Diffusion Transformer

Also known as DiT

Follow this topic Ask about this topic

Momentum

35 papers in the last four weeks, up 169% on the four weeks before. 0.3% of all new papers.

Jul 13Week of Sep 28

Latest papers 297

All topics

Breaking the Lock-in: Diversifying Text-to-Image Generation via Representation Modulation
Jun 5, 2026Dahee Kwon, Haeun Lee, Jaesik ChoiDiffusion Transformer T2I Generation
Korea Advanced Institute of Science and Technology (KAIST) · INEEJI
RhymeFlow: Training-Free Acceleration for Video Generation with Asynchronous Denoising Flow Scheduling
Jun 4, 2026Chensheng Dai, Shengjun Zhang, Yifan Li +3Video Diffusion Models Diffusion Transformer
1Tsinghua University · 2GigaAI
Style-CCL: Content-Preserving Style Transfer via Curriculum Continual Learning
Jun 4, 2026Shiwen Zhang, Haoyuan Wang, Xianghao Zang +3Diffusion Transformer Continual Learning
Institute of Artificial Intelligence (TeleAI), China Telecom.
Multimodal Action Diffusion for Robust End-to-End Autonomous Driving
Jun 1, 2026Jorge Daniel Rodríguez-Vidal, Diego Porres, Gabriel Villalonga Pineda +1Diffusion Transformer End-to-End Autonomous Driving
Computer Vision Center (CVC) Barcelona, Spain · Universitat Autònoma de Barcelona (UAB) Barcelona, Spain
FocusDiT: Masking Queries in Diffusion Transformers for Fine-grained Image Generation
Jun 1, 2026Xueji Fang, Liyuan Ma, Jianhao Zeng +3Diffusion Transformer Image Generation
Zhejiang University · Westlake University · Hangzhou, China
Chameleon: Style-Content Disentangled Framework for Cross-Domain Object Compositing
May 31, 2026Sukhun Ko, Jeahun Sung, Soo Ye Kim +1Diffusion Transformer Compositional Image Generation
CMLab, Chung-Ang University · Adobe Research
MedSyn2: Flexible Control of 3D CT Generation via Text and Semantically-Defined Segmentation Prompts
May 31, 2026Weicheng Dai, Chenyu Wang, Binxu Li +4Diffusion Transformer Conditional Image Generation
Boston University School of Engineering, Boston, MA, USA · Stanford University · University of Pittsburgh Medical Center +1
COLLAR: Cascaded Object-Level Latent Refinement for High-Fidelity Conditional Generation
May 31, 2026Xinlong Zhang, Jia Wei, Xiaoyu Zhang +3Diffusion Transformer Conditional Diffusion Models
College of Computer Science Zhejiang University Hangzhou, Zhejiang, China
Improving Visual Representation Alignment Generation with GRPO
May 30, 2026Shentong Mo, Sukmin YunDiffusion Model Alignment Diffusion Transformer
Carnegie Mellon University · Hanyang University
UniVerse: A Unified Modulation Framework for Segmentation-Free,Disentangled Multi-Concept Personalization
May 29, 2026Quynh Phung, Sandesh Ghimire, Minsi Hu +2Diffusion Transformer Image Generation
University of Maryland, College Park · Qualcomm Technologies, Inc.
TunerDiT: Training-free Progressive Steering of Diffusion Transformer for Multi-Event Video Generation
May 29, 2026Ruotong Liao, Guowen Huang, Qing Cheng +6Diffusion Transformer Text-to-Video Generation
Ludwig Maximilian University of Munich · MCML · Technical University of Munich +2
Towards Streaming Synchronized Spatial Audio Generation via Autoregressive Diffusion Transformer
May 29, 2026Ke Lei, Yu Zhang, Changhao Pan +4Text-to-Audio Generation Audio-Video Generation
1Zhejiang University, China · 2ByteDance
SANA-Streaming: Real-time Streaming Video Editing with Hybrid Diffusion Transformer
May 28, 2026Yuyang Zhao, Yicheng Pan, Qiyuan He +6Diffusion Transformer Streaming Video Generation
1NVIDIA · 3THU · 4NUS +2
Veda: Scalable Video Diffusion via Distilled Sparse Attention
May 28, 2026Shihao Han, Hao Yang, Xinting Hu +3Video Diffusion Models Diffusion Transformer
ByteDance Inc. · University of Science and Technology of China · The University of Hong Kong
Robust and Generalizable Safety Steering for Text-to-Image Diffusion Transformers
May 28, 2026Zihao Xue, Yan Wang, Zhen Bi +7Diffusion Transformer Domain Generalization
1Huzhou Normal University · 2Alibaba Group · University of Science and Technology of China +2
PARE: Pruning and Adaptive Routing for Efficient Video Generation
May 26, 2026Yutong Wang, Yunke Wang, Tianfan Xue +4Video Diffusion Models Diffusion Transformer
The University of Sydney · The Chinese University of Hong Kong · Shanghai AI Laboratory
MRT: Masked Region Transformer for Layered Image Generation and Editing at Scale
May 26, 2026Zhicong Tang, Zhao Zhang, Jingye Chen +6Diffusion Transformer Image Generation
Canva Research
Equivalent Flows, Unequal Learning: Clean-Latent Prediction in Transformers
