Type a name, or just describe what you need. Results blend keyword and meaning-based search. 18 matches, each with an EU availability status.
Research
Research video world model that reasons in a learned discrete "physical language" before rendering video.
Model
Streaming real-world video super-resolution using sparse large-model keyframes and a lightweight propagation network.
Diffusion framework that learns text-to-3D human motion generation from 2D poses extracted from monocular videos.
Research model that turns a pretrained video diffusion model into a latent action learner for human-to-robot motion transfer.
Research method that turns a single photo or video into a simulation-ready 3D scene for robot reinforcement learning.
Model · Skild AI
Skild AI's robotic foundation model that performs new tasks from a single video demonstration, with no fine-tuning.
Research framework letting a frozen VLM agent learn robot tasks in context from videos, images and feedback, no fine-tuning.
Research · Google
Google DeepMind research demo in which a Gemini-based robot learned to play cornhole from first-person videos and practice.
Monocular video motion capture that combines flow matching with physics-based RL for plausible 3D human motion.
Model · Dyna Robotics
World-action model from Dyna Robotics pre-trained on over 1 million hours of egocentric human video for robot manipulation.
Model · Alibaba
Research method for instruction-based video editing by repurposing Qwen-Image-Edit with Wan 2.1 video latents.
App · Steve Aoki
Early-access AI video editing app from Steve Aoki and a partner that learns a creator's editing taste.
Single-step GRPO training framework for aligning video diffusion models with human preferences, tested on Wan2.1 1.3B–14B.
Model · Adobe
Adobe Research video world model that builds navigable interactive worlds from an image or video at 16 FPS.
Research video generation framework that keeps scenes consistent after edits using RGB and depth context memory banks.
Hybrid softmax and linear attention variant of MiniMax H3 for faster long video generation, from UC Berkeley and Impossible, Inc.
Model · JD
Open-weights 16B autoregressive diffusion model from JD for real-time, instruction-guided editing of streaming video.
Research framework for real-time, causal streaming video editing with diffusion, running at about 12.66 FPS.
