MolmoMotion: Forecasting Point Trajectories in 3D with Language Instruction Paper • 2606.18558 • Published 3 days ago • 41
PAIWorld: A 3D-Consistent World Foundation Model for Robotic Manipulation Paper • 2606.18375 • Published 4 days ago • 6
ViT-Up: Faithful Feature Upsampling for Vision Transformers Paper • 2606.14024 • Published 8 days ago • 6
DreamX-World 1.0: A General-Purpose Interactive World Model Paper • 2606.16993 • Published 5 days ago • 101
Skip a Layer or Loop It? Learning Program-of-Layers in LLMs Paper • 2606.06574 • Published 16 days ago • 22
Next Forcing: Causal World Modeling with Multi-Chunk Prediction Paper • 2606.11187 • Published 11 days ago • 6
WorldOlympiad: Can Your World Model Survive a Triathlon? Paper • 2606.11129 • Published 11 days ago • 31
MilliVid: Hierarchical Latents for Long-Range Consistency in Video Generation Paper • 2606.09056 • Published 12 days ago • 6
minWM: A Full-Stack Open-Source Framework for Real-Time Interactive Video World Models Paper • 2605.30263 • Published 23 days ago • 58
Do Enterprise Systems Need Learned World Models? The Importance of Context to Infer Dynamics Paper • 2605.12178 • Published May 12 • 63
When to Trust Imagination: Adaptive Action Execution for World Action Models Paper • 2605.06222 • Published May 7 • 44
End-to-End Autoregressive Image Generation with 1D Semantic Tokenizer Paper • 2605.00503 • Published May 1 • 12