Related papers: Morpheus: Benchmarking Physical Reasoning of Video…
Video generation models are increasingly used as world simulators for storytelling, simulation, and embodied AI. As these models advance, a key question arises: do generated videos obey the physical laws of the real world? Existing…
Generative world models are increasingly used for video generation, where learned simulators are expected to capture the physical rules that govern real-world dynamics. However, evaluating whether generated videos actually follow these…
Text-to-video generative models have made significant strides in recent years, producing high-quality videos that excel in both aesthetic appeal and accurate instruction following, and have become central to digital art creation and user…
Recent advances in internet-scale video data pretraining have led to the development of text-to-video generative models that can create high-quality videos across a broad range of visual concepts, synthesize realistic motions and render…
Video generation models have achieved remarkable progress in creating high-quality, photorealistic content. However, their ability to accurately simulate physical phenomena remains a critical and unresolved challenge. This paper presents…
Video generation models have rapidly progressed, positioning themselves as video world models capable of supporting decision-making applications like robotics and autonomous driving. However, current benchmarks fail to rigorously evaluate…
Large-scale video generative models, capable of creating realistic videos of diverse visual concepts, are strong candidates for general-purpose physical world simulators. However, their adherence to physical commonsense across real-world…
AI video generation is undergoing a revolution, with quality and realism advancing rapidly. These advances have led to a passionate scientific debate: Do video models learn "world models" that discover laws of physics -- or, alternatively,…
Recent advancements in video generation have witnessed significant progress, especially with the rapid advancement of diffusion models. Despite this, their deficiencies in physical cognition have gradually received widespread attention -…
Video generation models have emerged as high-fidelity models of the physical world, capable of synthesizing high-quality videos capturing fine-grained interactions between agents and their environments conditioned on multi-modal user…
The next frontier for video generation lies in developing models capable of zero-shot reasoning, where understanding real-world scientific laws is crucial for accurate physical outcome modeling under diverse conditions. However, existing…
Modern foundational Multimodal Large Language Models (MLLMs) and video world models have advanced significantly in mathematical, common-sense, and visual reasoning, but their grasp of the underlying physics remains underexplored. Existing…
Recent advances in video generation models demonstrate their potential as world simulators, but they often struggle with videos deviating from physical laws, a key concern overlooked by most text-to-video benchmarks. We introduce a…
Evaluating whether Multimodal Large Language Models (MLLMs) genuinely reason about physical dynamics remains challenging. Most existing benchmarks rely on recognition-style protocols such as Visual Question Answering (VQA) and Violation of…
Recent progress in text-to-video (T2V) generation has enabled the synthesis of visually compelling and temporally coherent videos from natural language. However, these models often fall short in basic physical commonsense, producing outputs…
Recent video diffusion models can synthesize visually compelling clips, yet often violate basic physical laws-objects float, accelerations drift, and collisions behave inconsistently-revealing a persistent gap between visual realism and…
Can we learn the physics of matter in motion directly from images and video--and trust it? Answering this question requires integrating experiments, physics-based simulation, and data across traditionally separate disciplines. Much of this…
State-of-the-art video generative models produce promising visual content yet often violate basic physics principles, limiting their utility. While some attribute this deficiency to insufficient physics understanding from pre-training, we…
Neural rendering has demonstrated remarkable success in dynamic scene reconstruction. Thanks to the expressiveness of neural representations, prior works can accurately capture the motion and achieve high-fidelity reconstruction of the…
Despite impressive visual fidelity, modern video generative models frequently produce sequences that violate intuitive physical laws, such as objects floating, teleporting, or morphing in ways that defy causality. While humans can easily…