Related papers: PhyGround: Benchmarking Physical Reasoning in Gene…
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…
Understanding the physical world is a fundamental challenge in embodied AI, critical for enabling agents to perform complex tasks and operate safely in real-world environments. While Vision-Language Models (VLMs) have shown great promise in…
Video generation models have significantly advanced embodied intelligence, unlocking new possibilities for generating diverse robot data that capture perception, reasoning, and action in the physical world. However, synthesizing…
Understanding the physical world, including object dynamics, material properties, and causal interactions, remains a core challenge in artificial intelligence. Although recent multi-modal large language models (MLLMs) have demonstrated…
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 vision and language generative models have been overgrown in recent years. For video generation, various open-sourced models and public-available services have been developed to generate high-quality videos. However, these methods often…
While generative video models have achieved remarkable visual fidelity, their capacity to internalize and reason over implicit world rules remains a critical yet under-explored frontier. To bridge this gap, we present RISE-Video, a…
Existing benchmarks fail to capture a crucial aspect of intelligence: physical reasoning, the integrated ability to combine domain knowledge, symbolic reasoning, and understanding of real-world constraints. To address this gap, we introduce…
Video generation assessment is essential for ensuring that generative models produce visually realistic, high-quality videos while aligning with human expectations. Current video generation benchmarks fall into two main categories:…
State-of-the-art text-to-video (T2V) generators frequently violate physical laws despite high visual quality. We show this stems from insufficient physical constraints in prompts rather than model limitations: manually adding physics…
Recent advances in generative foundational models, often termed "world models," have propelled interest in applying them to critical tasks like robotic planning and autonomous system training. For reliable deployment, these models must…
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…
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 -…
Generative AI models, particularly Text-to-Video (T2V) systems, offer a promising avenue for transforming science education by automating the creation of engaging and intuitive visual explanations. In this work, we take a first step toward…
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…
Recent advances in text-to-video generation have produced increasingly realistic and diverse content, yet evaluating such videos remains a fundamental challenge due to their multi-faceted nature encompassing visual quality, semantic…
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…
Current benchmarks for evaluating the reasoning capabilities of Large Language Models (LLMs) face significant limitations: task oversimplification, data contamination, and flawed evaluation items. These deficiencies necessitate more…
Recent progress in generative video models, such as Veo-3, has shown surprising zero-shot reasoning abilities, creating a growing need for systematic and reliable evaluation. We introduce V-ReasonBench, a benchmark designed to assess video…