ODE$_t$(ODE$_l$): Shortcutting the Time and the Length in Diffusion and Flow Models for Faster Sampling

Documenti analoghi

• Proxy3D: Efficient 3D Representations for Vision-Language Models via Semantic Clustering and Alignment
  di: Jiang, Jerry, et al.
  Pubblicazione: (2026)
• Split-Ensemble: Efficient OOD-aware Ensemble via Task and Model Splitting
  di: Chen, Anthony, et al.
  Pubblicazione: (2023)
• ContextFlow++: Generalist-Specialist Flow-based Generative Models with Mixed-Variable Context Encoding
  di: Gudovskiy, Denis, et al.
  Pubblicazione: (2024)
• DFM: Interpolant-free Dual Flow Matching
  di: Gudovskiy, Denis, et al.
  Pubblicazione: (2024)
• SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference
  di: Zhang, Yuan, et al.
  Pubblicazione: (2024)