activity
20242026
collaborators

5 papers

cs.SE2026

Can Large Language Models Model Programs Formally?

Zhiyong Chen, Jialun Cao, Jiarong Wu +2

In the digital age, ensuring the correctness, safety, and reliability of software through formal verification is paramount, particularly as software increasingly underpins critical…

cs.SE2026

ModelWisdom: An Integrated Toolkit for TLA+ Model Visualization, Digest and Repair

Zhiyong Chen, Jialun Cao, Chang Xu +1

Model checking in TLA+ provides strong correctness guarantees, yet practitioners continue to face significant challenges in interpreting counterexamples, understanding large state-…

cs.LG2026

TriSpec: Ternary Speculative Decoding via Lightweight Proxy Verification

Haoyun Jiang, Junqi He, Feng Hong +8

Inference efficiency in Large Language Models (LLMs) is fundamentally limited by their serial, autoregressive generation, especially as reasoning becomes a key capability and respo…

cs.SE2025

AetherCode: Evaluating LLMs' Ability to Win In Premier Programming Competitions

Zihan Wang, Jiaze Chen, Zhicheng Liu +25

Competitive programming has emerged as a critical benchmark for evaluating the reasoning and coding capabilities of Large Language Models (LLMs). Despite impressive progress on exi…

cs.LG2024

JavaBench: A Benchmark of Object-Oriented Code Generation for Evaluating Large Language Models

Jialun Cao, Zhiyong Chen, Jiarong Wu +2

Code generation benchmarks such as HumanEval are widely adopted to evaluate LLMs' capabilities. However, after consolidating the latest 24 benchmarks, we noticed three significant…