Lune

Profiles2024-2026

Boyuan Pan

Xiaohongshu Inc

19Papers
0Last author
12Unique co-authors
0First author
0Solo

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

Recent papers19

  1. LLM-Powered Benchmark Factory: Reliable, Generic, and EfficientAuthor 8 of 10ACL 2026 · 8 citations
  2. Breaking the Self-Confirming Loop: Diagnosing and Mitigating Systemic Reward Bias in Self-Rewarding RLAuthor 9 of 11ICML 2026 · 1 citation
  3. Learning More from Less: Unlocking Internal Representations for Benchmark CompressionAuthor 10 of 12ICML 2026
  4. PatternKV: Flattening KV Representation Expands Quantization HeadroomAuthor 9 of 11ICML 2026
  5. Every Rollout Counts: Optimal Resource Allocation for Efficient Test-Time ScalingAuthor 8 of 10NeurIPS 2025 · 16 citations
  6. Beyond One-Size-Fits-All: Tailored Benchmarks for Efficient EvaluationAuthor 8 of 10ACL 2025 · 6 citations
  7. Silencer: From Discovery to Mitigation of Self-Bias in LLM-as-Benchmark-GeneratorAuthor 8 of 10NeurIPS 2025 · 4 citations
  8. From Sub-Ability Diagnosis to Human-Aligned Generation: Bridging the Gap for Text Length Control via MarkerGenAuthor 8 of 10ACL 2025 · 2 citations
  9. Speculative Decoding for Multi-Sample InferenceAuthor 9 of 11EMNLP Findings 2025 · 1 citation
  10. InsBank: Evolving Instruction Subset for Ongoing AlignmentAuthor 8 of 11EMNLP Findings 2025
  11. Mind the Quote: Enabling Quotation-Aware Dialogue in LLMs via Plug-and-Play ModulesAuthor 8 of 10NeurIPS 2025
  12. Revisiting Self-Consistency from Dynamic Distributional Alignment Perspective on Answer AggregationAuthor 9 of 11ACL Findings 2025
  13. UniCBE: An Uniformity-driven Comparing Based Evaluation Framework with Unified Multi-Objective OptimizationAuthor 8 of 10ICLR 2025
  14. Escape Sky-high Cost: Early-stopping Self-Consistency for Multi-step ReasoningAuthor 4 of 7ICLR 2024 · 101 citations
  15. Turning Dust into Gold: Distilling Complex Reasoning Capabilities from LLMs by Leveraging Negative DataAuthor 4 of 7AAAI 2024 · 31 citations
  16. BatchEval: Towards Human-like Text EvaluationAuthor 5 of 7ACL 2024
  17. Focused Large Language Models are Stable Many-Shot LearnersAuthor 7 of 10EMNLP 2024
  18. Integrate the Essence and Eliminate the Dross: Fine-Grained Self-Consistency for Free-Form Language GenerationAuthor 5 of 8ACL 2024
  19. Poor-Supervised Evaluation for SuperLLM via Mutual ConsistencyAuthor 5 of 8ACL Findings 2024
Dusk over the sea between two cliffs drawn in fine vertical lines