Search papers, labs, and topics across Lattice.
4
0
9
10
Frontier LLMs can be induced to generate biologically hazardous sequences, with attack success rates reaching up to 100%.
Achieving superior safety alignment with LLMs using only 100 harmful samples, SafeSteer drastically cuts alignment costs while maintaining model performance.
AgentSchool offers a powerful new way to simulate educational environments, moving beyond simple role-play to model learning as a dynamic state transition and providing a testbed for long-horizon memory and multi-agent coordination.
Self-evolving agents can now learn more efficiently in resource-constrained environments by explicitly structuring experience into a tool graph memory that facilitates planning and tool reuse.
