Papers, modelos e datasets em alta no Hugging Face, além do blog oficial — com leitura editorial em português.
Dataset em destaque no Hugging Face — 951 downloads.
Introducing Co-Scientist, a collaborative AI partner built with Gemini to help researchers accelerate scientific breakthroughs.
Modelo de modelo · 27 B de parâmetros — 207 downloads e 46 curtidas no Hugging Face.
Using SocialReasoning Bench, we observed a stable pattern across models—agents execute competently, but fail to consistently improve the user’s position, even with explicit instructions to optimize for user interest. The post SocialReasoning-Bench: Measuring whether AI agents act in users’ best interests appeared first on Microsoft Research .
.apr-fig { text-align: center; margin: 1.35em 0; line-height: 1.4; } .apr-fig--wide img { display: inline-block; width: 100%; max-width: 100%; height: auto; vertical-align: middle; } .apr-fig--wide-0-8 { max-width: 80%; margin-left: auto; margin-right: auto; } .apr-fig--tall img { display: inline-block; max-height: 300px; width: auto; max-width: 100%; height: auto; object-fit: contain; vertical-align: middle; } .apr-fig--tall-1-2x img { display: inline-block; max-height: 360px; width: auto; max-...
An axiomatic evaluation framework reveals systematic failures in latent thought representations of LLMs across multiple reasoning tasks, demonstrating that current representations…
Explore how AlphaEvolve's Gemini-powered algorithms are driving impact across business, infrastructure, and science.
Dataset com 1 mil – 10 mil exemplos — 9.0 mil downloads no Hugging Face. Background Ended up with some tokens to burn on a Claude Max plan.
Data Mining & Modeling
Researching the path to AI-augmented care and development of an AI co-clinician.