Remix-DiT: Mixing Diffusion Transformers for Multi-Expert Denoising

Authors: Gongfan Fang, Xinyin Ma, Xinchao Wang

NeurIPS 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Experiments conducted on the Image Net dataset demonstrate that Remix Di T achieves promising results compared to standard diffusion transformers and other multiple-expert methods.
Researcher Affiliation Academia Gongfan Fang Xinyin Ma Xinchao Wang National University of Singapore {gongfan,maxinyin}@u.nus.edu, xinchao@nus.edu.sg
Pseudocode Yes Algorithm 1 Mixed Linear (Py Torch-like Pseudo Code) Algorithm 2 Remix-Di T
Open Source Code Yes Code is available in the supplemental material.
Open Datasets Yes Experiments conducted on the Image Net dataset demonstrate that Remix Di T achieves promising results compared to standard diffusion transformers and other multiple-expert methods.
Dataset Splits No The paper does not explicitly provide train/validation/test dataset splits with percentages or counts.
Hardware Specification No The paper mentions 'GPU Mem. (Mi B)' in Table 3 but does not specify the exact GPU models, CPU models, or other specific hardware components used for the experiments.
Software Dependencies No The paper mentions 'Py Torch-like Pseudo Code' but does not specify any software names with version numbers for libraries or environments.
Experiment Setup Yes In our experiments, we conducted 100 K fine-tuning on Di T-S/B/L models [29], pre-trained for 2M/1M/1M steps correspondingly.