Robots need many different ways to grab things, just like people use pinch, tripod, whole-hand, or two hands together.
FireRed-OCR turns a general vision-language model into a careful document reader that follows strict rules, so its outputs are usable in the real world.
ExStrucTiny is a new test (benchmark) that checks if AI can pull many connected facts from all kinds of documents and neatly put them into JSON, even when the question style and schema change.
The paper builds a new way to create realistic, long conversations between people and AI that use tools like databases.
Solar Open is a giant bilingual AI (102 billion parameters) that focuses on helping underserved languages like Korean catch up with English-level AI quality.
X-Coder shows that models can learn expert-level competitive programming using data that is 100% synthetic—no real contest problems needed.
DataFlow is a building-block system that helps large language models get better data by unifying how we create, clean, check, and organize that data.
VOYAGER is a training-free way to make large language models (LLMs) create data that is truly different, not just slightly reworded.
The paper introduces M3DR, a way for computers to find the right document image no matter which of 22 languages the query or the document uses.