Scaling Vision Pre-Training to 4K Resolution
Paper: https://
arxiv.org/abs/2503.19903
Page: https://
nvlabs.github.io/PS3/
Code (Coming Soon): https://
github.com/NVLabs/PS3
RESEARCH
-

Scaling Vision Pre-Training to 4K Resolution
By
–
-

Berkeley NVIDIA Launch PS3 Vision Encoder for 4K Pretraining
By
–
Berkeley and NVIDIA dropped a major breakthrough: PS3, the first vision encoder to enable efficient visual pretraining at 4K ultra-high resolution—with no extra compute overhead. On top of that, they introduced VILA-HD, a multimodal large model built on PS3.
-
ICCV Review Completed: Computer Vision Research Insights
By
–
iccv review done..
My eyes need to have a rest.. -
Models interpret same prompts in intriguing experiment
By
–
It's intriguing to see how different models can interpret the same prompts. Great experiment! Can't wait to check out those videos.
-
Preview of LLMs: reasoning, autonomy, and task execution
By
–
What’s next This launch is a preview of where LLMs are going: – Unified reasoning + conversation
– Autonomy in tool use
– True task execution o3 is not just a model. It’s a step toward intelligent agents. Try them in ChatGPT https://
chat.openai.com
Developer docs -

Multimodal thinking: AI analyzes images and text
By
–
Multimodal thinking is here Upload a whiteboard photo or blurry chart? They don’t just see it they think with it. – Image + text reasoning
– Visual math and figure analysis
– Best-in-class performance on MathVista and CharXiv-Reasoning -

OpenAI o3 outperforms all models on math, code, and reasoning
By
–
o3 = OpenAI’s smartest model yet It outperforms everything on real-world tasks: – 91.6% on AIME 2024 math
– 2706 ELO on Codeforces
– 86.8% on multimodal MMMU benchmark
– 26.6% on GPQA “Humanity’s Last Exam” It doesn’t just answer it thinks, reasons, and adapts. -
OpenAI’s O3 and O4-mini models think, reason, and act with tools
By
–
🚨 Breaking: OpenAI just dropped its smartest models yet.
— God of Prompt (@godofprompt) 17 avril 2025
O3 and O4-mini don’t just answer they think, reason, and act.
They now choose how and when to use tools like code, search, and images.
Here's why this changes everything about what ChatGPT can do: pic.twitter.com/62pNUcwrsPBreaking: OpenAI just dropped its smartest models yet. O3 and O4-mini don’t just answer they think, reason, and act. They now choose how and when to use tools like code, search, and images. Here's why this changes everything about what ChatGPT can do:
-
AI Empire: Understanding Global Perspectives on Technology
By
–
In the end, my hope is anyone reading the book will gain both expansive breadth and depth, be able to step into the shoes of people from all corners of the world and see the empire of AI through them. 8/
-
Global reporting journey across five continents for OpenAI book
By
–
As a result, I traveled to five continents for my reporting. Between taking you within OpenAI's walls, the book also brings you to places like some of the most impoverished neighborhoods in Nairobi, Kenya and to the Atacama Desert in Chile, the driest place on earth. 6/