Papers

• NanoVDR: Distilling a 2B Vision-Language Retriever into a 70M Text-Only Encoder for Visual Document Retrieval (2026)
  Zhuchenyang Liu et al.
  1.94
• Anti-Self-Distillation for Reasoning RL via Pointwise Mutual Information (2026)
  Guobin Shen et al.
  1.94
• RUBRIC-ARROW: Alternating Pointwise Rubric Reward Modeling for LLM Post-training in Non-verifiable Domains (2026)
  Haoxiang Jiang et al.
  1.94
• Pref-GRPO: Pairwise Preference Reward-based GRPO for Stable Text-to-Image Reinforcement Learning (2025)
  Yibin Wang et al.
  1.28