Early-Exit and Instant Confidence Translation Quality Estimation Paper • 2502.14429 • Published 5 days ago • 2 • 2
How to Select Datapoints for Efficient Human Evaluation of NLG Models? Paper • 2501.18251 • Published 26 days ago • 2 • 1
Tuning Timestep-Distilled Diffusion Model Using Pairwise Sample Optimization Paper • 2410.03190 • Published Oct 4, 2024 • 1
KITAB-Bench: A Comprehensive Multi-Domain Benchmark for Arabic OCR and Document Understanding Paper • 2502.14949 • Published 5 days ago • 6 • 2
Evaluating Multimodal Generative AI with Korean Educational Standards Paper • 2502.15422 • Published 4 days ago • 8 • 3