SALAD: Achieve High-Sparsity Attention via Efficient Linear Attention Tuning for Video Diffusion Transformer

Documenti analoghi

• DiTFastAttn: Attention Compression for Diffusion Transformer Models
  di: Yuan, Zhihang, et al.
  Pubblicazione: (2024)
• VocabTailor: Dynamic Vocabulary Selection for Downstream Tasks in Small Language Models
  di: Zhang, Hanling, et al.
  Pubblicazione: (2025)
• ViDiT-Q: Efficient and Accurate Quantization of Diffusion Transformers for Image and Video Generation
  di: Zhao, Tianchen, et al.
  Pubblicazione: (2024)
• LiteVAR: Compressing Visual Autoregressive Modelling with Efficient Attention and Quantization
  di: Xie, Rui, et al.
  Pubblicazione: (2024)
• SLA: Beyond Sparsity in Diffusion Transformers via Fine-Tunable Sparse-Linear Attention
  di: Zhang, Jintao, et al.
  Pubblicazione: (2025)