This week join Jason Ren of Ai2 (Allen Institute for AI) for MolmoMotion: Forecasting Point Trajectories in 3D with Language Instruction, a live look at how open multimodal models move past describing a scene to predicting where things go next. Building on the Molmo family’s pointing and tracking capabilities, MolmoMotion takes a plain-language instruction and forecasts point trajectories through 3D space, so the model answers by showing exactly where and when motion will happen. Expect live demos, a walk through the training data and recipe, and a discussion of what this opens up for robotics, video understanding, and embodied agents — plus open Q&A with the audience.
Join our live stream and stick around for our giveaway of a free OpenCV University course to one lucky viewer.
- Watch on Patreon (DRM-Free, Ad-Free!)
- Watch on YouTube
- Watch on Apple Podcasts
- Watch on LinkedIn
- Watch on Zoom
- Watch on Twitch
Got a cool project of your own? Send it to us and you may be featured on a future episode.
The post MolmoMotion: Forecasting Point Trajectories in 3D with Language Instruction – OpenCV Live! 221 appeared first on OpenCV.