arXiv ·
A new approach to composed video retrieval (CoVR) is presented, which leverages large multimodal models to infer causal and temporal consequences implied by an edit. The method aligns reasoned queries to candidate videos without task-specific finetuning. A new benchmark, CoVR-Reason, is introduced to evaluate reasoning in CoVR.
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.
MBZUAI ·
Manling Li from UIUC proposes a new research direction: Event-Centric Multimodal Knowledge Acquisition, which transforms traditional entity-centric single-modal knowledge into event-centric multi-modal knowledge. The approach addresses challenges in understanding multimodal semantic structures using zero-shot cross-modal transfer (CLIP-Event) and long-horizon temporal dynamics through the Event Graph Model. Li's work aims to enable machines to capture complex timelines and relationships, with applications in timeline generation, meeting summarization, and question answering. Why it matters: This research pioneers a new approach to multimodal information extraction, moving from static entity-based understanding to dynamic, event-centric knowledge acquisition, which is essential for advanced AI applications in understanding complex scenarios.
MBZUAI ·
Nicu Sebe from the University of Trento presented recent work on video generation, focusing on animating objects in a source image using external information like labels, driving videos, or text. He introduced a Learnable Game Engine (LGE) trained from monocular annotated videos, which maintains states of scenes, objects, and agents to render controllable viewpoints. Why it matters: This talk highlights advancements in cross-modal AI, potentially enabling new applications in gaming, simulation, and content creation within the region.
arXiv ·
Researchers at MBZUAI have introduced Video-R2, a reinforcement learning approach to improve the consistency and visual grounding of reasoning in multimodal language models. Video-R2 combines timestamp-aware supervised fine-tuning with Group Relative Policy Optimization (GRPO) guided by a Temporal Alignment Reward (TAR). The model demonstrates higher Think Answer Consistency (TAC), Video Attention Score (VAS), and accuracy across multiple benchmarks, showing improved temporal alignment and reasoning coherence for video understanding.
MBZUAI ·
Vicky Kalogeiton from École Polytechnique discussed the importance of multimodality for story-level recognition and generation using video, audio, text, masks and clinical data. She presented on multimodal video understanding using FunnyNet-W and Short Film Dataset. She further showed examples of visual generation from text and other modalities (ET, CAD, DynamicGuidance). Why it matters: Multimodal AI research is growing globally, and this talk highlights the potential of combining different data types for enhanced understanding and generation, which could have implications for various applications, including those relevant to the Middle East.
MBZUAI ·
Paul Liang from CMU presented on machine learning foundations for multisensory AI, discussing a theoretical framework for modality interactions. The talk covered cross-modal attention and multimodal transformer architectures, and applications in mental health, pathology, and robotics. Liang's research aims to enable AI systems to integrate and learn from diverse real-world sensory modalities. Why it matters: This highlights the growing importance of multimodal AI research and its potential for advancements across various sectors in the region, including healthcare and robotics.