Image de couverture de livre

PhyGDPO: Physics-Aware Groupwise Direct Preference Optimization for Physically Consistent Text-to-Video Generation

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Cai, Yuanhao, Li, Kunpeng, Jia, Menglin, Wang, Jialiang, Sun, Junzhe, Liang, Feng, Chen, Weifeng, Juefei-Xu, Felix, Wang, Chu, Thabet, Ali, Dai, Xiaoliang, Ju, Xuan, Yuille, Alan, Hou, Ji
Format:	Preprint
Publié:	2025
Sujets:	Computer Vision and Pattern Recognition
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

DGPO: Beyond Pairwise Preferences with Directional Consistent Groupwise Optimization
par: Deng, Mengyi, et autres
Publié: (2026)

Exploring MLLM-Diffusion Information Transfer with MetaCanvas
par: Lin, Han, et autres
Publié: (2025)

GDPO-SR: Group Direct Preference Optimization for One-Step Generative Image Super-Resolution
par: Yi, Qiaosi, et autres
Publié: (2026)

MetaGDPO: Alleviating Catastrophic Forgetting with Metacognitive Knowledge through Group Direct Preference Optimization
par: Zhang, Lanxue, et autres
Publié: (2025)

Dictionary-based Framework for Interpretable and Consistent Object Parsing
par: Zhang, Tiezheng, et autres
Publié: (2025)

Llama Learns to Direct: DirectorLLM for Human-Centric Video Generation
par: Song, Kunpeng, et autres
Publié: (2024)

Structure-Aware Sparse-View X-ray 3D Reconstruction
par: Cai, Yuanhao, et autres
Publié: (2023)

GDPO: Learning to Directly Align Language Models with Diversity Using GFlowNets
par: Kwon, Oh Joon, et autres
Publié: (2024)

Improving Chain-of-Thought Efficiency for Autoregressive Image Generation
par: Gu, Zeqi, et autres
Publié: (2025)

RDPO: Real Data Preference Optimization for Physics Consistency Video Generation
par: Qian, Wenxu, et autres
Publié: (2025)

PhiP-G: Physics-Guided Text-to-3D Compositional Scene Generation
par: Li, Qixuan, et autres
Publié: (2025)

PhyBench: A Physical Commonsense Benchmark for Evaluating Text-to-Image Models
par: Meng, Fanqing, et autres
Publié: (2024)

LinGen: Towards High-Resolution Minute-Length Text-to-Video Generation with Linear Computational Complexity
par: Wang, Hongjie, et autres
Publié: (2024)

PhyCustom: Towards Realistic Physical Customization in Text-to-Image Generation
par: Wu, Fan, et autres
Publié: (2025)

PhyAVBench: A Challenging Audio Physics-Sensitivity Benchmark for Physically Grounded Text-to-Audio-Video Generation
par: Xie, Tianxin, et autres
Publié: (2025)

"PhyWorldBench": A Comprehensive Evaluation of Physical Realism in Text-to-Video Models
par: Gu, Jing, et autres
Publié: (2025)

Can These Views Be One Scene? Evaluating Multiview 3D Consistency when 3D Foundation Models Hallucinate
par: Paul, Soumava, et autres
Publié: (2026)

DirectTriGS: Triplane-based Gaussian Splatting Field Representation for 3D Generation
par: Ju, Xiaoliang, et autres
Publié: (2025)

UniT: Unified Multimodal Chain-of-Thought Test-time Scaling
par: Chen, Leon Liangyu, et autres
Publié: (2026)

PhyScensis: Physics-Augmented LLM Agents for Complex Physical Scene Arrangement
par: Wang, Yian, et autres
Publié: (2026)

DIRECT-3D: Learning Direct Text-to-3D Generation on Massive Noisy 3D Data
par: Liu, Qihao, et autres
Publié: (2024)

Phy124: Fast Physics-Driven 4D Content Generation from a Single Image
par: Lin, Jiajing, et autres
Publié: (2024)

PhyScene3D: Physically Consistent Interactive 3D Tabletop Scene Generation
par: Chen, Weixing, et autres
Publié: (2026)

ViMix-14M: A Curated Multi-Source Video-Text Dataset with Long-Form, High-Quality Captions and Crawl-Free Access
par: Yang, Timing, et autres
Publié: (2025)

Groupwise Registration with Physics-Informed Test-Time Adaptation on Multi-parametric Cardiac MRI
par: Li, Xinqi, et autres
Publié: (2025)

Causal Inference with Groupwise Matching
par: Rincón, Ratzanyel, et autres
Publié: (2025)

PhyCritic: Multimodal Critic Models for Physical AI
par: Xiong, Tianyi, et autres
Publié: (2026)

Compositional 4D Dynamic Scenes Understanding with Physics Priors for Video Question Answering
par: Wang, Xingrui, et autres
Publié: (2024)

Think in Strokes, Not Pixels: Process-Driven Image Generation via Interleaved Reasoning
par: Zhang, Lei, et autres
Publié: (2026)

Groupwise image registration with edge‐based loss for low‐SNR cardiac MRI
par: Xuan Lei, et autres
Publié: (2025)

Groupwise Image Registration with Edge-Based Loss for Low-SNR Cardiac MRI
par: Lei, Xuan, et autres
Publié: (2024)

PhyDetEx: Detecting and Explaining the Physical Plausibility of T2V Models
par: Wang, Zeqing, et autres
Publié: (2025)

ProPhy: Progressive Physical Alignment for Dynamic World Simulation
par: Wang, Zijun, et autres
Publié: (2025)

PhyRecon: Physically Plausible Neural Scene Reconstruction
par: Ni, Junfeng, et autres
Publié: (2024)

PhyEduVideo: A Benchmark for Evaluating Text-to-Video Models for Physics Education
par: M, Megha Mariam K., et autres
Publié: (2026)

PhyPrompt: RL-based Prompt Refinement for Physically Plausible Text-to-Video Generation
par: Wu, Shang, et autres
Publié: (2026)

PhyWorld: Physics-Faithful World Model for Video Generation
par: Zhao, Pu, et autres
Publié: (2026)

PhySense: Sensor Placement Optimization for Accurate Physics Sensing
par: Ma, Yuezhou, et autres
Publié: (2025)

FastVideoEdit: Leveraging Consistency Models for Efficient Text-to-Video Editing
par: Zhang, Youyuan, et autres
Publié: (2024)

GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization
par: Liu, Shih-Yang, et autres
Publié: (2026)