Get started
Author

Peiwen Yuan

Observed name: Yuan, Peiwen
ORCID: 0000-0002-5529-1576
Observed ORCID: 0000-0002-5529-1576
OpenAlex ID: A5102600276
BatchEval: Towards Human-like Text Evaluation
2024 · Peiwen Yuan, Shaoxiong Feng, et al. · Proceedings of the conference - Association for Computational Linguistics. Meeting · 6
PDF
CogLM: Tracking Cognitive Development of Large Language Models
2025 · Xinglin Wang, Peiwen Yuan, et al. · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) · 4
PDF
Escape Sky-high Cost: Early-stopping Self-Consistency for Multi-step Reasoning
2024 · Li, Yiwei, Yuan, Peiwen, et al. · arXiv (Cornell University) · 3
PDF
Make Every Penny Count: Difficulty-Adaptive Self-Consistency for Cost-Efficient Reasoning
2025 · Xinglin Wang, Shaoxiong Feng, et al. · Findings of the Association for Computational Linguistics: NAACL · 2
PDF
Integrate the Essence and Eliminate the Dross: Fine-Grained Self-Consistency for Free-Form Language Generation
2024 · Xinglin Wang, Yiwei Li, et al. · Proceedings of the conference - Association for Computational Linguistics. Meeting · 2
PDF
Generative Dense Retrieval: Memory Can Be a Burden
2024 · Peiwen Yuan, Xinglin Wang, et al. · Conference of the European Chapter of the Association for Computational Linguistics · 2
PDF
MODE+: A benchmark and a probe into multimodal open-domain dialogue evaluation
2026 · Hang Yin, Xinglin Wang, et al. · Neurocomputing · 1
LLM-Powered Benchmark Factory: Reliable, Generic, and Efficient
2026 · Peiwen Yuan, Shaoxiong Feng, et al. · Proceedings of the conference - Association for Computational Linguistics. Meeting · 1
PDF
Silencer: From Discovery to Mitigation of Self-Bias in LLM-as-Benchmark-Generator
2025 · Peiwen Yuan, Yiwei Li, et al. · neural information processing systems · 1
PDF
Speculative Decoding for Multi-Sample Inference
2025 · Yiwei Li, Jiayi Shi, et al. · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · 1
PDF
Generative Dense Retrieval: Memory Can Be a Burden
2024 · Yuan, Peiwen, Wang, Xinglin, et al. · arXiv (Cornell University) · 1
PDF
Focused Large Language Models are Stable Many-Shot Learners
2024 · Peiwen Yuan, Shaoxiong Feng, et al. · Conference on Empirical Methods in Natural Language Processing (EMNLP) · 1
PDF
BatchEval: Towards Human-like Text Evaluation
2023 · Yuan, Peiwen, Feng, Shaoxiong, et al. · arXiv (Cornell University) · 1
PDF
From Pareto to Preference: Personalized Test-Time Scaling via Amortized Agentic Policy Discovery
2026 · Wang, Xinglin, Liu, Zishen, et al. · arXiv (Cornell University)
PDF
LLM-Powered Benchmark Factory: Reliable, Generic, and Efficient
2026 · Association for Computational Linguistics 2026, Feng, Shaoxiong, et al. · Underline Science Inc.
On Time, Within Budget: Constraint-Driven Online Resource Allocation for Agentic Workflows
2026 · Wang, Xinglin, Liu, Zishen, et al. · arXiv (Cornell University)
PDF
Learning More from Less: Unlocking Internal Representations for Benchmark Compression
2026 · Zhang, Yueqi, Hu, Jin, et al. · arXiv (Cornell University)
PDF
Two-Round Voting: Improving Self-Consistency by Recycling Low-Vote Reasoning Evidence
2026 · Lingxiang Wei, Peiwen Yuan, et al. · International Conference on Communication Networks and Machine Learning (CNML)
Do Not Waste Your Rollouts: Recycling Search Experience for Efficient Test-Time Scaling
2026 · Wang, Xinglin, Shi, Jiayi, et al. · arXiv (Cornell University)
PDF
Share More, Search Less: Collaborative Parallel Thinking for Efficient Test-Time Scaling
2026 · Xinglin Wang, Hao Lin, et al. · Conference on Empirical Methods in Natural Language Processing (EMNLP)
PDF
Breaking the Self-Confirming Loop: Diagnosing and Mitigating Systemic Reward Bias in Self-Rewarding RL
2025 · Tan, Chuyi, Yuan, Peiwen, et al. · arXiv (Cornell University)
PDF
PatternKV: Flattening KV Representation Expands Quantization Headroom
2025 · Zhang, Ji, Li, Yiwei, et al. · arXiv (Cornell University)
PDF
From Sub-Ability Diagnosis to Human-Aligned Generation: Bridging the Gap for Text Length Control via MARKERGEN
2025 · Yuan, Peiwen, Tan, Chuyi, et al. · arXiv (Cornell University)
PDF
InsBank: Evolving Instruction Subset for Ongoing Alignment
2025 · Shi, Jiayi, Li, Yiwei, et al. · arXiv (Cornell University)
PDF
UniCBE: An Uniformity-driven Comparing Based Evaluation Framework with Unified Multi-Objective Optimization
2025 · Yuan, Peiwen, Feng, Shaoxiong, et al. · arXiv (Cornell University)
PDF
Works count: 40
Citation count: 26
H-index: 3
I10-index:
Year
Topic
Type