LLM AutoML searcher jointly tunes architecture, hyperparameters, and data
Trained on one vision task, the searcher reports a 0.91 GenEval score after 896 GPU-days on a billion-parameter Diffusion Transformer.
4 stories, newest first · one card per story
Trained on one vision task, the searcher reports a 0.91 GenEval score after 896 GPU-days on a billion-parameter Diffusion Transformer.
Architecture search yields a 409-parameter Sentinel-2 bloom model, lifting AUC to 0.820.
Study tests adversarial training against label-flip and noise poisoning of streaming AutoML models for IoT.
TabFM, a 400M tabular foundation model, delivers calibrated zero-shot predictions that beat tuned AutoML.
Today 793 readers · 868 views · 84 reads · all time 215K views