GAE: Learning a Geometry-Native Latent Space for 3D-Consistent World Generation Paper • 2609.24981 • Published 4 days ago • 43
GameHorizon Suite: Multi-Horizon Data and Evaluation in Gameplay Paper • 2609.25001 • Published 4 days ago • 126
WorldCrafter: Consistent Video World Model with Implicit 3D-aware Memory Paper • 2609.24984 • Published 4 days ago • 141
History-Aware Transformation of ReID Features for Multiple Object Tracking Paper • 2503.12562 • Published Mar 16, 2025 • 1
TimeLens2: Generalist Video Temporal Grounding with Multimodal LLMs Paper • 2607.17423 • Published Jul 19 • 98
UniDDT: Unifying Multimodal Understanding and Generation with Decoupled Diffusion Transformer Paper • 2606.16255 • Published Jun 15 • 15
Representation Forcing for Bottleneck-Free Unified Multimodal Models Paper • 2605.31604 • Published May 29 • 62
DeCo: Frequency-Decoupled Pixel Diffusion for End-to-End Image Generation Paper • 2511.19365 • Published Nov 24, 2025 • 66
MeMOTR: Long-Term Memory-Augmented Transformer for Multi-Object Tracking Paper • 2307.15700 • Published Jul 28, 2023 • 2