Search papers, labs, and topics across Lattice.
3
0
7
2
Multimodal perception is no longer just an add-on: GLM-5V-Turbo bakes it directly into the core of reasoning, planning, and action.
Agentic RAG gets a 7.7 point accuracy boost thanks to Search-P1's path-centric reward shaping, which extracts learning signals even from failed reasoning attempts.
Dramatically reduce hallucination in industrial RAG systems by jointly optimizing retrieval and generation with graph-aware retrieval and reinforcement learning, leading to a 92.7% reduction in URL hallucination in a real-world advertising QA system.
