paper-with-me

홈 › Papers

MonoFormer: One Transformer for Both Diffusion and Autoregression

2024-09-24 · Chuyang Zhao, Yuxing Song, Wenhao Wang, Haocheng Feng, Errui Ding, Yifan Sun, Xinyan Xiao, Jingdong Wang

Most existing multimodality methods use separate backbones for autoregression-based discrete text generation and diffusion-based continuous visual generation, or the same backbone by discretizing the visual data to use autoregression for both text and visual generation. In this paper, we propose to study a simple idea: share one transformer for both autoregression and diffusion. The feasibility comes from two main aspects: (i) Transformer is successfully applied to diffusion for visual generation, and (ii) transformer training for autoregression and diffusion is very similar, and the difference merely lies in that diffusion uses bidirectional attention mask and autoregression uses causal attention mask. Experimental results show that our approach achieves comparable image generation performance to current state-of-the-art methods as well as maintains the text generation capability. The project is publicly available at https://monoformer.github.io/.

📄 PDF Abstract BibTeX arXiv:2409.16280

Code (1)

MonoFormer/MonoFormer 공식 구현 pytorch

Tasks

Image GenerationText Generation

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Position-Wise Feed-Forward Layer 설명 없음
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…
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…
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
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 $x$…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…

Similar Papers 제목 키워드 기반

Deep Digging into the Generalization of Self-Supervised Monocular Depth Estimation

2022-05-23 · Jinwoo Bae, Sungho Moon, Sunghoon Im

Self-supervised monocular depth estimation has been widely studied recently. Most of the work has focused on improving performance on benchmark datasets, such as KITTI, but has offered a few experiments on generalization…

Depth EstimationMonocular Depth Estimation

Marrying Autoregressive Transformer and Diffusion with Multi-Reference Autoregression

2025-06-11 · Dingcheng Zhen, Qian Qiao, Tan Yu, Kangxi Wu 외

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 …

Image Generation

A Spark of Vision-Language Intelligence: 2-Dimensional Autoregressive Transformer for Efficient Finegrained Image Generation

2024-10-02 · Liang Chen, Sinan Tan, Zefan Cai, Weichu Xie 외

This work tackles the information loss bottleneck of vector-quantization (VQ) autoregressive image generation by introducing a novel model architecture called the 2-Dimensional Autoregression (DnD) Transformer. The DnD-T…

Image GenerationQuantization

FREE: Uncertainty-Aware Autoregression for Parallel Diffusion Transformers

2025-11-25 · Xinwan Wen, Bowen Li, Jiajun Luo, Ye Li 외 arxiv

Diffusion Transformers (DiTs) achieve state-of-the-art generation quality but require long sequential denoising trajectories, leading to high inference latency. Recent speculative inference methods enable lossless parall…

End-to-End Multi-Modal Diffusion Mamba

2025-10-15 · Chunhao Lu, Qiang Lu, Meichen Dong, Jake Luo arxiv

Current end-to-end multi-modal models utilize different encoders and decoders to process input and output information. This separation hinders the joint representation learning of various modalities. To unify multi-modal…

Visual Question AnsweringComputational EfficiencyRepresentation LearningImage Captioning