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.
Representation Guidance lets a 459M pixel diffusion model beat larger transformers, with FID 1.55.
UniEvo-VL self-distills multimodal models from their own critiques, raising Qwen-Image GenEval scores.
RWTD post-trains one-step generators, raising SANA Sprint GenEval from 0.73 to 0.80.
Today 804 readers · 879 views · 84 reads · all time 215K views