ReDi: Efficient Learning-Free Diffusion Inference via Trajectory Retrieval

2023-02-05 · Kexun Zhang, Xianjun Yang, William Yang Wang, Lei LI

Diffusion models show promising generation capability for a variety of data. Despite their high generation quality, the inference for diffusion models is still time-consuming due to the numerous sampling iterations required. To accelerate the inference, we propose ReDi, a simple yet learning-free Retrieval-based Diffusion sampling framework. From a precomputed knowledge base, ReDi retrieves a trajectory similar to the partially generated trajectory at an early stage of generation, skips a large portion of intermediate steps, and continues sampling from a later step in the retrieved trajectory. We theoretically prove that the generation performance of ReDi is guaranteed. Our experiments demonstrate that ReDi improves the model inference efficiency by 2x speedup. Furthermore, ReDi is able to generalize well in zero-shot cross-domain image generation such as image stylization.

📄 PDF Abstract BibTeX arXiv:2302.02285

Code (1)

zkx06111/rediffusion 공식 구현 pytorch

Tasks

Image GenerationImage StylizationRetrieval

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…

Self-Augmenting Retrieval for Diffusion Language Models

2026-06-04 · Paul Jünger, Justin Lovelace, Linxi Zhao, Dongyoung Go 외 arxiv

Discrete diffusion language models generate text by iteratively denoising an entire response in parallel. At each step, they predict tentative tokens for every masked position, committing the confident predictions to the…

DISK: Dynamic Inference SKipping for World Models

2026-01-31 · Anugunj Naman, Gaibo Zhang, Ayushman Singh, Yaguang Zhang arxiv

We present DISK, a training-free adaptive inference method for autoregressive world models. DISK coordinates two coupled diffusion transformers for video and ego-trajectory via dual-branch controllers with cross-modal sk…

Trajectory Prediction

LAGO Policy: Latency-Aware Asynchronous Diffusion Policies with Goal-Directed Collision-Free Planning for Smooth Manipulation

2026-06-16 · Guowei Shi, Xupeng Xie, Yiming Luo, Jian Guo 외 arxiv

Diffusion-based visuomotor policies deployed with asynchronous inference often exhibit inter-chunk discontinuities and lack explicit mechanisms for obstacle-aware execution, leading to jerky motions and collisions that h…

Trajectory Planning

EmbodiedDiffusion: End-to-End Traversability-Guided Visual Diffusion for Heterogeneous Robot Navigation

2025-12-02 · Iana Zhura, Sausar Karaf, Faryal Batool, Nipun Dhananjaya Weerakkodi Mudalige 외 arxiv

Visual traversability estimation is central to autonomous navigation, yet most approaches either rely on prompt-driven Vision-Language Model (VLM) or decouple traversability from trajectory planning, requiring separate p…

Prompt Engineering

Behavioral Score Diffusion: Model-Free Trajectory Planning via Kernel-Based Score Estimation from Data

2026-04-01 · Shihao Li, Jiachen Li, Jiamin Xu, Dongmei Chen arxiv

Diffusion-based trajectory optimization has emerged as a powerful planning paradigm, but existing methods require either learned score networks trained on large datasets or analytical dynamics models for score computatio…