WorldSimBench: Towards Video Generation Models as World Simulators Paper • 2410.18072 • Published 21 days ago • 16
TrackGo: A Flexible and Efficient Method for Controllable Video Generation Paper • 2408.11475 • Published Aug 21 • 16
MineDreamer: Learning to Follow Instructions via Chain-of-Imagination for Simulated-World Control Paper • 2403.12037 • Published Mar 18 • 1
MP5: A Multi-modal Open-ended Embodied System in Minecraft via Active Perception Paper • 2312.07472 • Published Dec 12, 2023 • 2
From GPT-4 to Gemini and Beyond: Assessing the Landscape of MLLMs on Generalizability, Trustworthiness and Causality through Four Modalities Paper • 2401.15071 • Published Jan 26 • 35