Hear the World in Stereo: Learning Dynamic Spatial Correspondence for Immersive Joint Video-Audio Generation Paper • 2609.38748 • Published 8 days ago • 65
Chaos in the Text: Revealing the Modality Preference in Mixed-Modality Retrievers Paper • 2610.11816 • Published 8 days ago • 15
AdSpark: A Large-Scale Dataset and Benchmark for Product-Centric Advertisement Video Generation Paper • 2610.10047 • Published 9 days ago • 21
HypoEvolve: Genetic Algorithms Enable Multi-Agent LLMs to Discover Scientific Hypotheses Paper • 2609.15938 • Published Sep 14 • 31
Puffin-World: Scaling a Unified Multimodal Model with Native 3D World States Paper • 2609.04196 • Published Sep 3 • 71
LLaDA-Image: Building Strong Image Generators with Fully Open Training Recipes Paper • 2609.03796 • Published Sep 3 • 183
4DAnyone: Create Anyone in 4D from a Casual Monocular Video Paper • 2608.20335 • Published Aug 20 • 89
FM-Bench: A Benchmark for Long-Horizon Management with Competing Agents Paper • 2608.18423 • Published Aug 19 • 21