Microsoft AI just released Phi-4: a small language model available on Hugging Face under the MIT license
Microsoft has released Phi-4, a compact and efficient small language model, on Hugging Face under the MIT license. This decision ...
Tag: model
Princeton University Researchers Introduce Metadata Conditioning Then Cooling (MeCo) to Simplify and Optimize Language Model Pre-Training
Pre-training language models (LMs) plays a crucial role in enabling their ability to understand and generate text. However, a major ...
USC and Prime Intellect researchers released METAGENE-1: a 7B-parameter autoregressive transformer model trained on over 1.5 T of DNA and RNA base pairs
At a time when global health faces persistent threats from emerging pandemics, the need for advanced biosurveillance and pathogen detection ...
NVIDIA AI Unveils Cosmos World Foundation Model (WFM) Platform to Advance Physics AI Development
The development of physics ai – ai systems designed to simulate, predict and optimize real-world physics – has long been ...
VITA-1.5: A multimodal large language model that integrates vision, language and speech through a carefully designed three-stage training methodology
The development of multimodal large language models (MLLM) has provided new opportunities in artificial intelligence. However, significant challenges remain in ...
Graph Generative Pretrained Transformer (G2PT): An autoregressive model designed to learn graph structures by predicting the next token
Graph generation is an important task in several fields, including molecular design and social network analysis, due to its ability ...
Journey to the Full-Stack Data Scientist: Model Deployment | by Alex Davis | January 2025
First, for our example, we need to develop a model. Since this article focuses on the implementation of the model, ...
OLMo 2: fully open source basic model
OLMo 2 models are Ai2's fully open source language models. They have dense autoregressive architectures with optimized training, pre-training data ...
ProTrek: a trimodal protein language model to advance sequence-structure-function analysis
Proteins, the essential molecular machinery of life, play a central role in numerous biological processes. Decoding its intricate sequence, structure, ...
A new computational model can predict the structures of antibodies with greater precision | MIT News
<img src="https://news.mit.edu/sites/default/files/styles/news_article__cover_image__original/public/images/202501/MIT-Antibodies-ai-01_0.jpg?itok=Y9SPR7l6" /> By adapting artificial intelligence models known as big language models, researchers have made great strides in their ...
Recommended.
