ThinkGuard: Deliberative Slow Thinking Leads to Cautious Guardrails Paper • 2502.13458 • Published Feb 19, 2025 • 1
MetaScientist: A Human-AI Synergistic Framework for Automated Mechanical Metamaterial Design Paper • 2412.16270 • Published Dec 20, 2024
RedCoder: Automated Multi-Turn Red Teaming for Code LLMs Paper • 2507.22063 • Published Jun 25, 2025 • 2
Diagnosing and Mitigating Modality Interference in Multimodal Large Language Models Paper • 2505.19616 • Published May 26, 2025 • 1
Towards Policy-Compliant Agents: Learning Efficient Guardrails For Policy Violation Detection Paper • 2510.03485 • Published Oct 3, 2025
ModelLens: Finding the Best for Your Task from Myriads of Models Paper • 2605.07075 • Published 14 days ago • 15