[177] Fine-grained Image Captioning with CLIP Reward

2024λ…„ 9μ›” 6일 Β· 2 λΆ„ Β· long8v Β· 

[160] ALOHa: A New Measure for Hallucination in Captioning Models

2024λ…„ 6μ›” 15일 Β· 2 λΆ„ Β· long8v Β·