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.
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.
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.
Song Chaoyang from the Southern University of Science and Technology (SUSTech) presented research on Vision-Based Tactile Sensing (VBTS) for robot learning, combining soft robotic design with learning algorithms to achieve state-of-the-art performance in tactile perception. Their VBTS solution demonstrates robustness up to 1 million test cycles and enables multi-modal outputs from a single, vision-based input, facilitating applications such as amphibious tactile grasping and industrial welding. The talk also highlighted the DeepClaw system for capturing human demonstration actions, aiming for a universal interaction interface. Why it matters: This research advances embodied intelligence by improving robot dexterity and adaptability through enhanced tactile sensing, which is crucial for complex manipulation tasks in various sectors such as manufacturing and healthcare within the region.
MBZUAI Professor Fahad Khan is working on a unified theory of machine visual intelligence. His goal is to enable AI systems to better understand and function in complex, chaotic visual environments. The aim is to improve real-world applications like smart cities, personalized healthcare, and autonomous vehicles. Why it matters: This research could significantly advance AI's ability to perceive and interact with the real world, especially in challenging environments common in the developing world.
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.
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.