Cover Image

VideoPhy-2: A Challenging Action-Centric Physical Commonsense Evaluation in Video Generation

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Bansal, Hritik, Peng, Clark, Bitton, Yonatan, Goldenberg, Roman, Grover, Aditya, Chang, Kai-Wei
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

VideoPhy: Evaluating Physical Commonsense for Video Generation
by: Bansal, Hritik, et al.
Published: (2024)

TALC: Time-Aligned Captions for Multi-Scene Text-to-Video Generation
by: Bansal, Hritik, et al.
Published: (2024)

PhyEduVideo: A Benchmark for Evaluating Text-to-Video Models for Physics Education
by: M, Megha Mariam K., et al.
Published: (2026)

ConTextual: Evaluating Context-Sensitive Text-Rich Visual Reasoning in Large Multimodal Models
by: Wadhawan, Rohan, et al.
Published: (2024)

Visual Riddles: a Commonsense and World Knowledge Challenge for Large Vision and Language Models
by: Bitton-Guetta, Nitzan, et al.
Published: (2024)

HoneyBee: Data Recipes for Vision-Language Reasoners
by: Bansal, Hritik, et al.
Published: (2025)

PhyBench: A Physical Commonsense Benchmark for Evaluating Text-to-Image Models
by: Meng, Fanqing, et al.
Published: (2024)

Video-STaR: Self-Training Enables Video Instruction Tuning with Any Supervision
by: Zohar, Orr, et al.
Published: (2024)

Contrastive Sequential-Diffusion Learning: Non-linear and Multi-Scene Instructional Video Synthesis
by: Ramos, Vasco, et al.
Published: (2024)

GenEARL: A Training-Free Generative Framework for Multimodal Event Argument Role Labeling
by: Bansal, Hritik, et al.
Published: (2024)

PhyRPR: Training-Free Physics-Constrained Video Generation
by: Zhao, Yibo, et al.
Published: (2026)

MedMax: Mixed-Modal Instruction Tuning for Training Biomedical Assistants
by: Bansal, Hritik, et al.
Published: (2024)

PhyMotion: Structured 3D Motion Reward for Physics-Grounded Human Video Generation
by: Huang, Yidong, et al.
Published: (2026)

LaViDa: A Large Diffusion Language Model for Multimodal Understanding
by: Li, Shufan, et al.
Published: (2025)

OpenVLThinker: Complex Vision-Language Reasoning via Iterative SFT-RL Cycles
by: Deng, Yihe, et al.
Published: (2025)

Towards World Simulator: Crafting Physical Commonsense-Based Benchmark for Video Generation
by: Meng, Fanqing, et al.
Published: (2024)

Semantic Parsing of Colonoscopy Videos with Multi-Label Temporal Networks
by: Kelner, Ori, et al.
Published: (2023)

PhysGame: Uncovering Physical Commonsense Violations in Gameplay Videos
by: Cao, Meng, et al.
Published: (2024)

PhyGDPO: Physics-Aware Groupwise Direct Preference Optimization for Physically Consistent Text-to-Video Generation
by: Cai, Yuanhao, et al.
Published: (2025)

ContPhy: Continuum Physical Concept Learning and Reasoning from Videos
by: Zheng, Zhicheng, et al.
Published: (2024)

ActionArt: Advancing Multimodal Large Models for Fine-Grained Human-Centric Video Understanding
by: Peng, Yi-Xing, et al.
Published: (2025)

PhyVLLM: Physics-Guided Video Language Model with Motion-Appearance Disentanglement
by: Zhan, Yu-Wei, et al.
Published: (2025)

"PhyWorldBench": A Comprehensive Evaluation of Physical Realism in Text-to-Video Models
by: Gu, Jing, et al.
Published: (2025)

PhyT2V: LLM-Guided Iterative Self-Refinement for Physics-Grounded Text-to-Video Generation
by: Xue, Qiyao, et al.
Published: (2024)

PhyWorld: Physics-Faithful World Model for Video Generation
by: Zhao, Pu, et al.
Published: (2026)

PhyPrompt: RL-based Prompt Refinement for Physically Plausible Text-to-Video Generation
by: Wu, Shang, et al.
Published: (2026)

RefVNLI: Towards Scalable Evaluation of Subject-driven Text-to-image Generation
by: Slobodkin, Aviv, et al.
Published: (2025)

Survey of Bias In Text-to-Image Generation: Definition, Evaluation, and Mitigation
by: Wan, Yixin, et al.
Published: (2024)

Editor's Choice: Evaluating Abstract Intent in Image Editing through Atomic Entity Analysis
by: Ventura, Mor, et al.
Published: (2026)

Discovering Novel Actions from Open World Egocentric Videos with Object-Grounded Visual Commonsense Reasoning
by: Kundu, Sanjoy, et al.
Published: (2023)

EditInspector: A Benchmark for Evaluation of Text-Guided Image Edits
by: Yosef, Ron, et al.
Published: (2025)

Implicit and Explicit Commonsense for Multi-sentence Video Captioning
by: Chou, Shih-Han, et al.
Published: (2023)

VideoChat: Chat-Centric Video Understanding
by: Li, KunChang, et al.
Published: (2023)

Chain of Event-Centric Causal Thought for Physically Plausible Video Generation
by: Wang, Zixuan, et al.
Published: (2026)

Learning Action and Reasoning-Centric Image Editing from Videos and Simulations
by: Krojer, Benno, et al.
Published: (2024)

Are Synthetic Videos Useful? A Benchmark for Retrieval-Centric Evaluation of Synthetic Videos
by: Zhao, Zecheng, et al.
Published: (2025)

Seeing Isn't Knowing: Do VLMs Know When Not to Answer Spatial Questions (and Why)?
by: Zhang, Yue, et al.
Published: (2026)

DocVideoQA: Towards Comprehensive Understanding of Document-Centric Videos through Question Answering
by: Wang, Haochen, et al.
Published: (2025)

Droplet3D: Commonsense Priors from Videos Facilitate 3D Generation
by: Li, Xiaochuan, et al.
Published: (2025)

Commonsense Video Question Answering through Video-Grounded Entailment Tree Reasoning
by: Liu, Huabin, et al.
Published: (2025)