paper-with-me

홈 › Papers

Marrying Autoregressive Transformer and Diffusion with Multi-Reference Autoregression

2025-06-11 · Dingcheng Zhen, Qian Qiao, Tan Yu, Kangxi Wu, Ziwei Zhang, Siyuan Liu, Shunshun Yin, Ming Tao

We introduce TransDiff, the first image generation model that marries Autoregressive (AR) Transformer with diffusion models. In this joint modeling framework, TransDiff encodes labels and images into high-level semantic features and employs a diffusion model to estimate the distribution of image samples. On the ImageNet 256x256 benchmark, TransDiff significantly outperforms other image generation models based on standalone AR Transformer or diffusion models. Specifically, TransDiff achieves a Fr\'echet Inception Distance (FID) of 1.61 and an Inception Score (IS) of 293.4, and further provides x2 faster inference latency compared to state-of-the-art methods based on AR Transformer and x112 faster inference compared to diffusion-only models. Furthermore, building on the TransDiff model, we introduce a novel image generation paradigm called Multi-Reference Autoregression (MRAR), which performs autoregressive generation by predicting the next image. MRAR enables the model to reference multiple previously generated images, thereby facilitating the learning of more diverse representations and improving the quality of generated images in subsequent iterations. By applying MRAR, the performance of TransDiff is improved, with the FID reduced from 1.61 to 1.42. We expect TransDiff to open up a new frontier in the field of image generation.

📄 PDF Abstract BibTeX arXiv:2506.09482

Code (1)

transdiff/transdiff 공식 구현 pytorch

Tasks

Image Generation

Methods 이 논문이 사용한 방법론

Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Transformer A Transformer is a model architecture that eschews recurrence and instead relies entirely on an [attention…

Similar Papers 제목 키워드 기반

DiT as Real-Time Rerenderer: Streaming Video Stylization with Autoregressive Diffusion Transformer

2026-04-15 · Hengye Lyu, Zisu Li, Yue Hong, Yueting Weng 외 arxiv

Recent advances in video generation models has significantly accelerated video generation and related downstream tasks. Among these, video stylization holds important research value in areas such as immersive application…

Video Generation

DiTAR: Diffusion Transformer Autoregressive Modeling for Speech Generation

2025-02-06 · Dongya Jia, Zhuo Chen, Jiawei Chen, Chenpeng Du 외

Several recent studies have attempted to autoregressively generate continuous speech representations without discrete speech tokens by combining diffusion and autoregressive models, yet they often face challenges with ex…

DiversityLanguage ModelingLanguage Modelling

ACDiT: Interpolating Autoregressive Conditional Modeling and Diffusion Transformer

2024-12-10 · Jinyi Hu, Shengding Hu, Yuxuan Song, Yufei Huang 외

The recent surge of interest in comprehensive multimodal models has necessitated the unification of diverse modalities. However, the unification suffers from disparate methodologies. Continuous visual generation necessit…

DenoisingImage GenerationVideo Generation

Diffusion Glancing Transformer for Parallel Sequence to Sequence Learning

2022-12-20 · Lihua Qian, Mingxuan Wang, Yang Liu, Hao Zhou

Previously, non-autoregressive models were widely perceived as being superior in generation efficiency but inferior in generation quality due to the difficulties of modeling multiple target modalities. To enhance the mul…

Knowledge DistillationMachine TranslationText Generation

Attention Sinks in Diffusion Transformers: A Causal Analysis

2026-05-10 · Fangzheng Wu, Brian Summa arxiv

Attention sinks -- tokens that receive disproportionate attention mass -- are assumed to be functionally important in autoregressive language models, but their role in diffusion transformers remains unclear. We present a…