Imagen de Portada

Reasoning Physical Video Generation with Diffusion Timestep Tokens via Reinforcement Learning

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Lin, Wang, Jia, Liyu, Hu, Wentao, Pan, Kaihang, Yue, Zhongqi, Zhao, Wei, Chen, Jingyuan, Wu, Fei, Zhang, Hanwang
Formato:	Preprint
Publicado:	2025
Materias:	Computer Vision and Pattern Recognition
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Generative Multimodal Pretraining with Discrete Diffusion Timestep Tokens
por: Pan, Kaihang, et al.
Publicado: (2025)

Selftok: Discrete Visual Tokens of Autoregression, by Diffusion, and for Reasoning
por: Wang, Bohan, et al.
Publicado: (2025)

Few-shot Learner Parameterization by Diffusion Time-steps
por: Yue, Zhongqi, et al.
Publicado: (2024)

AnyEdit: Mastering Unified High-Quality Image Editing for Any Idea
por: Yu, Qifan, et al.
Publicado: (2024)

Layer- and Timestep-Adaptive Differentiable Token Compression Ratios for Efficient Diffusion Transformers
por: You, Haoran, et al.
Publicado: (2024)

Exploring Diffusion Time-steps for Unsupervised Representation Learning
por: Yue, Zhongqi, et al.
Publicado: (2024)

Timestep Embedding Tells: It's Time to Cache for Video Diffusion Model
por: Liu, Feng, et al.
Publicado: (2024)

Auto-Encoding Morph-Tokens for Multimodal LLM
por: Pan, Kaihang, et al.
Publicado: (2024)

Dysen-VDM: Empowering Dynamics-aware Text-to-Video Diffusion with LLMs
por: Fei, Hao, et al.
Publicado: (2023)

Characterizing Motion Encoding in Video Diffusion Timesteps
por: Baherwani, Vatsal, et al.
Publicado: (2025)

Non-confusing Generation of Customized Concepts in Diffusion Models
por: Lin, Wang, et al.
Publicado: (2024)

Video-of-Thought: Step-by-Step Video Reasoning from Perception to Cognition
por: Fei, Hao, et al.
Publicado: (2024)

Video-KTR: Reinforcing Video Reasoning via Key Token Attribution
por: Wang, Ziyue, et al.
Publicado: (2026)

ART for Diffusion Sampling: A Reinforcement Learning Approach to Timestep Schedule
por: Huang, Yilie, et al.
Publicado: (2026)

Janus-Pro-R1: Advancing Collaborative Visual Comprehension and Generation via Reinforcement Learning
por: Pan, Kaihang, et al.
Publicado: (2025)

Don't Let It Fade: Preserving Edits in Diffusion Language Models via Token Timestep Allocation
por: Kim, Woojin, et al.
Publicado: (2025)

Pusa V1.0: Unlocking Temporal Control in Pretrained Video Diffusion Models via Vectorized Timestep Adaptation
por: Liu, Yaofang, et al.
Publicado: (2025)

Thinking with Images as Continuous Actions: Numerical Visual Chain-of-Thought
por: Zhao, Kesen, et al.
Publicado: (2026)

Unified Generative and Discriminative Training for Multi-modal Large Language Models
por: Chow, Wei, et al.
Publicado: (2024)

Redefining Temporal Modeling in Video Diffusion: The Vectorized Timestep Approach
por: Liu, Yaofang, et al.
Publicado: (2024)

ERTACache: Error Rectification and Timesteps Adjustment for Efficient Diffusion
por: Peng, Xurui, et al.
Publicado: (2025)

TASR: Timestep-Aware Diffusion Model for Image Super-Resolution
por: Lin, Qinwei, et al.
Publicado: (2024)

Timestep-Aware Correction for Quantized Diffusion Models
por: Yao, Yuzhe, et al.
Publicado: (2024)

OmniWeaving: Towards Unified Video Generation with Free-form Composition and Reasoning
por: Pan, Kaihang, et al.
Publicado: (2026)

Timestep-Aware Diffusion Model for Extreme Image Rescaling
por: Wang, Ce, et al.
Publicado: (2024)

Fine-tuning Diffusion Policies with Backpropagation Through Diffusion Timesteps
por: Yang, Ningyuan, et al.
Publicado: (2025)

FrameMind: Frame-Interleaved Video Reasoning via Reinforcement Learning
por: Ge, Haonan, et al.
Publicado: (2025)

Manifold-Aware Exploration for Reinforcement Learning in Video Generation
por: Zheng, Mingzhe, et al.
Publicado: (2026)

DyDiT++: Diffusion Transformers with Timestep and Spatial Dynamics for Efficient Visual Generation
por: Zhao, Wangbo, et al.
Publicado: (2025)

EPO: Explicit Policy Optimization for Strategic Reasoning in LLMs via Reinforcement Learning
por: Liu, Xiaoqian, et al.
Publicado: (2025)

Video-STR: Reinforcing MLLMs in Video Spatio-Temporal Reasoning with Relation Graph
por: Wang, Wentao, et al.
Publicado: (2025)

Metacognition as Reward: Reinforcing LLM Reasoning via Knowledge and Regulation Signals
por: Chen, Sirui, et al.
Publicado: (2026)

Unsupervised Visual Chain-of-Thought Reasoning via Preference Optimization
por: Zhao, Kesen, et al.
Publicado: (2025)

Compute Only 16 Tokens in One Timestep: Accelerating Diffusion Transformers with Cluster-Driven Feature Caching
por: Zheng, Zhixin, et al.
Publicado: (2025)

Self-Reflective Reinforcement Learning for Diffusion-based Image Reasoning Generation
por: Pan, Jiadong, et al.
Publicado: (2025)

RDPM: Solve Diffusion Probabilistic Models via Recurrent Token Prediction
por: Wu, Xiaoping, et al.
Publicado: (2024)

ViD-GPT: Introducing GPT-style Autoregressive Generation in Video Diffusion Models
por: Gao, Kaifeng, et al.
Publicado: (2024)

Accelerating Diffusion-based Video Editing via Heterogeneous Caching: Beyond Full Computing at Sampled Denoising Timestep
por: Liu, Tianyi, et al.
Publicado: (2026)

RLEP: Reinforcement Learning with Experience Replay for LLM Reasoning
por: Zhang, Hongzhi, et al.
Publicado: (2025)

Co-Reinforcement Learning for Unified Multimodal Understanding and Generation
por: Jiang, Jingjing, et al.
Publicado: (2025)