Search papers, labs, and topics across Lattice.
2
5
5
6
An open-source ecosystem for agentic learning, complete with a trained agent and novel policy optimization, promises to accelerate research by providing a standardized, scalable platform.
MLLMs can be made significantly safer without sacrificing performance by disentangling risks in multimodal inputs and using RLAIF, outperforming even GPT-4V by 16% on safety benchmarks.