When to Commit? Towards Variable-Size Self-Contained Blocks for Discrete Diffusion Language Models

Ähnliche Einträge

• Text Meets Topology: Rethinking Out-of-distribution Detection in Text-Rich Networks
  von: Wang, Danny, et al.
  Veröffentlicht: (2025)
• Block-R1: Rethinking the Role of Block Size in Multi-domain Reinforcement Learning for Diffusion Large Language Models
  von: Jiang, Yan, et al.
  Veröffentlicht: (2026)
• TRN-R1-Zero: Text-rich Network Reasoning via LLMs with Reinforcement Learning Only
  von: Liu, Yilun, et al.
  Veröffentlicht: (2026)
• Break the Block: Dynamic-size Reasoning Blocks for Diffusion Large Language Models via Monotonic Entropy Descent with Reinforcement Learning
  von: Jiang, Yan, et al.
  Veröffentlicht: (2026)
• When Does a Language Model Commit? A Finite-Answer Theory of Pre-Verbalization Commitment
  von: Zhang, Long, et al.
  Veröffentlicht: (2026)