T$^\star$: Progressive Block Scaling for Masked Diffusion Language Models Through Trajectory Aware Reinforcement Learning

Documenti analoghi

• Latent Poincaré Shaping for Agentic Reinforcement Learning
  di: Xia, Hanchen, et al.
  Pubblicazione: (2026)
• BARD: Bridging AutoRegressive and Diffusion Vision-Language Models Via Highly Efficient Progressive Block Merging and Stage-Wise Distillation
  di: Chen, Baoyou, et al.
  Pubblicazione: (2026)
• TRIMS: Trajectory-Ranked Instruction Masked Supervision for Diffusion Language Models
  di: Chen, Lingjie, et al.
  Pubblicazione: (2026)
• Taming Masked Diffusion Language Models via Consistency Trajectory Reinforcement Learning with Fewer Decoding Step
  di: Yang, Jingyi, et al.
  Pubblicazione: (2025)
• Route-and-Reason: Scaling Large Language Model Reasoning with Reinforced Model Router
  di: Shao, Chenyang, et al.
  Pubblicazione: (2025)