Search papers, labs, and topics across Lattice.
7
1
9
12
ConRub-Med achieves unprecedented accuracy in open-ended medical question answering by leveraging scalable, model-generated rubrics that outperform traditional expert-driven methods.
SimpleSearch-VL achieves a remarkable 15.8-point boost in agentic search performance with minimal data, challenging the need for larger models or extensive training.
Clinical agents face a staggering 62.3% accuracy ceiling in complex EHR reasoning, revealing significant gaps in current AI capabilities.
SlimSearcher cuts tool-call rounds by up to 58% without sacrificing accuracy, redefining efficiency in web agent training.
Forget static user profiles – LATTE forecasts where a user's preferences are *going*, not just where they've been, boosting personalized LLM generation.
Forget RLHF, a new framework distills clinician preferences into reusable "HealthPrinciples" that let smaller models outperform giants on medical benchmarks.
Current LLMs still struggle with multi-turn medical diagnosis, needing more than just bigger models to truly master dialogue management.
