Cover Image

Disentangled World Models: Learning to Transfer Semantic Knowledge from Distracting Videos for Reinforcement Learning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wang, Qi, Zhang, Zhipeng, Xie, Baao, Jin, Xin, Wang, Yunbo, Wang, Shiyu, Zheng, Liaomo, Yang, Xiaokang, Zeng, Wenjun
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Graph-based Unsupervised Disentangled Representation Learning via Multimodal Large Language Models
by: Xie, Baao, et al.
Published: (2024)

Interpretable Single-View 3D Gaussian Splatting using Unsupervised Hierarchical Disentangled Representation Learning
by: Zhang, Yuyang, et al.
Published: (2025)

Making Offline RL Online: Collaborative World Models for Offline Visual Reinforcement Learning
by: Wang, Qi, et al.
Published: (2023)

NaviNeRF: NeRF-based 3D Representation Disentanglement by Latent Semantic Navigation
by: Xie, Baao, et al.
Published: (2023)

OccScene: Semantic Occupancy-based Cross-task Mutual Learning for 3D Scene Generation
by: Li, Bohan, et al.
Published: (2024)

Open-World Reinforcement Learning over Long Short-Term Imagination
by: Li, Jiajian, et al.
Published: (2024)

Scene Graph Disentanglement and Composition for Generalizable Complex Image Generation
by: Wang, Yunnan, et al.
Published: (2024)

Latent Intuitive Physics: Learning to Transfer Hidden Physics from A 3D Video
by: Zhu, Xiangming, et al.
Published: (2024)

Goal-Driven Reward by Video Diffusion Models for Reinforcement Learning
by: Wang, Qi, et al.
Published: (2025)

Continual Visual Reinforcement Learning with A Life-Long World Model
by: Pan, Minting, et al.
Published: (2023)

MetaGS: A Meta-Learned Gaussian-Phong Model for Out-of-Distribution 3D Scene Relighting
by: He, Yumeng, et al.
Published: (2024)

Improving Masked Autoencoders by Learning Where to Mask
by: Chen, Haijian, et al.
Published: (2023)

Hierarchical Context Alignment with Disentangled Geometric and Temporal Modeling for Semantic Occupancy Prediction
by: Li, Bohan, et al.
Published: (2024)

DynaVol: Unsupervised Learning for Dynamic Scenes through Object-Centric Voxelization
by: Zhao, Yanpeng, et al.
Published: (2023)

MotionBank: A Large-scale Video Motion Benchmark with Disentangled Rule-based Annotations
by: Xu, Liang, et al.
Published: (2024)

Disentangled Robot Learning via Separate Forward and Inverse Dynamics Pretraining
by: Zhang, Wenyao, et al.
Published: (2026)

Video-Enhanced Offline Reinforcement Learning: A Model-Based Approach
by: Pan, Minting, et al.
Published: (2025)

Occlusion-Guided Feature Purification Learning via Reinforced Knowledge Distillation for Occluded Person Re-Identification
by: Zheng, Yufei, et al.
Published: (2025)

Model-Based Reinforcement Learning with Multi-Task Offline Pretraining
by: Pan, Minting, et al.
Published: (2023)

NeoWorld: Neural Simulation of Explorable Virtual Worlds via Progressive 3D Unfolding
by: Zhao, Yanpeng, et al.
Published: (2025)

Plasticine: Accelerating Research in Plasticity-Motivated Deep Reinforcement Learning
by: Yuan, Mingqi, et al.
Published: (2025)

VideoWorld 2: Learning Transferable Knowledge from Real-world Videos
by: Ren, Zhongwei, et al.
Published: (2026)

Tell Codec What Worth Compressing: Semantically Disentangled Image Coding for Machine with LMMs
by: Liu, Jinming, et al.
Published: (2024)

EMGauss: Continuous Slice-to-3D Reconstruction via Dynamic Gaussian Modeling in Volume Electron Microscopy
by: He, Yumeng, et al.
Published: (2025)

Cross-Camera Distracted Driver Classification through Feature Disentanglement and Contrastive Learning
by: Celona, Luigi, et al.
Published: (2024)

Learning Visual Proxy for Compositional Zero-Shot Learning
by: Zhang, Shiyu, et al.
Published: (2025)

SceneScribe-1M: A Large-Scale Video Dataset with Comprehensive Geometric and Semantic Annotations
by: Wang, Yunnan, et al.
Published: (2026)

Harnessing Textual Semantic Priors for Knowledge Transfer and Refinement in CLIP-Driven Continual Learning
by: He, Lingfeng, et al.
Published: (2025)

Dynamic Scene Understanding through Object-Centric Voxelization and Neural Rendering
by: Zhao, Yanpeng, et al.
Published: (2024)

Learning Domain Knowledge in Multimodal Large Language Models through Reinforcement Fine-Tuning
by: Cao, Qinglong, et al.
Published: (2026)

VideoWorld: Exploring Knowledge Learning from Unlabeled Videos
by: Ren, Zhongwei, et al.
Published: (2025)

Semantics Disentanglement and Composition for Universal Image Coding with Efficiently LLM Reasoning and Generative Diffusion
by: Liu, Jinming, et al.
Published: (2024)

Hierarchical Temporal Context Learning for Camera-based Semantic Scene Completion
by: Li, Bohan, et al.
Published: (2024)

Video-Thinker: Sparking "Thinking with Videos" via Reinforcement Learning
by: Wang, Shijian, et al.
Published: (2025)

Learning Transferable Negative Prompts for Out-of-Distribution Detection
by: Li, Tianqi, et al.
Published: (2024)

DistractMIA: Black-Box Membership Inference on Vision-Language Models via Semantic Distraction
by: Tang, Hongyi, et al.
Published: (2026)

Closed-Loop Unsupervised Representation Disentanglement with $β$-VAE Distillation and Diffusion Probabilistic Feedback
by: Jin, Xin, et al.
Published: (2024)

Learning to Tell Apart: Weakly Supervised Video Anomaly Detection via Disentangled Semantic Alignment
by: Yin, Wenti, et al.
Published: (2025)

Disentangled Human Body Representation Based on Unsupervised Semantic-Aware Learning
by: Wang, Lu, et al.
Published: (2025)

ContactGaussian-WM: Learning Physics-Grounded World Model from Videos
by: Wang, Meizhong, et al.
Published: (2026)