Dingmin Wang

Cyber-Zero: Training Cybersecurity Agents without Runtime

t-BEN: A Temporal Logic Guided Approach for Temporal Reasoning Benchmark Generation

Training Language Model Agents to Find Vulnerabilities with CTF-Dojo

BigCodeArena: Unveiling More Reliable Human Preferences in Code Generation via Execution

CRABS: A syntactic-semantic pincer strategy for bounding LLM interpretation of Python notebooks

C-3PO: Compact Plug-and-Play Proxy Optimization to Achieve Human-like Retrieval-Augmented Generation

RuleRAG: Rule-Guided Retrieval-Augmented Generation with Language Models for Question Answering

tBen: Benchmarking and Testing the Rule-Based Temporal Logic Reasoning Ability of Large Language Models with DatalogMTL