{"type":"rich","version":"1.0","provider_name":"Transistor","provider_url":"https://transistor.fm","author_name":"Jiggly Jar","title":"DreamZero: World Action Models as Zero-Shot Robotic Policies","html":"<iframe width=\"100%\" height=\"180\" frameborder=\"no\" scrolling=\"no\" seamless src=\"https://share.transistor.fm/e/0c7d8cf4\"></iframe>","width":"100%","height":180,"duration":1636,"description":"Introduces World Action Models (WAMs) that jointly predict video and actions via a 14B-parameter autoregressive diffusion model, enabling state-of-the-art zero-shot generalization on manipulation benchmarks like MolmoSpaces and RoboArena through emergent internal world modeling.","thumbnail_url":"https://img.transistorcdn.com/VWvjo5LNHt0jVXjsQyqmBgllLFwydS3vycw2FisL51I/rs:fill:0:0:1/w:400/h:400/q:60/mb:500000/aHR0cHM6Ly9pbWct/dXBsb2FkLXByb2R1/Y3Rpb24udHJhbnNp/c3Rvci5mbS8xMGQ3/ZjVhZjJjNTFjMTll/YmM4YTZjMDAxYjRk/Y2YxZi5qcGVn.webp","thumbnail_width":300,"thumbnail_height":300}