← Search

Naijun Zhan

4 accepted papers

2026

How Powerful are LLMs in Generating Program Specifications?

ICML 2026poster

Formal verification provides strong guarantees of software correctness, but its adoption is limited by the high cost of writing precise formal specifications. While recent large language models (LLMs) have demonstrated impressive capabilities in theorem proving and verified code generation, how powe…

Cited by 0SourceScholar
2026

PRM-PBE: Process Reward Model for Reinforcement Learning in Programming-by-Example

ICML 2026poster

Programming-by-Example (PBE), as a typical few-shot inductive reasoning paradigm, aims to synthesize corresponding algorithms from a set of input-output examples. Although Large Language Models (LLMs) have demonstrated strong program synthesis potential, they still remain ineffective when handling c…

Cited by 0SourceScholar
2026

RESTL: Reinforcement Learning Guided by Multi-Aspect Rewards for Signal Temporal Logic Transformation

AAAI 2026technical

Signal Temporal Logic (STL) is a powerful formal language for specifying real-time specifications of Cyber-Physical Systems (CPS). Transforming specifications written in natural language into STL formulas automatically has attracted increasing attention. Existing rule-based methods depend heavily on

Cited by 0SourcePDFScholar
2025

Enhancing Transformation from Natural Language to Signal Temporal Logic Using LLMs with Diverse External Knowledge

ACL 2025finding

Temporal Logic (TL), especially Signal Temporal Logic (STL), enables precise formal specification, making it widely used in cyber-physical systems such as autonomous driving and robotics. Automatically transforming NL into STL is an attractive approach to overcome the limitations of manual transform…