相关论文: Physion-Eval: Evaluating Physical Realism in Gener…
Today's driving world models can generate remarkably realistic dash-cam videos, yet no single model excels universally. Some generate photorealistic textures but violate basic physics; others maintain geometric consistency but fail when…
Egocentric perception enables humans to experience and understand the world directly from their own point of view. Translating exocentric (third-person) videos into egocentric (first-person) videos opens up new possibilities for immersive…
AI-generated video generation continues its journey through the uncanny valley to produce content that is increasingly perceptually indistinguishable from reality. To better protect individuals, organizations, and societies from its…
Numerous synthesized videos from generative models, especially human-centric ones that simulate realistic human actions, pose significant threats to human information security and authenticity. While progress has been made in binary forgery…
This paper reports on the LoViF 2026 PhyScore challenge, a competition on holistic quality assessment of world-model-generated videos across both 2D and 4D generation settings. The challenge is motivated by a central gap in current…
While exocentric video synthesis has achieved great progress, egocentric video generation remains largely underexplored, which requires modeling first-person view content along with camera motion patterns induced by the wearer's body…
Reasoning in the real world is not divorced from situations. How to capture the present knowledge from surrounding situations and perform reasoning accordingly is crucial and challenging for machine intelligence. This paper introduces a new…
Video generative models show emerging reasoning behaviors. It is essential to ensure that generated events remain causally consistent across frames for reliable deployment, a property we define as reasoning coherence. To bridge the gap in…
Generative Artificial Intelligence (AI) has rapidly advanced the field of computer vision by enabling machines to create and interpret visual data with unprecedented sophistication. This transformation builds upon a foundation of generative…
Quality assessment of AI-generated content is crucial for evaluating model capability and guiding model optimization. However, most existing quality assessment datasets and models provide only a single quality score, which is too coarse to…
Vision-Language Models (VLMs) have achieved strong results in video understanding, yet a key question remains: do they truly comprehend visual content or only learn shallow correlations between vision and language? Real visual…
Current text-to-video models (T2V) can generate high-quality, temporally coherent, and visually realistic videos. Nonetheless, errors still often occur, and are more nuanced and local compared to the previous generation of T2V models. While…
A long-standing question in physical reasoning is whether video-based models need to rely on factorized representations of physical variables in order to make physically accurate predictions, or whether they can implicitly represent such…
Recent progress in video generation has led to substantial improvements in visual fidelity, yet ensuring physically consistent motion remains a fundamental challenge. Intuitively, this limitation can be attributed to the fact that…
Generative world models are reshaping embodied AI, enabling agents to synthesize realistic 4D driving environments that look convincing but often fail physically or behaviorally. Despite rapid progress, the field still lacks a unified way…
Can humans identify AI-generated (fake) videos and provide grounded reasons? While video generation models have advanced rapidly, a critical dimension -- whether humans can detect deepfake traces within a generated video, i.e.,…
Recent progress in video generation has led to impressive visual quality, yet current models still struggle to produce results that align with real-world physical principles. To this end, we propose an iterative self-refinement framework…
We introduce CausalVQA, a benchmark dataset for video question answering (VQA) composed of question-answer pairs that probe models' understanding of causality in the physical world. Existing VQA benchmarks either tend to focus on surface…
Video generation has emerged as a promising tool for world simulation, leveraging visual data to replicate real-world environments. Within this context, egocentric video generation, which centers on the human perspective, holds significant…
Recent advances in video generation models have sparked interest in world models capable of simulating realistic environments. While navigation has been well-explored, physically meaningful interactions that mimic real-world forces remain…