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.
Researchers at MBZUAI introduce "Interactive Video Reasoning," a new paradigm enabling models to actively "think with videos" by performing iterative visual actions to gather and refine evidence. They developed Video CoM, which reasons through a Chain of Manipulations (CoM), and constructed Video CoM Instruct, an 18K instruction tuning dataset for multi-step manipulation reasoning. The model is further optimized via reinforcement learning with reasoning aware Group Relative Policy Optimization (GRPO), achieving strong results across nine video reasoning benchmarks.
MBZUAI researchers have introduced MIRA, a novel framework for improving the factual accuracy of multimodal large language models in medical applications. MIRA uses calibrated retrieval to manage factual risk and integrates image embeddings with a medical knowledge base for efficient reasoning. Evaluated on medical VQA and report generation benchmarks, MIRA achieves state-of-the-art results, with code available on GitHub.
MBZUAI researchers introduce Web2Code, a new large-scale dataset and evaluation framework for training and benchmarking multimodal LLMs on webpage understanding and HTML code generation. The dataset includes webpage images, HTML code, and QA pairs about webpage content. Experiments demonstrate the dataset's utility in webpage understanding, code generation, and general visual domain tasks, with code and data available on Github.
The paper introduces MedPromptX, a clinical decision support system using multimodal large language models (MLLMs), few-shot prompting (FP), and visual grounding (VG) for chest X-ray diagnosis, integrating imagery with EHR data. MedPromptX refines few-shot data dynamically for real-time adjustment to new patient scenarios and narrows the search area in X-ray images. The study introduces MedPromptX-VQA, a new visual question answering dataset, and demonstrates state-of-the-art performance with an 11% improvement in F1-score compared to baselines.
MBZUAI researchers have introduced SURPRISE3D, a benchmark for evaluating 3D spatial reasoning in AI systems, along with a 3D Spatial Reasoning Segmentation (3D-SRS) task. The benchmark includes over 900 indoor scenes and 200,000 language queries paired with 3D masks, emphasizing spatial relationships over object naming. A companion paper, MLLM-For3D, explores adapting 2D multimodal LLMs for 3D reasoning. Why it matters: This work addresses a key limitation in current AI, pushing towards embodied AI that can understand and act in 3D environments based on human-like spatial reasoning.
MBZUAI graduates Abdulla and Abdulrahman Almarzooqi are developing AI systems to improve UAE road safety. Abdulla's research focuses on external highway monitoring using MLLMs to analyze driving scenes and generate accident reports, while Abdulrahman's work uses in-cabin sensors to detect driver fatigue and distractions. Together, their systems aim to create a comprehensive view of factors influencing traffic accidents, with potential applications in ADAS and automated accident reporting. Why it matters: This research showcases the potential of AI agents and multimodal LLMs to proactively enhance road safety in the UAE and reduce traffic-related incidents.
MBZUAI researchers developed FarSight, a plugin to reduce hallucinations in Multimodal Large Language Models (MLLMs). FarSight addresses the issue where MLLMs generate inaccurate text by losing focus on relevant image details, leading to snowball hallucinations. Testing on models like LLaVA-1.5-7B showed FarSight's effectiveness in reducing initial mistakes, thereby minimizing overall hallucinations. Why it matters: Improving the reliability of MLLMs is crucial for applications requiring high accuracy, enhancing their utility in various real-world scenarios.