Tag
A user demonstrates using OpenAI's Codex to automatically generate a Colab notebook that trains a ~10 million parameter transformer in JAX/Flax/Optax on addition, achieving high accuracy after 4000 steps on a T4 GPU.
Google Research releases TimesFM 2.5, an open-source time-series foundation model for forecasting, with 200M parameters, 16k context length, and support for quantile forecasts up to 1k horizon. The model is available on PyPI and Hugging Face, with fine-tuning via LoRA and integration into Google products like BigQuery ML, Google Sheets, and Vertex Model Garden.