4 papers · 1 filter
CRAFT: Cost-aware Refinement And Front-aware Tuning of Prompts
Shanu Kumar, Shubhanshu Khandelwal, Akhila Yesantarao Venkata +3
Prompts tuned for accuracy often grow long, raising inference cost on every model call. The best accuracy-cost trade-off depends on the task and the budget, so prompt optimization…
CONCAP: Seeing Beyond English with Concepts Retrieval-Augmented Captioning
George Ibrahim, Rita Ramos, Yova Kementchedjhieva
Multilingual vision-language models have made significant strides in image captioning, yet they still lag behind their English counterparts due to limited multilingual training dat…
Overcoming Vocabulary Constraints with Pixel-level Fallback
Jonas F. Lotz, Hendra Setiawan, Stephan Peitz +1
Subword tokenization requires balancing computational efficiency and vocabulary coverage, which often leads to suboptimal performance on languages and scripts not prioritized durin…
JEEM: Vision-Language Understanding in Four Arabic Dialects
Karima Kadaoui, Hanin Atwany, Hamdan Al-Ali +7
We introduce JEEM, a benchmark designed to evaluate Vision-Language Models (VLMs) on visual understanding across four Arabic-speaking countries: Jordan, The Emirates, Egypt, and Mo…