Diogo Glória-Silva

Specialized multilingual data outperforms model size in enhancing OCR performance for European Portuguese, revealing critical insights for future benchmarks.

European Portuguese finally gets its own dedicated vision and language model, setting a new standard for inclusivity in multimodal AI.

Most LLMs exhibit a strong bias towards Brazilian Portuguese, highlighting a critical gap in multilingual representation that could affect communication equity.

Finally, a multimodal dialogue model that doesn't just talk about instructional videos, but actually understands and reasons about the visual steps involved, blowing away previous text-only approaches.