Delineate Anything v2: A Global Foundation Model for Field Delineation Paper • 2607.19069 • Published 25 days ago • 6
AlayaWorld: Interactive Long-Horizon World Modeling -- Full Technical Report Paper • 2607.18367 • Published 25 days ago • 60
From Pixels to States: Rethinking Interactive World Models as Game Engines Paper • 2607.14076 • Published about 1 month ago • 37
Vinci2: Providing Proactive Assistance in Continuous Egocentric Videos Paper • 2607.11523 • Published Jul 13 • 13
SAM-MT: Real-Time Interactive Multi-Target Video Segmentation Paper • 2607.08688 • Published Jul 9 • 9
KVpop -- Key-Value Cache Compression with Predictive Online Pruning Paper • 2607.05061 • Published Jul 6 • 24
AgenticSTS: A Bounded-Memory Testbed for Long-Horizon LLM Agents Paper • 2607.02255 • Published Jul 2 • 68
OcclusionFormer: Arranging Z-Order for Layout-Grounded Image Generation Paper • 2605.21343 • Published May 20 • 8
PanoWorld: Towards Spatial Supersensing in 360^circ Panorama World Paper • 2605.13169 • Published May 13 • 21
AnyFlow: Any-Step Video Diffusion Model with On-Policy Flow Map Distillation Paper • 2605.13724 • Published May 13 • 105
Beyond the Last Layer: Multi-Layer Representation Fusion for Visual Tokenization Paper • 2605.10780 • Published May 12 • 33