Towards Stabilized and Efficient Diffusion Transformers through Long-Skip-Connections with Spectral Constraints

Documenti analoghi

• Flash-DMD: Towards High-Fidelity Few-Step Image Generation with Efficient Distillation and Joint Reinforcement Learning
  di: Chen, Guanjie, et al.
  Pubblicazione: (2025)
• From Head to Tail: Towards Balanced Representation in Large Vision-Language Models through Adaptive Data Calibration
  di: Song, Mingyang, et al.
  Pubblicazione: (2025)
• DiffThinker: Towards Generative Multimodal Reasoning with Diffusion Models
  di: He, Zefeng, et al.
  Pubblicazione: (2025)
• SURf: Teaching Large Vision-Language Models to Selectively Utilize Retrieved Information
  di: Sun, Jiashuo, et al.
  Pubblicazione: (2024)
• Step-level Reward for Free in RL-based T2I Diffusion Model Fine-tuning
  di: Liao, Xinyao, et al.
  Pubblicazione: (2025)