arXiv ·
MBZUAI releases Bactrian-X, a multilingual parallel dataset of 3.4 million instruction-response pairs across 52 languages. They trained low-rank adaptation (LoRA) adapters using this dataset, creating lightweight, replaceable components for large language models. Experiments show the LoRA-based models outperform vanilla and existing instruction-tuned models in multilingual settings.
MBZUAI ·
MBZUAI researchers created Bactrian-X, a new dataset to improve LLM instruction following in low-resource languages. The dataset leverages instruction tuning, pairing instructions in various languages with expected responses. Bactrian-X builds upon existing open-source instruction tuning models. Why it matters: This work aims to democratize access to LLMs by enabling users to interact with them in their native languages, even when English proficiency is limited.
KAUST ·
KAUST's Beacon Development (KBD) is a key partner in the Heart of Arabia expedition, retracing a 750-mile journey across Saudi Arabia. The expedition aims to advance human performance understanding in extreme environments and deepen knowledge of pre-Islamic history and local biodiversity. KBD's Terrestrial Ecology and Conservation team is advising the field science component, providing equipment and expertise for data collection. Why it matters: This partnership highlights KAUST's commitment to environmental research and historical exploration, contributing to a deeper understanding of Saudi Arabia's natural and cultural heritage.
KAUST ·
KAUST's Women to Impact (WTI) initiative announced the winners of its Resilience Challenge, a global competition seeking tech-based solutions for building resilience in local ecosystems. The challenge, sponsored by SEDCO Holding, was part of KAUST's Winter Enrichment Program. First place went to AI-AMRS for their AI-based solution to antimicrobial resistance, while second and third place went to SandX/BiocharX for aridland agriculture and takeAbreath for stress management respectively. Why it matters: The challenge highlights KAUST's commitment to fostering innovation and supporting women in STEM, while addressing pressing global issues like climate change, food security, and health.
arXiv ·
MBZUAI introduces Agent-X, a benchmark for evaluating multi-step reasoning in vision-centric agents across real-world, multimodal settings. Agent-X includes 828 tasks with diverse visual contexts and spans six environments, requiring tool use and stepwise decision-making. Experiments show that current LLMs struggle with multi-step vision tasks, achieving less than 50% success, highlighting areas for improvement in LMM reasoning and tool use.