paper-with-me

홈 › Papers

Prompt Tuning with Diffusion for Few-Shot Pre-trained Policy Generalization

2024-11-02 · Shengchao Hu, Wanru Zhao, Weixiong Lin, Li Shen, Ya zhang, DaCheng Tao

Offline reinforcement learning (RL) methods harness previous experiences to derive an optimal policy, forming the foundation for pre-trained large-scale models (PLMs). When encountering tasks not seen before, PLMs often utilize several expert trajectories as prompts to expedite their adaptation to new requirements. Though a range of prompt-tuning methods have been proposed to enhance the quality of prompts, these methods often face optimization restrictions due to prompt initialization, which can significantly constrain the exploration domain and potentially lead to suboptimal solutions. To eliminate the reliance on the initial prompt, we shift our perspective towards the generative model, framing the prompt-tuning process as a form of conditional generative modeling, where prompts are generated from random noise. Our innovation, the Prompt Diffuser, leverages a conditional diffusion model to produce prompts of exceptional quality. Central to our framework is the approach to trajectory reconstruction and the meticulous integration of downstream task guidance during the training phase. Further experimental results underscore the potency of the Prompt Diffuser as a robust and effective tool for the prompt-tuning process, demonstrating strong performance in the meta-RL tasks.

📄 PDF Abstract BibTeX arXiv:2411.01168

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning (RL)

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

Diffusion Policy Policy Optimization

2024-09-01 · Allen Z. Ren, Justin Lidard, Lars L. Ankile, Anthony Simeonov 외

We introduce Diffusion Policy Policy Optimization, DPPO, an algorithmic framework including best practices for fine-tuning diffusion-based policies (e.g. Diffusion Policy) in continuous control and robot learning tasks u…

continuous-controlContinuous ControlReinforcement Learning (RL)

FIND: Fine-tuning Initial Noise Distribution with Policy Optimization for Diffusion Models

2024-07-28 · Changgu Chen, Libing Yang, Xiaoyan Yang, Lianggangxu Chen 외

In recent years, large-scale pre-trained diffusion models have demonstrated their outstanding capabilities in image and video generation tasks. However, existing models tend to produce visual objects commonly found in th…

DenoisingVideo Generation

Ada-adapter:Fast Few-shot Style Personlization of Diffusion Model with Pre-trained Image Encoder

2024-07-08 · Jia Liu, Changlin Li, Qirui Sun, Jiahui Ming 외

Fine-tuning advanced diffusion models for high-quality image stylization usually requires large training datasets and substantial computational resources, hindering their practical applicability. We propose Ada-Adapter, …

DiversityImage StylizationStyle Transfer

Zero-Shot Video Deraining with Video Diffusion Models

2025-11-23 · Tuomas Varanka, Juan Luis Gonzalez, Hyeongwoo Kim, Pablo Garrido 외 arxiv

Existing video deraining methods are often trained on paired datasets, either synthetic, which limits their ability to generalize to real-world rain, or captured by static cameras, which restricts their effectiveness in …

Video deraining

BLIP-Diffusion: Pre-trained Subject Representation for Controllable Text-to-Image Generation and Editing

2023-05-24 · NeurIPS 2023 11 · Dongxu Li, Junnan Li, Steven C. H. Hoi

Subject-driven text-to-image generation models create novel renditions of an input subject based on text prompts. Existing models suffer from lengthy fine-tuning and difficulties preserving the subject fidelity. To overc…

Image GenerationPersonalized Image GenerationRepresentation LearningText to Image Generation+1