Imagen de Portada

HarmoniCa: Harmonizing Training and Inference for Better Feature Caching in Diffusion Transformer Acceleration

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Huang, Yushi, Wang, Zining, Gong, Ruihao, Liu, Jing, Zhang, Xinjie, Guo, Jinyang, Liu, Xianglong, Zhang, Jun
Formato:	Preprint
Publicado:	2024
Materias:	Computer Vision and Pattern Recognition
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

MoDES: Accelerating Mixture-of-Experts Multimodal Large Language Models via Dynamic Expert Skipping
por: Huang, Yushi, et al.
Publicado: (2025)

PTSBench: A Comprehensive Post-Training Sparsity Benchmark Towards Algorithms and Models
por: Wnag, Zining, et al.
Publicado: (2024)

TFMQ-DM: Temporal Feature Maintenance Quantization for Diffusion Models
por: Huang, Yushi, et al.
Publicado: (2023)

Temporal Feature Matters: A Framework for Diffusion Model Quantization
por: Huang, Yushi, et al.
Publicado: (2024)

SpeCa: Accelerating Diffusion Transformers with Speculative Feature Caching
por: Liu, Jiacheng, et al.
Publicado: (2025)

Fast and Controllable Post-training Sparsity: Learning Optimal Sparsity Allocation with Global Constraint in Minutes
por: Gong, Ruihao, et al.
Publicado: (2024)

Accelerating Diffusion Transformers with Token-wise Feature Caching
por: Zou, Chang, et al.
Publicado: (2024)

Focus-dLLM: Accelerating Long-Context Diffusion LLM Inference via Confidence-Guided Context Focusing
por: Long, Lingkun, et al.
Publicado: (2026)

DisCa: Accelerating Video Diffusion Transformers with Distillation-Compatible Learnable Feature Caching
por: Zou, Chang, et al.
Publicado: (2026)

Collaborative Few-Step Distillation and Low-Bit Quantization for Wan2.2 Dual-Expert Video Diffusion Models
por: Du, Jinyang, et al.
Publicado: (2026)

Rethinking Token-wise Feature Caching: Accelerating Diffusion Transformers with Dual Feature Caching
por: Zou, Chang, et al.
Publicado: (2024)

A Survey of Low-bit Large Language Models: Basics, Systems, and Algorithms
por: Gong, Ruihao, et al.
Publicado: (2024)

LinVideo: A Post-Training Framework towards O(n) Attention in Efficient Video Generation
por: Huang, Yushi, et al.
Publicado: (2025)

SmoothCache: A Universal Inference Acceleration Technique for Diffusion Transformers
por: Liu, Joseph, et al.
Publicado: (2024)

SGMD: Score Gradient Matching Distillation for Few-Step Video Diffusion Distillation
por: Wu, Zhuguanyu, et al.
Publicado: (2026)

Light Forcing: Accelerating Autoregressive Video Diffusion via Sparse Attention
por: Lv, Chengtao, et al.
Publicado: (2026)

AB-Cache: Training-Free Acceleration of Diffusion Models via Adams-Bashforth Cached Feature Reuse
por: Yu, Zichao, et al.
Publicado: (2025)

Relational Feature Caching for Accelerating Diffusion Transformers
por: Son, Byunggwan, et al.
Publicado: (2026)

LLMC: Benchmarking Large Language Model Quantization with a Versatile Compression Toolkit
por: Gong, Ruihao, et al.
Publicado: (2024)

QVGen: Pushing the Limit of Quantized Video Generative Models
por: Huang, Yushi, et al.
Publicado: (2025)

Beyond Few-Step Inference: Accelerating Video Diffusion Transformer Model Serving with Inter-Request Caching Reuse
por: Liu, Hao, et al.
Publicado: (2026)

FreqCa: Accelerating Diffusion Models via Frequency-Aware Caching
por: Liu, Jiacheng, et al.
Publicado: (2025)

Token Caching for Diffusion Transformer Acceleration
por: Lou, Jinming, et al.
Publicado: (2024)

Self-transcendence: Is External Feature Guidance Indispensable for Accelerating Diffusion Transformer Training?
por: Sun, Lingchen, et al.
Publicado: (2026)

ProCache: Constraint-Aware Feature Caching with Selective Computation for Diffusion Transformer Acceleration
por: Cao, Fanpu, et al.
Publicado: (2025)

U-Harmony: Enhancing Joint Training for Segmentation Models with Universal Harmonization
por: Ma, Weiwei, et al.
Publicado: (2026)

HarmoniDiff-RS: Training-Free Diffusion Harmonization for Satellite Image Composition
por: Zhuang, Xiaoqi, et al.
Publicado: (2026)

Token Pruning for Caching Better: 9 Times Acceleration on Stable Diffusion for Free
por: Zhang, Evelyn, et al.
Publicado: (2024)

PTQ4SAM: Post-Training Quantization for Segment Anything
por: Lv, Chengtao, et al.
Publicado: (2024)

BWTA: Accurate and Efficient Binarized Transformer by Algorithm-Hardware Co-design
por: Ding, Yifu, et al.
Publicado: (2026)

Salt: Self-Consistent Distribution Matching with Cache-Aware Training for Fast Video Generation
por: Ge, Xingtong, et al.
Publicado: (2026)

Accelerating Diffusion Transformer via Gradient-Optimized Cache
por: Qiu, Junxiang, et al.
Publicado: (2025)

Accelerating Diffusion Transformer via Error-Optimized Cache
por: Qiu, Junxiang, et al.
Publicado: (2025)

Let Features Decide Their Own Solvers: Hybrid Feature Caching for Diffusion Transformers
por: Zheng, Shikang, et al.
Publicado: (2025)

Exploiting Defenses against GAN-Based Feature Inference Attacks in Federated Learning
por: Luo, Xinjian, et al.
Publicado: (2020)

Forecast then Calibrate: Feature Caching as ODE for Efficient Diffusion Transformers
por: Zheng, Shikang, et al.
Publicado: (2025)

Compute Only 16 Tokens in One Timestep: Accelerating Diffusion Transformers with Cluster-Driven Feature Caching
por: Zheng, Zhixin, et al.
Publicado: (2025)

Learning-to-Cache: Accelerating Diffusion Transformer via Layer Caching
por: Ma, Xinyin, et al.
Publicado: (2024)

LLMC+: Benchmarking Vision-Language Model Compression with a Plug-and-play Toolkit
por: Lv, Chengtao, et al.
Publicado: (2025)

Window-Diffusion: Accelerating Diffusion Language Model Inference with Windowed Token Pruning and Caching
por: Zuo, Fengrui, et al.
Publicado: (2026)