English
Related papers

Related papers: Towards World Simulator: Crafting Physical Commons…

200 papers

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…

Computer Vision and Pattern Recognition · Computer Science 2026-02-12 Meng Cao , Haoran Tang , Haoze Zhao , Mingfei Han , Ruyang Liu , Qiang Sun , Xiaojun Chang , Ian Reid , Xiaodan Liang

Recent text-to-image (T2I) models have demonstrated impressive capabilities in photorealistic synthesis and instruction following. However, their reliability in knowledge-intensive settings remains largely unexplored. Unlike natural image…

Computer Vision and Pattern Recognition · Computer Science 2026-04-27 Ran Zhao , Sheng Jin , Size Wu , Kang Liao , Zerui Gong , Zujin Guo , Yang Xiao , Wei Li

While Chain-of-Thought (CoT) prompting enables sophisticated symbolic reasoning in LLMs, it remains confined to discrete text and cannot simulate the continuous, physics-governed dynamics of the real world. Recent video generation models…

Computer Vision and Pattern Recognition · Computer Science 2026-02-13 Xinxin Liu , Zhaopan Xu , Ming Li , Kai Wang , Yong Jae Lee , Yuzhang Shang

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…

We propose a novel text-to-video (T2V) generation benchmark, ChronoMagic-Bench, to evaluate the temporal and metamorphic capabilities of the T2V models (e.g. Sora and Lumiere) in time-lapse video generation. In contrast to existing…

Computer Vision and Pattern Recognition · Computer Science 2024-10-03 Shenghai Yuan , Jinfa Huang , Yongqi Xu , Yaoyang Liu , Shaofeng Zhang , Yujun Shi , Ruijie Zhu , Xinhua Cheng , Jiebo Luo , Li Yuan

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 advancements in text-to-video (T2V) diffusion models have enabled high-fidelity and realistic video synthesis. However, current T2V models often struggle to generate physically plausible content due to their limited inherent ability…

Computer Vision and Pattern Recognition · Computer Science 2025-05-30 Xiangdong Zhang , Jiaqi Liao , Shaofeng Zhang , Fanqing Meng , Xiangpeng Wan , Junchi Yan , Yu Cheng

Recently, open-domain text-to-video (T2V) generation models have made remarkable progress. However, the promising results are mainly shown by the qualitative cases of generated videos, while the quantitative evaluation of T2V models still…

Computer Vision and Pattern Recognition · Computer Science 2023-12-27 Yuanxin Liu , Lei Li , Shuhuai Ren , Rundong Gao , Shicheng Li , Sishuo Chen , Xu Sun , Lu Hou

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…

Computer Vision and Pattern Recognition · Computer Science 2026-05-22 Jiarong Liang , Max Ku , Ka-Hei Hui , Ping Nie , Wenhu Chen

Text-to-image (T2I) models have achieved remarkable success in generating high-fidelity images, but they often fail in handling complex spatial relationships, e.g., spatial perception, reasoning, or interaction. These critical aspects are…

Computer Vision and Pattern Recognition · Computer Science 2026-01-30 Zengbin Wang , Xuecai Hu , Yong Wang , Feng Xiong , Man Zhang , Xiangxiang Chu

Recent advances in image and video generation raise hopes that these models possess world modeling capabilities, the ability to generate realistic, physically plausible videos. This could revolutionize applications in robotics, autonomous…

World simulators can provide safe and scalable environments for training Physical AI systems before real-world deployment. Large video generation models are emerging as a promising basis for such simulators because they can generate diverse…

Computer Vision and Pattern Recognition · Computer Science 2026-05-20 Pu Zhao , Juyi Lin , Timothy Rupprecht , Arash Akbari , Chence Yang , Rahul Chowdhury , Elaheh Motamedi , Arman Akbari , Yumei He , Chen Wang , Geng Yuan , Weiwei Chen , Yanzhi Wang

Evaluating generative video models remains an open problem. Reference-based metrics such as Structural Similarity Index Measure (SSIM) and Peak Signal to Noise Ratio (PSNR) reward pixel fidelity over semantic correctness, while Frechet…

Computer Vision and Pattern Recognition · Computer Science 2026-05-07 Karthik Inbasekar , Guy Rom , Omer Shlomovits

Text-to-video (T2V) generation has been recently enabled by transformer-based diffusion models, but current T2V models lack capabilities in adhering to the real-world common knowledge and physical rules, due to their limited understanding…

Computer Vision and Pattern Recognition · Computer Science 2025-04-02 Qiyao Xue , Xiangyu Yin , Boyuan Yang , Wei Gao

The scarcity of large-scale robotic data has motivated the repurposing of foundation models from other modalities for policy learning. In this work, we introduce PhysGen (Learning Physics from Pretrained Video Generation Models), a scalable…

Robotics · Computer Science 2026-04-24 Zijian Song , Qichang Li , Sihan Qin , Yuhao Chen , Tianshui Chen , Liang Lin , Guangrun Wang

In order for AI to be safely deployed in real-world scenarios such as hospitals, schools, and the workplace, it must be able to robustly reason about the physical world. Fundamental to this reasoning is physical common sense: understanding…

Machine Learning · Computer Science 2022-08-02 Samuel Yu , Peter Wu , Paul Pu Liang , Ruslan Salakhutdinov , Louis-Philippe Morency

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…

Existing text-to-video (T2V) evaluation benchmarks, such as VBench and EvalCrafter, suffer from two limitations. (i) While the emphasis is on subject-centric prompts or static camera scenes, camera motion essential for producing cinematic…

Computer Vision and Pattern Recognition · Computer Science 2025-10-10 Nithin C. Babu , Aniruddha Mahapatra , Harsh Rangwani , Rajiv Soundararajan , Kuldeep Kulkarni

Text-to-image (T2I) generation aims to synthesize images from textual prompts, which jointly specify what must be shown and imply what can be inferred, which thus correspond to two core capabilities: \textbf{\textit{composition}} and…

Computer Vision and Pattern Recognition · Computer Science 2026-03-03 Ouxiang Li , Yuan Wang , Xinting Hu , Huijuan Huang , Rui Chen , Jiarong Ou , Xin Tao , Pengfei Wan , Xiaojuan Qi , Fuli Feng

Commonsense reasoning, the ability to make logical assumptions about daily scenes, is one core intelligence of human beings. In this work, we present a novel task and dataset for evaluating the ability of text-to-image generative models to…

Multimedia · Computer Science 2024-01-24 Mianzhi Pan , Jianfei Li , Mingyue Yu , Zheng Ma , Kanzhi Cheng , Jianbing Zhang , Jiajun Chen