Responsibility & Safety
Published
6 October 2025
…
admin
Image by Author
# Introduction
If you’ve used LLMs for different tasks, you’ve probably noticed that the response often depends on how you write the prompt. This is what we call prompt engineering. The way you give instructions can be the difference between a vague reply and a precise, actionable answer. I know…
How do you create 3D datasets to train AI for Robotics without expensive traditional approaches? A team of researchers from NVIDIA released “ViPE: Video Pose Engine for 3D Geometric Perception” bringing a key improvement for Spatial AI. It addresses the central, agonizing bottleneck that has constrained the field of 3D computer vision for years.
ViPE…
Earlier this year, we mentioned that we're bringing computer use capabilities to developers via the Gemini API. Today, we are releasing the Gemini 2.5 Computer Use model, our new specialized model built on Gemini 2.5 Pro’s visual understanding and reasoning capabilities that powers agents capable of interacting with user interfaces (UIs). It outperforms leading alternatives…
Image by Editor
# Introducing ChatGPT Study Mode
Among the unending supply of AI-powered tools and features of late, ChatGPT Study Mode has captured the attention of students, educators, and lifelong learners. It promises to revolutionize study habits with personalized learning, interactive exercises, and on-demand explanations. Yet, as with any new technology, the…
A team of researchers from Meta Reality Labs and Carnegie Mellon University has introduced MapAnything, an end-to-end transformer architecture that directly regresses factored metric 3D scene geometry from images and optional sensor inputs. Released under Apache 2.0 with full training and benchmarking code, MapAnything advances beyond specialist pipelines by supporting over 12 distinct 3D vision…
Acknowledgements We thank the International Collegiate Programming Contest (ICPC) for their support. This project was a large-scale collaboration, and its success is due to the combined efforts of many individuals and teams. Hanzhao (Maggie) Lin led the overall technical direction for Gemini competitive programming and ICPC 2025 efforts, and co-led with Heng-Tze Cheng on the…
Image by Editor
# Introduction
In Python, there is a concept called object-oriented programming (OOP). This programming paradigm revolves around data and objects. It works by encapsulating related state (attributes) and behavior (methods) within classes, and creating object instances from those classes.
For many data scientists, Python is the first programming language they…
IBM has released Granite-Docling-258M, an open-source (Apache-2.0) vision-language model designed specifically for end-to-end document conversion. The model targets layout-faithful extraction—tables, code, equations, lists, captions, and reading order—emitting a structured, machine-readable representation rather than lossy Markdown. It is available on Hugging Face with a live demo and MLX build for Apple Silicon.
What’s new compared to…
Acknowledgements This work was developed by the Gemini Robotics team: Abbas Abdolmaleki, Saminda Abeyruwan, Joshua Ainslie, Jean-Baptiste Alayrac, Montserrat Gonzalez Arenas, Ashwin Balakrishna, Nathan Batchelor, Alex Bewley, Jeff Bingham, Michael Bloesch, Konstantinos Bousmalis, Philemon Brakel, Anthony Brohan, Thomas Buschmann, Arunkumar Byravan, Serkan Cabi, Ken Caluwaerts, Federico Casarini, Christine Chan, Oscar Chang, London Chappellet-Volpini, Jose Enrique…