OSP-Next: Efficient High-Quality Video Generation with Sparse Sequence Parallelism, HiF8 Quantization, and Reinforcement Learning

Documenti analoghi

• FlashI2V: Fourier-Guided Latent Shifting Prevents Conditional Image Leakage in Image-to-Video Generation
  di: Ge, Yunyang, et al.
  Pubblicazione: (2025)
• SwapAnyone: Consistent and Realistic Video Synthesis for Swapping Any Person into Any Video
  di: Zhao, Chengshu, et al.
  Pubblicazione: (2025)
• HiF-DTA: Hierarchical Feature Learning Network for Drug-Target Affinity Prediction
  di: Li, Minghui, et al.
  Pubblicazione: (2025)
• UniWorld-V1: High-Resolution Semantic Encoders for Unified Visual Understanding and Generation
  di: Lin, Bin, et al.
  Pubblicazione: (2025)
• HiF-VLA: Hindsight, Insight and Foresight through Motion Representation for Vision-Language-Action Models
  di: Lin, Minghui, et al.
  Pubblicazione: (2025)