d3 Decision Model
Typed decisions with probabilities from vllm-sr/d3
None defined yet.
Typed decisions with probabilities from vllm-sr/d3
Typed decisions with a probability for every option
Typed decisions with a probability for every option
Pose-free feed-forward 3D object removal
Predict human DNA from ~100 vertebrate homologs
First frame + caption to 4s video via physical language
Gestalt unified multimodal discrete diffusion, text-to-image
Binaural audio-language model with spatial awareness
Unlearned on Dijkstra — can it reinvent the algorithm?
Multi-reference image-grounded video captioning
Same prompt, many seeds - diversity LoRA for Krea 2 Turbo
Text-to-3D human motion with NVIDIA ARDY + root waypoints
Forecast LEO satellite orbits from TLE history
Typed decisions with a probability for every option
Streaming Arabic speech-to-text (MSA + dialects)
Multimodal typed decisions with probabilities from Clef-Omni
Tiny 21M Brazilian Portuguese TTS — 48 kHz, offline
8-step text-to-image and editing with Qwen-Image-2.1-Turbo
Erase a person from a video clip with MiniMax-H3
Ground desktop UI elements from a screenshot and task.
Reshoot any photo from a new angle with a 3D camera
Natural-language ship-hull design decisions on KVLCC2
Option probabilities read after every thinking loop
Analyze robot manipulation videos for failures