PPaperPicks

Feifan Song

11 papers at tracked venues · 9 at CORE A* · active 20242026

Venues

Frequent coauthors

Papers

  1. P-Aligner: Pre-Aligning LLMs via Principled Instruction Synthesis
    WWW 2026 · Feifan Song
  2. Two Pathways to Truthfulness: On the Intrinsic Encoding of LLM Hallucinations
  3. ATLANTIS: Weak-to-Strong Learning via Importance Sampling
  4. Instantly Learning Preference Alignment via In-context DPO
    NAACL 2025 · Feifan Song
  5. MPO: Boosting LLM Agents with Meta Plan Optimization
  6. Odysseus Navigates the Sirens' Song: Dynamic Focus Decoding for Factual and Diverse Open-Ended Text Generation
  7. Omni-MATH: A Universal Olympiad Level Mathematic Benchmark for Large Language Models
  8. TimE: A Multi-level Benchmark for Temporal Reasoning of LLMs in Real-World Scenarios
  9. Towards A Better Initial Policy Model For Scalable Long-CoT Reinforcement Learning
  10. Well Begun is Half Done: Low-resource Preference Alignment by Weak-to-Strong Decoding
    ACL 2025 · Feifan Song
  11. Preference Ranking Optimization for Human Alignment
    AAAI 2024 · Feifan Song