What comes next is even crazier: you can do this in real time and tell the actor to kick or punch, and it will happen instantly. I just posted about real-time world models, which are in their early days but will bring these capabilities to us soon. Then, sometime in the next 18
RESEARCH
-
FDA Submissions Embrace Real-World Evidence and AI Tools
By
–
82% of FDA submissions now include real-world evidence. @DominoDataLab
's Chris McSpiritt explains how statistical programmers are adapting to diverse data sources, open-source tools, and AI. -
Biggest obstacle to AI impact models: incomplete understanding of world
By
–
The biggest obstacle to making proper models about how AI will impact the world in the short, medium, and the long term is that we still don't have very good models of how the world *actually* works. For instance, we have never properly taken into the account that the world is
-

Best Data Visualization Projects of 2025
By
–
Best Data Visualization Projects of 2025 https://
buff.ly/65d6hff
#AI #MachineLearning #DeepLearning #LLMs #DataScience -

Gemini Accelerates Scientific Research Through Agentic Reasoning
By
–
The second paper "Accelerating Scientific Research with Gemini: Case Studies and Common Techniques" builds on similar agentic reasoning ideas, and identifies effective "recipes" for collaboration, specifically the "Advisor" model, where humans guide AI through iterative
-

Human-AI Interaction Card Proposes Novel Transparency Framework
By
–
Inspired by the "model" card, we also propose a novel concept of Human-AI Interaction (HAI) card to better capture how the experts and AI interacted. The goal here is for transparency to the general public. This is only the first proposal and we hope the community can further
-

AI Generates First Research Papers Without Human Intervention
By
–
At research-level mathematics, we are excited to announce the first wave of 6 research papers:
* Reliable autonomous research. A research paper (Feng26, https://
arxiv.org/abs/2601.23245) generated by AI without any human intervention, which calculates certain structure constants in -

Aletheia: Advanced AI Reasoning with Deep Think and Scaling
By
–
The three main sources that power Aletheia are:
#1: an advanced version of Gemini Deep Think for tackling extremely hard reasoning problems
#2: a novel inference-time scaling law that extends from
Olympiad-level problems to PhD-level exercises
#3: intensive tool use such as -

Foundation Models Struggle with Advanced Mathematics Research
By
–
Research-level mathematics draws on advanced techniques from vast literature, with papers often spanning dozens of pages. While foundation models possess a large knowledge base from pretraining, their understanding of advanced subjects remains superficial due to data scarcity,
-
Gemini Deep Think Accelerates Mathematical Scientific Discovery
By
–
Here's the link to the joint blog post: https://
deepmind.google/blog/accelerat
ing-mathematical-and-scientific-discovery-with-gemini-deep-think/
…. See details of the two papers below!