3. Minimize cross-entropy loss between predicted and actual next tokens. (This is equivalent to trying to minimize encoding length.) ViT don't have quantization baked into the algorithm, but NNs are being moved towards quantization in general. ----- I think it's pretty interesting how closely related generation and compression are. ClosedAI's Sora[^1] model uses a denoising vision transformer, and is the... - Source: Hacker News / about 2 months ago

Did you miss the fish?[0] You should see the error in first viewing What about the woman with glasses? Her face literally "jumps"[1] Same with this guy's hands[2] Interesting, we notice that [1] has "sora" in the name though I think it is a reference to the main image on sora[3] Not sure if the gallery is weird to anyone else, but it doesn't exactly show new images and the position indicator is wonky. The thing... - Source: Hacker News / about 2 months ago

As an architect, I've experienced firsthand the challenges of visualizing design ideas and the time-consuming process of creating 3D models using tools like 3ds Max or Vray. That's why we developed VisualizeAI - an app that enables architects, interior designers, and hobbyists to upload room images or sketches and receive instant renders in their desired style. In 3 months since its launch, we've reached a... Source: about 1 year ago