Search papers, labs, and topics across Lattice.
4
0
8
Current subject-driven text-to-image models struggle with specific subject categories and prompt scenarios, a problem exposed by a new benchmark that also offers actionable insights for improvement.
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.
LLMs still struggle with real-world advertising analytics, with even Gemini-3-Pro dropping to 49.4% accuracy on the most complex tasks in the new AD-Bench benchmark.
