Lune

Profiles2024-2026

Pengfei Liu

Shanghai Jiao Tong University

17Papers
14Last author
26Unique co-authors
0First author
0Solo

First and last author come from byline position, which some venues assign alphabetically.

Recent papers17

  1. SR-Scientist: Scientific Equation Discovery With Agentic AIAuthor 3 of 3ICLR 2026 · 28 citations
  2. Proximal Supervised Fine-TuningAuthor 6 of 6ICLR 2026 · 13 citations
  3. What Does Vision Tool-Use Reinforcement Learning Really Learn? Disentangling Tool-Induced and Intrinsic Effects for Crop-and-ZoomAuthor 6 of 6ICML 2026 · 5 citations
  4. Hybrid Policy Distillation for LLMsAuthor 4 of 4ICML 2026 · 2 citations
  5. DeepResearcher: Scaling Deep Research via Reinforcement Learning in Real-world EnvironmentsAuthor 7 of 7EMNLP 2025 · 8 citations
  6. Programming Every Example: Lifting Pre-training Data Quality Like Experts at ScaleAuthor 5 of 5ICML 2025
  7. Alignment for HonestyAuthor 5 of 5NeurIPS 2024 · 82 citations
  8. InFoBench: Evaluating Instruction Following Ability in Large Language ModelsAuthor 9 of 10ACL Findings 2024 · 26 citations
  9. Prompt Chaining or Stepwise Prompt? Refinement in Text SummarizationAuthor 5 of 5ACL Findings 2024 · 23 citations
  10. Knowledge-Centric Hallucination DetectionAuthor 8 of 10EMNLP 2024 · 5 citations
  11. Reformatted AlignmentAuthor 8 of 8EMNLP Findings 2024 · 3 citations
  12. Weak-to-Strong ReasoningAuthor 3 of 3EMNLP Findings 2024 · 3 citations
  13. ECON: On the Detection and Resolution of Evidence ConflictsAuthor 8 of 9EMNLP 2024 · 2 citations
  14. MoPS: Modular Story Premise Synthesis for Open-Ended Automatic Story GenerationAuthor 3 of 3ACL 2024 · 2 citations
  15. The Critique of CritiqueAuthor 6 of 6ACL Findings 2024 · 2 citations
  16. Dissecting Human and LLM PreferencesAuthor 6 of 6ACL 2024 · 1 citation
  17. FRoG: Evaluating Fuzzy Reasoning of Generalized Quantifiers in LLMsAuthor 3 of 3EMNLP 2024
Dusk over the sea between two cliffs drawn in fine vertical lines