May 26, 2026Funing Fu, Tenghui Wang, Guanyu Zhou +2Flow Matching Diffusion Transformer
Independent Researcher · Wuhan University of Technology · Hangzhou Jiyi Artificial Intelligence Co., Ltd.
SoftCap: Soft-Budget Control for Diffusion Transformer Acceleration
May 26, 2026Yuhang Zhang, Junxiang Qiu, Huixia Ben +3Diffusion Transformer Diffusion Model Caching
Hefei University of Technology · University of Science and Technology of China · Anhui University of Science and Technology +1
Timestep-Aware SVDQuant-GPTQ for W4A4 Quantization of Wan2.2-I2V
May 26, 2026Junhao Wu, Dezhong Yao, Hai JinVideo Diffusion Models Diffusion Transformer
School of Computer Science and Technology, Huazhong University of Science and Technology Wuhan, Hubei, China 430074
RT-Lynx: Putting the GEMM Sparsity In a Right Way for Diffusion Models
May 26, 2026Xing Cong, Hanlin Tang, Kan Liu +3Diffusion Transformer Activation Sparsity
1Alibaba Group · 2Independent Researcher
Where Concept Erasure Should Occur: Concept-Layer Alignment in Text-to-Video Diffusion Models
May 25, 2026Yiwei Xie, Ping Liu, Zheng ZhangVideo Diffusion Models Diffusion Transformer
The School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan 430074, China · Department of Computer Science and Engineering, University of Nevada, Reno, NV, USA.
Diffusion Image Generation with Explicit Modeling of Data Manifold Geometry
May 25, 2026Duoduo Xue, Zhiyu Zhu, Junhui HouDiffusion Transformer Diffusion Model Sampling
Department of Computer Science, City University of Hong Kong, China · City University of Hong Kong (Dongguan), China
Blocked Gibbs meets Diffusion Transformers: Unsupervised Learning for Constraint Optimization
May 24, 2026Yudong W. Xu, Wenhao Li, Xiaoyu Wang +2Diffusion Transformer Constrained Optimization
University of Toronto · Vector Institute
Trajectory-Consistent Calibration for Cache-Accelerated Diffusion Models
May 24, 2026Mingyu Liang, Dingkun Xu, Jingwei XuDiffusion Transformer Diffusion-Based Image Generation
Laboratory for Novel Software Technology, Nanjing University, China
Reasoning to Align: Implicit Reasoning in Diffusion Transformers for Video Editing
May 23, 2026Yan Li, Lin Liu, Xiaopeng Zhang +1Video Diffusion Models Diffusion Transformer
†The Hongkong University of Science and Technology · ‡Huawei Inc.
DFSAttn: Dynamic Fine-grained Sparse Attention for Efficient Video Generation
May 22, 2026Jie Hu, Zixiang Gao, Yutong He +1Video Diffusion Models Diffusion Transformer
1Peking University.
SEGA: Spectral-Energy Guided Attention for Resolution Extrapolation in Diffusion Transformers
May 21, 2026Javad Rajabi, Kimia Shaban, Koorosh Roohi +2Rotary Positional Embeddings Diffusion Model Guidance
University of Toronto · Vector Institute
ORBIS: Output-Guided Token Reduction with Distribution-Aware Matching for Video Diffusion Acceleration
May 21, 2026Hangyeol Lee, Joo-Young KimToken Merging Video Diffusion Models
KAIST · Daejeon, South Korea
Rethinking Token Reduction for Diffusion Models via Output-Similarity-Awareness
May 21, 2026Hangyeol Lee, Hyojeong Lee, Joo-Young KimDiffusion Transformer Diffusion-Based Image Generation
KAIST, Daejeon, Republic of Korea

Jun 5, 2026, cs.CVJ/K move · Enter open · S save

Breaking the Lock-in: Diversifying Text-to-Image Generation via Representation Modulation

Dahee Kwon, Haeun Lee, Jaesik Choi

Korea Advanced Institute of Science and Technology (KAIST) · INEEJI

Diffusion Transformer T2I Generation

Open paper AskPDF arXiv

Recent text-to-image models built on large-scale Transformer backbones and flow-based objectives deliver strong text-image alignment and high visual quality, yet often produce overly similar samples under a fixed prompt. Existing diversity-enhancement methods alleviate this issue, but typically require expensive sampling or auxiliary optimization, incurring non-trivial overhead. To investigate the root cause of this homogeneity, we examine intermediate Transformer features and observe that the zero-frequency spatial average (DC) component rapidly converges across seeds early in generation, causing early trajectory lock-in that limits downstream variation. Building on this observation, we propose DC Attenuation for diVersity Enhancement (DAVE), a training-free representation-level intervention that selectively attenuates this component in the early regime. DAVE preserves the sampling pipeline with negligible overhead, improving prompt-consistent diversity while maintaining competitive image quality.

Momentum

Related topics

Latest papers 297