João Magalhães

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.

Diminishing returns in parallel sampling can be overcome by generating diverse initial queries, leading to substantial performance gains in multi-hop question answering.

Recycling zero-variance queries during training can boost model performance, enabling a smaller 1.7B parameter model to match or exceed the accuracy of larger counterparts.