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