DataFlex: A Unified Framework for Data-Centric Dynamic Training of Large Language Models Paper • 2603.26164 • Published 13 days ago • 245
Speed by Simplicity: A Single-Stream Architecture for Fast Audio-Video Generative Foundation Model Paper • 2603.21986 • Published 17 days ago • 121
Gemma 4 Collection Gemma 4 is Google's new model family including including E2B, E4B, 26B-A4B, and 31B. • 25 items • Updated 2 days ago • 104
FIPO: Eliciting Deep Reasoning with Future-KL Influenced Policy Optimization Paper • 2603.19835 • Published 20 days ago • 326
TimesFM Release Collection TimesFM (Time Series Foundation Model) is a pretrained time-series foundation model developed by Google Research for time-series forecasting. • 7 items • Updated 28 days ago • 43
EdgeCrafter: Compact ViTs for Edge Dense Prediction via Task-Specialized Distillation Paper • 2603.18739 • Published 21 days ago • 11
view article Article How I contributed a new model to the Transformers library using Codex 10 days ago • 42
LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels Paper • 2603.19312 • Published 26 days ago • 24
view article Article Nemotron 3 Nano 4B: A Compact Hybrid Model for Efficient Local AI 22 days ago • 61