Evolve the Method, Not the Prompts: Evolutionary Synthesis of Jailbreak Attacks on LLMs Paper • 2511.12710 • Published 4 days ago • 34
WithAnyone: Towards Controllable and ID Consistent Image Generation Paper • 2510.14975 • Published Oct 16 • 80
SafeWork-R1: Coevolving Safety and Intelligence under the AI-45^{circ} Law Paper • 2507.18576 • Published Jul 24 • 7
Frontier AI Risk Management Framework in Practice: A Risk Analysis Technical Report Paper • 2507.16534 • Published Jul 22 • 7