Sci-VBench: Evaluating Knowledge- and Reasoning-Intensive Video Generation in Science Domains Paper • 2608.09873 • Published 6 days ago • 29
UEmbed: Unified Sparse and Dense Multimodal Embeddings Paper • 2608.02583 • Published 13 days ago • 50
TexOCR: Advancing Document OCR Models for Compilable Page-to-LaTeX Reconstruction Paper • 2604.22880 • Published Apr 24 • 10
VideoKR: Towards Knowledge- and Reasoning-Intensive Video Understanding Paper • 2606.05259 • Published Jun 3 • 39
Is This Edit Correct? A Multi-Dimensional Benchmark for Reasoning-Aware Image Editing Paper • 2606.05172 • Published Apr 16 • 1
VideoKR: Towards Knowledge- and Reasoning-Intensive Video Understanding Paper • 2606.05259 • Published Jun 3 • 39