MET-D Multilingual Ethics
Theory-grounded culture-aware multilingual moral reasoning
None defined yet.
Theory-grounded culture-aware multilingual moral reasoning
Remote sensing text-to-image with SHARP resolution promotion
Unified text and formula recognition with 0.1B params
Audio-text LLM β transcribe, translate & describe audio
Compact multilingual ASR model (324M params)
8-step distilled text-to-image model by fal
Audio MoE LLM for audio QA, ASR, and temporal grounding
Multilingual speech recognition (RU, EN, KK, KY, UZ)
Multi-modal omni-task vision model demo
Extract flat albedo maps from textures with FLUX.2 Klein
DM0.5 VLA β predict robot actions from images + text
Krea-2 Turbo with adjustable prompt-adherence LoRA
Controllable image-to-video with Giga-World-1
20-step Ideogram 4 Fast text-to-image by fal
SupraCMA-8M Channel-Mixing Attention language model
Kairos 4B world-action model for robot video generation
Parse document images into Markdown with OvisOCR2
Real-time one-step generative video restoration
Fast fp8 still-to-cinemagraph (LTX-2.3-22B LoRA)
Predict metric 3D robot trajectories from RGB-D + language
Exemplar-based portrait photo retouching
Still image to looping cinemagraph (LTX-2.3-22B LoRA)
Scientific multimodal model for RNA/DNA/protein/molecules
4D world model β synced RGB, depth & optical-flow video