Type a name, or just describe what you need. Results blend keyword and meaning-based search. 13 matches, each with an EU availability status.
Model · Nvidia
Nvidia research model that understands and generates images and video directly in pixel space, with no VAE or vision encoder.
Model
Unified motion-language model for text-to-motion, motion captioning, completion and editing, from HKUST and Tencent Games.
Model · ByteDance
ByteDance research model unifying image and video understanding, generation and editing in a 3B active-parameter network.
Model · Tencent
Tencent's unified multimodal model for 3D understanding, text-to-3D generation, instruction-based editing and part generation.
Model · inclusionAI
Open-weights 6B unified text-to-image and instruction-based image editing model family from inclusionAI.
Hardware · Xiaomi
Prototype compact desktop AI computer from Xiaomi with 80GB unified memory for running large models locally.
Hardware · Apple
Apple's compact desktop workstation with M5 Max or M5 Ultra chips and up to 512GB unified memory for local AI and pro work.
Apple's M6 and M5 Ultra chips for Mac mini and Mac Studio, with up to 512 GB unified memory for AI workloads.
App · Rivian
In-vehicle voice assistant for Rivian R1 vehicles, built on Rivian Unified Intelligence, with agentic integrations.
Model · Unitree
Unitree's 6B-parameter vision-language-action foundation model for humanoid robots, covering 64 tabletop and whole-body tasks.
Action-conditioned robotics world model fine-tuned from Cosmos-Predict2.5-2B using 2D skeleton conditioning across embodiments.
Research framework that conditions one video world model on force, camera, hand pose and robot pose actions.
Research
Research framework that retargets human motion to humanoid robots using learned point cloud correspondences.
