The Prism Hypothesis: Harmonizing Semantic and Pixel Representations via Unified Autoencoding Paper • 2512.19693 • Published 12 days ago • 61
The Quest for Generalizable Motion Generation: Data, Model, and Evaluation Paper • 2510.26794 • Published Oct 30, 2025 • 26
T2I-ReasonBench: Benchmarking Reasoning-Informed Text-to-Image Generation Paper • 2508.17472 • Published Aug 24, 2025 • 26
LongVie: Multimodal-Guided Controllable Ultra-Long Video Generation Paper • 2508.03694 • Published Aug 5, 2025 • 51