Imagen de Portada

Fine-tuning Diffusion Policies with Backpropagation Through Diffusion Timesteps

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Yang, Ningyuan, Gao, Jiaxuan, Gao, Feng, Wu, Yi, Yu, Chao
Formato:	Preprint
Publicado:	2025
Materias:	Machine Learning Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Towards Green AI in Fine-tuning Large Language Models via Adaptive Backpropagation
por: Huang, Kai, et al.
Publicado: (2023)

Pioneering 4-Bit FP Quantization for Diffusion Models: Mixup-Sign Quantization and Timestep-Aware Fine-Tuning
por: Zhao, Maosen, et al.
Publicado: (2025)

TMRL: Diffusion Timestep-Modulated Pretraining Enables Exploration for Efficient Policy Finetuning
por: Hong, Matthew M., et al.
Publicado: (2026)

Fine-tuning Pocket-Aware Diffusion Models via Denoising Policy Optimization
por: Xue, Yuan, et al.
Publicado: (2026)

Behavior-Regularized Diffusion Policy Optimization for Offline Reinforcement Learning
por: Gao, Chen-Xiao, et al.
Publicado: (2025)

REFINE-DP: Diffusion Policy Fine-tuning for Humanoid Loco-manipulation via Reinforcement Learning
por: Gu, Zhaoyuan, et al.
Publicado: (2026)

A Minimalist Method for Fine-tuning Text-to-Image Diffusion Models
por: Miao, Yanting, et al.
Publicado: (2025)

Membership Inference Attacks Against Fine-tuned Diffusion Language Models
por: Chen, Yuetian, et al.
Publicado: (2026)

LFPO: Likelihood-Free Policy Optimization for Masked Diffusion Models
por: Wei, Chenxing, et al.
Publicado: (2026)

Task-Agnostic Pre-training and Task-Guided Fine-tuning for Versatile Diffusion Planner
por: Fan, Chenyou, et al.
Publicado: (2024)

Towards Revealing the Effectiveness of Small-Scale Fine-tuning in R1-style Reinforcement Learning
por: Chen, Yutong, et al.
Publicado: (2025)

ICPL: Few-shot In-context Preference Learning via LLMs
por: Yu, Chao, et al.
Publicado: (2024)

Ratio-Variance Regularized Policy Optimization for Efficient LLM Fine-tuning
por: Luo, Yu, et al.
Publicado: (2026)

Reducing Fine-Tuning Memory Overhead by Approximate and Memory-Sharing Backpropagation
por: Yang, Yuchen, et al.
Publicado: (2024)

ChopGrad: Pixel-Wise Losses for Latent Video Diffusion via Truncated Backpropagation
por: Rivkin, Dmitriy, et al.
Publicado: (2026)

GRADE: Replacing Policy Gradients with Backpropagation for LLM Alignment
por: Nel, Lukas Abrie
Publicado: (2025)

Speculative Coreset Selection for Task-Specific Fine-tuning
por: Zhang, Xiaoyu, et al.
Publicado: (2024)

RevFFN: Memory-Efficient Full-Parameter Fine-Tuning of Mixture-of-Experts LLMs with Reversible Blocks
por: Liu, Ningyuan, et al.
Publicado: (2025)

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

Diffusion Fine-Tuning via Reparameterized Policy Gradient of the Soft Q-Function
por: Kang, Hyeongyu, et al.
Publicado: (2025)

Extending Test-Time Scaling: A 3D Perspective with Context, Batch, and Turn
por: Yu, Chao, et al.
Publicado: (2025)

Adaptive Divergence Regularized Policy Optimization for Fine-tuning Generative Models
por: Fan, Jiajun, et al.
Publicado: (2025)

Fine-tuning Behavioral Cloning Policies with Preference-Based Reinforcement Learning
por: Macuglia, Maël, et al.
Publicado: (2025)

AdjointDPM: Adjoint Sensitivity Method for Gradient Backpropagation of Diffusion Probabilistic Models
por: Pan, Jiachun, et al.
Publicado: (2023)

Outlier-weighed Layerwise Sampling for LLM Fine-tuning
por: Li, Pengxiang, et al.
Publicado: (2024)

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

A-SelecT: Automatic Timestep Selection for Diffusion Transformer Representation Learning
por: Liu, Changyu, et al.
Publicado: (2026)

Aligning Text-to-Image Diffusion Models with Reward Backpropagation
por: Prabhudesai, Mihir, et al.
Publicado: (2023)

Fine-Tuning Discrete Diffusion Models with Policy Gradient Methods
por: Zekri, Oussama, et al.
Publicado: (2025)

Exploring Diffusion Models' Corruption Stage in Few-Shot Fine-tuning and Mitigating with Bayesian Neural Networks
por: Wu, Xiaoyu, et al.
Publicado: (2024)

A Simple and Effective Reinforcement Learning Method for Text-to-Image Diffusion Fine-tuning
por: Gupta, Shashank, et al.
Publicado: (2025)

Non-Cross Diffusion for Semantic Consistency
por: Zheng, Ziyang, et al.
Publicado: (2023)

PolicyLong: Towards On-Policy Context Extension
por: Jia, Junlong, et al.
Publicado: (2026)

LRT-Diffusion: Calibrated Risk-Aware Guidance for Diffusion Policies
por: Sun, Ximan, et al.
Publicado: (2025)

Using Human Feedback to Fine-tune Diffusion Models without Any Reward Model
por: Yang, Kai, et al.
Publicado: (2023)

AirLLM: Diffusion Policy-based Adaptive LoRA for Remote Fine-Tuning of LLM over the Air
por: Yang, Shiyi, et al.
Publicado: (2025)

Practical Boolean Backpropagation
por: Golbert, Simon
Publicado: (2025)

OmniDrones: An Efficient and Flexible Platform for Reinforcement Learning in Drone Control
por: Xu, Botian, et al.
Publicado: (2023)

Adaptive Diffusion Policy Optimization for Robotic Manipulation
por: Jiang, Huiyun, et al.
Publicado: (2025)

Randomized Advantage Transformation (RAT): Computing Natural Policy Gradients via Direct Backpropagation
por: Sun, Mingfei
Publicado: (2026)