ZimaBlue: Evolving Generalizable World Action Models through Scalable Video Pre-training Paper • 2609.00188 • Published 6 days ago • 50
Beyond Data Scaling: Representation-Centric Continued Pre-training for Vision-Language-Action Models Paper • 2608.27550 • Published 10 days ago • 91
SpatialWorld: Benchmarking Interactive Spatial Reasoning of Multimodal Agents in Real-World Tasks Paper • 2606.09669 • Published Jun 8 • 49
π-Bench: Evaluating Proactive Personal Assistant Agents in Long-Horizon Workflows Paper • 2605.14678 • Published May 19 • 109
TextLDM: Language Modeling with Continuous Latent Diffusion Paper • 2605.07748 • Published May 8 • 26
OpenSpatial: A Principled Data Engine for Empowering Spatial Intelligence Paper • 2604.07296 • Published Apr 8 • 40
V-Bridge: Bridging Video Generative Priors to Versatile Few-shot Image Restoration Paper • 2603.13089 • Published Mar 13 • 13
V-Bridge: Bridging Video Generative Priors to Versatile Few-shot Image Restoration Paper • 2603.13089 • Published Mar 13 • 13
V-Bridge: Bridging Video Generative Priors to Versatile Few-shot Image Restoration Paper • 2603.13089 • Published Mar 13 • 13
P1: Mastering Physics Olympiads with Reinforcement Learning Paper • 2511.13612 • Published Nov 17, 2025 • 135