Papers

• The First Token Knows: Single-Decode Confidence for Hallucination Detection (2026)
  Mina Gabriel
  1.89
• VLM-R1: A Stable and Generalizable R1-style Large Vision-Language Model (2025)
  Haozhan Shen et al.
  1.28
• Bridging Supervised Learning and Reinforcement Learning in Math Reasoning (2025)
  Huayu Chen et al.
  1.28
• GCPO: When Contrast Fails, Go Gold (2025)
  Hao Wu et al.
  1.28
• Iterative Graph Alignment (2024)
  Fangyuan Yu et al.
  —