Type a name, or just describe what you need. Results blend keyword and meaning-based search. 9 matches, each with an EU availability status.
Research
Post-training method that refines feed-forward 3D reconstruction models (Pi3, DA3, VGGT) on unlabeled video.
Model · Sperid Labs
Open 3B-parameter text-to-image flow-matching model that generates directly in pixel space, without a VAE.
Research · OpenAI
Reported OpenAI training technique that reuses the same transformer layers repeatedly, reasoning in latent space.
Model
Image-based model that predicts depth maps, surface normals and albedo from a single regular image.
Model · Google
Predicts depth, surface normals and sky masks from a single 360° panorama using a cubemap-adapted 3D foundation model.
Research autoencoder with a geometry-native latent space for 3D-consistent video and world generation.
Research framework for globally consistent 3D reconstruction from long RGB videos using chunked priors and test-time adaptation.
Model · Alibaba
Alibaba's open-weights 2.4T-parameter MoE language model (95B active) from the Qwen3.8 family, with a hosted Max version.
Model · Moonshot AI
Moonshot AI's Kimi K3 model family, with K3.1 Pro as the current release in the Kimi app and API.
