oruk-loop-153M
English ASR with a looped transformer (153M params)
None defined yet.
English ASR with a looped transformer (153M params)
Calibrated yes/no, choice and score answers on images
Streaming multilingual TTS with zero-shot voice cloning
Simultaneous Chinese⇄English speech translation
Expressive Turkish TTS with a 32-expert Drama 3 speaker
Simultaneous English⇄Chinese speech translation
Agentic GUI grounding that zooms in with crops
Locally controllable 3D generation from primitives
Zero-shot English TTS and voice conversion, 33.6M params
Portrait to talking digital human with native audio
Vietnamese text recognition with a 10.65M-param CTC model
Interactive text + camera controlled video world model
Coarse-mask local editing with dual-path FLUX.2 Klein 9B
Image-to-3D part-level generation with variable granularity
Textureless city mesh to street views and 3D Gaussians
Step into a live, steerable generated world
MOSS-Image 5B finetune with 57 anime/furry artist styles
Document decisions with per-candidate probabilities
Chat with a 1B sparse mixture-of-experts instruct model
Image to high-res 3D mesh with Hi3Dv1 refinement
Blockout gameplay clips re-rendered as polished game video
Solve visual jigsaw puzzles via latent visual reasoning
Grounding, detection, OCR, segmentation & matting in one VLM
Detect, ground, count, OCR, segment & matte with one VLM