ReactVAU: A Slow-Fast Decoupled Framework for Streaming Video Anomaly Understanding Paper • 2609.07941 • Published 4 days ago • 15
VidaForge: Open Research Infrastructure for Video Pretraining Data Recipes Paper • 2609.06652 • Published 5 days ago • 18
CORE: Improving Compositional Reasoning in MLLM Embedding via Reranker Distillation Paper • 2609.04083 • Published 8 days ago • 26