol of a codeword by reading only a small number of other symbols, have been widely used in real-world distributed storage…