類似資料

• ConciseHint: Boosting Efficient Reasoning via Continuous Concise Hints during Generation
  著者:: Tang, Siao, 等
  出版事項: (2025)
• In-Video Instructions: Visual Signals as Generative Control
  著者:: Fang, Gongfan, 等
  出版事項: (2025)
• Remix-DiT: Mixing Diffusion Transformers for Multi-Expert Denoising
  著者:: Fang, Gongfan, 等
  出版事項: (2024)
• Collaborative Decoding Makes Visual Auto-Regressive Modeling Efficient
  著者:: Chen, Zigeng, 等
  出版事項: (2024)
• TinyFusion: Diffusion Transformers Learned Shallow
  著者:: Fang, Gongfan, 等
  出版事項: (2024)