BARD: Bridging AutoRegressive and Diffusion Vision-Language Models Via Highly Efficient Progressive Block Merging and Stage-Wise Distillation

Documenti analoghi

• T$^\star$: Progressive Block Scaling for Masked Diffusion Language Models Through Trajectory Aware Reinforcement Learning
  di: Xia, Hanchen, et al.
  Pubblicazione: (2026)
• Implementing Adaptations for Vision AutoRegressive Model
  di: Shaikh, Kaif, et al.
  Pubblicazione: (2025)
• Nested AutoRegressive Models
  di: Wu, Hongyu, et al.
  Pubblicazione: (2025)
• Inference-Time Scaling for Visual AutoRegressive modeling by Searching Representative Samples
  di: Tang, Weidong, et al.
  Pubblicazione: (2026)
• Resurrect Mask AutoRegressive Modeling for Efficient and Scalable Image Generation
  di: Xin, Yi, et al.
  Pubblicazione: (2025)