Abstract: Adversarial examples are important to test and enhance the robustness of deep code models. As source code is discrete and has to strictly stick to complex grammar and semantics constraints, ...
Abstract: The existing power grid dispatching control system utilizes CIM/G language to describe human-computer interaction interfaces. As the power system continues to evolve, the complexity of CIM/G ...
This is the official repository for Generative Judge for Evaluating Alignment. We develop Auto-J, a new open-source generative judge that can effectively evaluate different LLMs on how they align to ...
The complete collection of Claude Code configs from an Anthropic hackathon winner. Production-ready agents, skills, hooks, commands, rules, and MCP configurations evolved over 10+ months of intensive ...