Linum v2
PulseAugur coverage of Linum v2 — every cluster mentioning Linum v2 across labs, papers, and developer communities, ranked by signal.
2 day(s) with sentiment data
-
New text-to-image models leverage combined rewards and efficient architectures
Researchers have developed new methods for training text-to-image models. One approach combines human preference data with rubric-based rewards to improve prompt adherence and aesthetic quality, leading to models like I…
-
New JiT-DDT architecture trains text-to-image models 3.6x faster
Researchers have developed JiT-DDT, a novel architecture that significantly accelerates the training of text-to-image diffusion models. By unifying the compression and generation modules into a single model, JiT-DDT ach…
-
Linum-AI releases 2B parameter text-to-video model
Linum-AI, a startup founded by two brothers, has released Linum v2, a text-to-video model with 2 billion parameters. The model is available in 360p and 720p resolutions, capable of generating videos between 2 to 5 secon…