BackPlay: Head-Only Look-Back Self-Correction for Diffusion Language Models

Documenti analoghi

• A Minimalist Example of Edge-of-Stability and Progressive Sharpening
  di: Liu, Liming, et al.
  Pubblicazione: (2025)
• Self-Rewarding PPO: Aligning Large Language Models with Demonstrations Only
  di: Zhang, Qingru, et al.
  Pubblicazione: (2025)
• Diffusion Model for Manifold Data: Score Decomposition, Curvature, and Statistical Complexity
  di: Zhang, Zixuan, et al.
  Pubblicazione: (2026)
• Look-Back: Implicit Visual Re-focusing in MLLM Reasoning
  di: Yang, Shuo, et al.
  Pubblicazione: (2025)
• FBQuant: FeedBack Quantization for Large Language Models
  di: Liu, Yijiang, et al.
  Pubblicazione: (2025)