相关论文: WISA: World Simulator Assistant for Physics-Aware …
Video Diffusion Models (VDMs) offer a promising approach for simulating dynamic scenes and environments, with broad applications in robotics and media generation. However, existing models often generate temporally incoherent content that…
Despite remarkable advances in video generative models, they still struggle to generate physically realistic videos, frequently exhibiting appearance drift, implausible motion, and temporal inconsistencies. In this work, we address this…
Text-to-video (T2V) generation technology holds potential to transform multiple domains such as education, marketing, entertainment, and assistive technologies for individuals with visual or reading comprehension challenges, by creating…
Humans develop an understanding of intuitive physics through active interaction with the world. This approach is in stark contrast to current video models, such as Sora, which rely on passive observation and therefore struggle with grasping…
With the rapid development of generative models, Artificial Intelligence-Generated Contents (AIGC) have exponentially increased in daily lives. Among them, Text-to-Video (T2V) generation has received widespread attention. Though many T2V…
Large-scale pre-trained video generation models excel in content creation but are not reliable as physically accurate world simulators out of the box. This work studies the process of post-training these models for accurate world modeling…
The landscape of video generation is shifting, from a focus on generating visually appealing clips to building virtual environments that support interaction and maintain physical plausibility. These developments point toward the emergence…
The evolution of video generation from text, from animating MNIST to simulating the world with Sora, has progressed at a breakneck speed. Here, we systematically discuss how far text-to-video generation technology supports essential…
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 -…
Recent advances in Text-to-Video generation (T2V) have achieved remarkable success in synthesizing high-quality general videos from textual descriptions. A largely overlooked problem in T2V is that existing models have not adequately…
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…
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…
The recent wave of AI-generated content has witnessed the great development and success of Text-to-Image (T2I) technologies. By contrast, Text-to-Video (T2V) still falls short of expectations though attracting increasing interests. Existing…
Generating high-fidelity upper-body 3D avatars from one-shot input image remains a significant challenge. Current 3D avatar generation methods, which rely on large reconstruction models, are fast and capable of producing stable body…
Simulation has the potential to transform the development of robust algorithms for mobile agents deployed in safety-critical scenarios. However, the poor photorealism and lack of diverse sensor modalities of existing simulation engines…
Visuals are valuable tools for teaching math word problems (MWPs), helping young learners interpret textual descriptions into mathematical expressions before solving them. However, creating such visuals is labor-intensive and there is a…
Generative video models achieve high visual fidelity but often violate basic physical principles, limiting reliability in real-world settings. Prior attempts to inject physics rely on conditioning: frame-level signals are domain-specific…
Transforming recorded videos into concise and accurate textual summaries is a growing challenge in multimodal learning. This paper introduces VISTA, a dataset specifically designed for video-to-text summarization in scientific domains.…
Existing video generation models predominantly emphasize appearance fidelity while exhibiting limited ability to synthesize complex human motions, such as whole-body movements, long-range dynamics, and fine-grained human-environment…