相关论文: Towards World Simulator: Crafting Physical Commons…

While text-to-video (T2V) generation has achieved remarkable progress in photorealism, generating intent-aligned videos that faithfully obey physics principles remains a core challenge. In this work, we systematically study Newtonian…

Driven by the growing capacity and training scale, Text-to-Video (T2V) generation models have recently achieved substantial progress in video quality, length, and instruction-following capability. However, whether these models can…

Recent advances in text-to-video (T2V) technology, as demonstrated by models such as Runway Gen-3, Pika, Sora, and Kling, have significantly broadened the applicability and popularity of the technology. This progress has created a growing…

Generative diffusion models are developing rapidly and attracting increasing attention due to their wide range of applications. Image-to-Video (I2V) generation has become a major focus in the field of video synthesis. However, existing…

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…

Commercial video generation systems such as Seedance2.0 and Veo3.1 have rapidly improved, strengthening the view that video generators may be evolving into "world simulators." Yet the community still lacks a benchmark that directly tests…

The recent rapid advancement of Text-to-Video (T2V) generation technologies are engaging the trained models with more world model ability, making the existing benchmarks increasingly insufficient to evaluate state-of-the-art T2V models.…

Recent text-to-video generation models have made remarkable progress in visual realism, motion fidelity, and text-video alignment, yet they still struggle to produce socially coherent behavior. Unlike humans, who readily infer intentions,…

Physics problem-solving is a challenging domain for AI models, requiring integration of conceptual understanding, mathematical reasoning, and interpretation of physical diagrams. Existing evaluations fail to capture the full breadth and…

Recent progress in text-to-image (T2I) generation underscores the importance of reliable benchmarks in evaluating how accurately generated images reflect the semantics of their textual prompt. However, (1) existing benchmarks lack the…

Text-to-Audio-Video (T2AV) generation is rapidly becoming a core interface for media creation, yet its evaluation remains fragmented. Existing benchmarks largely assess audio and video in isolation or rely on coarse embedding similarity,…

We present PhysGen, a novel image-to-video generation method that converts a single image and an input condition (e.g., force and torque applied to an object in the image) to produce a realistic, physically plausible, and temporally…

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…

Video generation models have shown strong potential as world models for autonomous driving simulation. However, existing approaches are primarily trained on real-world driving datasets, which mostly contain natural and safe driving…

The rapid evolution of video generative models has shifted their focus from producing visually plausible outputs to tackling tasks requiring physical plausibility and logical consistency. However, despite recent breakthroughs such as Veo…

Text-to-image (T2I) models today are capable of producing photorealistic, instruction-following images, yet they still frequently fail on prompts that require implicit world knowledge. Existing evaluation protocols either emphasize…

Reasoning is a fundamental capability often required in real-world text-to-image (T2I) generation, e.g., generating ``a bitten apple that has been left in the air for more than a week`` necessitates understanding temporal decay and…

Text-to-video (T2V) generative models have advanced significantly, yet their ability to compose different objects, attributes, actions, and motions into a video remains unexplored. Previous text-to-video benchmarks also neglect this…

Physics-aware symbolic simulation of 3D scenes is critical for robotics, embodied AI, and scientific computing, requiring models to understand natural language descriptions of physical phenomena and translate them into executable simulation…

Physical AI aims to develop models that can perceive and predict real-world dynamics; yet, the extent to which current multi-modal large language models and video generative models support these abilities is insufficiently understood. We…