Researchers introduce RoboMME, a large-scale standardized benchmark for evaluating memory in robotic vision-language-action (VLA) models across 16 manipulation tasks. The study tests 14 memory-augmented VLA variants and finds that no single memory architecture excels across all task types—each design offers distinct trade-offs depending on temporal, spatial, object, and procedural demands.
Researchers introduce RealWonder, a real-time video generation system that simulates physical consequences of 3D actions by using physics simulation as an intermediate representation. The system generates 480x832 resolution videos at 13.2 FPS from a single image, handling rigid objects, deformable bodies, fluids, and granular materials.
Researchers introduce ELMUR, a transformer variant that adds structured external memory to handle long-horizon reinforcement learning problems under partial observability. The system extends effective decision-making horizons beyond standard attention windows by up to 100,000x and achieves 100% success on synthetic tasks with corridors spanning one million steps.
Researchers present REFLEX, a framework that equips LLM-powered robotic agents with metacognitive capabilities—skill decomposition, failure reflection, and solution synthesis—to perform complex tasks in zero-shot and few-shot settings. The system significantly outperforms existing baselines and demonstrates that LLMs can generate creative solutions that diverge from ground truth while still completing tasks successfully.
World Labs, the AI startup founded by Fei-Fei Li, has raised $1 billion in new funding to develop spatial intelligence—AI systems capable of understanding and operating in three-dimensional physical environments. The capital will fund the development of world models, a class of AI architecture designed to reason about spatial relationships and physical interactions.