MBZUAI researchers developed LetBabyTalk, an AI-powered multilingual parenting app that analyzes baby cries to identify needs like hunger or sleepiness. The app is trained on over 1,000 baby cries and uses supervised machine learning with input from experienced parents and educators. Cradle AI, the startup behind the app, aims to bridge the gap between advanced AI research and real-world solutions, focusing on family care and education. Why it matters: This project demonstrates the potential of AI to address everyday challenges and improve the lives of families in the region and globally, while also showcasing MBZUAI's focus on AI for social good.
The article discusses the rise of large language models like ChatGPT and Gemini. It highlights their role in driving the first wave of AI development. Why it matters: While lacking specifics, the article suggests ongoing interest in the impact and future of LLMs, a key area of AI research and development.
The Qatar Computing Research Institute (QCRI) has released SpokenNativQA, a multilingual spoken question-answering dataset for evaluating LLMs in conversational settings. The dataset contains 33,000 naturally spoken questions and answers across multiple languages, including low-resource and dialect-rich languages. It aims to address the limitations of text-based QA datasets by incorporating speech variability, accents, and linguistic diversity. Why it matters: This benchmark enables more robust evaluation of LLMs in speech-based interactions, particularly for Arabic dialects and other low-resource languages.
MBZUAI researchers introduce LLM-BabyBench, a benchmark suite for evaluating grounded planning and reasoning in LLMs. The suite, built on a textual adaptation of the BabyAI grid world, assesses LLMs on predicting action consequences, generating action sequences, and decomposing instructions. Datasets, evaluation harness, and metrics are publicly available to facilitate reproducible assessment.
MBZUAI researchers introduce LLMVoX, a 30M-parameter, LLM-agnostic, autoregressive streaming text-to-speech (TTS) system that generates high-quality speech with low latency. The system preserves the capabilities of the base LLM and achieves a lower Word Error Rate compared to speech-enabled LLMs. LLMVoX supports seamless, infinite-length dialogues and generalizes to new languages with dataset adaptation, including Arabic.
A new benchmark, LongShOTBench, is introduced for evaluating multimodal reasoning and tool use in long videos, featuring open-ended questions and diagnostic rubrics. The benchmark addresses the limitations of existing datasets by combining temporal length and multimodal richness, using human-validated samples. LongShOTAgent, an agentic system, is also presented for analyzing long videos, with both the benchmark and agent demonstrating the challenges faced by state-of-the-art MLLMs.