Emergent temporal abstractions in autoregressive models enable hierarchical reinforcement learning Paper • 2512.20605 • Published 6 days ago • 53
VA-π: Variational Policy Alignment for Pixel-Aware Autoregressive Generation Paper • 2512.19680 • Published 7 days ago • 7
Spatia: Video Generation with Updatable Spatial Memory Paper • 2512.15716 • Published 12 days ago • 24
view article Article cua-bench: A Framework for Benchmarking, Training Data, and RL Environments for Computer-Use Agents 13 days ago • 9
Bottom-up Policy Optimization: Your Language Model Policy Secretly Contains Internal Policies Paper • 2512.19673 • Published 7 days ago • 60
DeContext as Defense: Safe Image Editing in Diffusion Transformers Paper • 2512.16625 • Published 11 days ago • 24
Qwen-Image-Layered: Towards Inherent Editability via Layer Decomposition Paper • 2512.15603 • Published 12 days ago • 56
Depth Any Panoramas: A Foundation Model for Panoramic Depth Estimation Paper • 2512.16913 • Published 11 days ago • 33