Search

huggingface.co › papers › 2605.04012

Paper page - SymptomAI: Towards a Conversational AI Agent for Everyday Symptom Assessment

… We deployed SymptomAI, a set of conversational AI agents for end-to-end patient interviewing and differential diagnosis DDx , via the Fitbit app in a study that randomized participants N=13,917 to interact with five AI agents. …

May 7, 2026

huggingface.co › papers › 2605.01640

Paper page - Prescriptive Scaling Laws for Data Constrained Training

… View arXiv page View PDF Add to collection Community A scaling law that describes language model behavior under data repetition. …

May 8, 2026

huggingface.co › papers › 2605.01402

Paper page - Injecting Distributional Awareness into MLLMs via Reinforcement Learning for Deep Imbalanced Regression

… Token-level supervised fine-tuning SFT and point-wise regression rewards bias learning toward high-density regions, leading to regression-to-the-mean behavior and poor tail performance. …

May 12, 2026