Get started
Author

Peiyang He

Observed name: He, Peiyang
OpenAlex ID: A5136538604
Selfgait: A Spatiotemporal Representation Learning Method for Self-Supervised Gait Recognition
2021 · Yiqun Liu, Yi Zeng, et al. · IEEE International Conference on Acoustics Speech and Signal Processing · 21
PDF
Experience Compression Spectrum: Unifying Memory, Skills, and Rules in LLM Agents
2026 · Zhang, Xing, Wang, Guanghui, et al. · arXiv (Cornell University) · 19
PDF
Library Drift: Diagnosing and Fixing a Silent Failure Mode in Self-Evolving LLM Skill Libraries
2026 · Zhang, Xing, Cui, Yanwei, et al. · arXiv (Cornell University) · 18
PDF
Guardrails Beat Guidance: A Large-Scale Study of Rules, Skills, and Persistent Configuration for Coding Agents
2026 · Zhang, Xing, Wang, Guanghui, et al. · arXiv (Cornell University) · 13
PDF
Ratchet: How Reliable Must an LLM Judge Be to Retire a Skill?
2026 · Zhang, Xing, Cui, Yanwei, et al. · arXiv (Cornell University) · 7
PDF
Verified Multi-Agent Orchestration: A Plan-Execute-Verify-Replan Framework for Complex Query Resolution
2026 · Zhang, Xing, Cui, Yanwei, et al. · arXiv (Cornell University) · 7
PDF
STED and Consistency Scoring: A Framework for Evaluating LLM Structured Output Reliability
2025 · Wang, Guanghui, Yu, Jinze, et al. · arXiv (Cornell University) · 4
PDF
Who Grades the Grader? Co-Evolving Evaluation Metrics and Skills for Self-Improving LLM Agents
2026 · Zhang, Xing, Wang, Guanghui, et al. · arXiv (Cornell University) · 3
PDF
The Blind Curator: How a Biased Judge Silently Disables Skill Retirement in Self-Evolving Agents
2026 · Zhang, Xing, Cui, Yanwei, et al. · arXiv (Cornell University) · 3
PDF
Closing the Feedback Loop: From Experience Extraction to Insight Governance in Verbal Reinforcement Learning
2026 · Cui, Yanwei, Zhang, Xing, et al. · arXiv (Cornell University) · 3
PDF
Prompt Optimization Is a Coin Flip: Diagnosing When It Helps in Compound AI Systems
2026 · Zhang, Xing, Wang, Guanghui, et al. · arXiv (Cornell University) · 3
PDF
Who Verifies the Verifier? Co-Evolving Inspectable Graders with Self-Improving Agents
2026 · Zhang, Xing, Wang, Guanghui, et al. · arXiv (Cornell University) · 1
PDF
The Alignment Floor: How Persona Customization Breaks Safety in Weakly-Aligned LLMs
2026 · Zhang, Xing, Wang, Guanghui, et al. · arXiv (Cornell University) · 1
PDF
A Multi-Stage Pipeline for Accurate Handwritten Information Extraction from Financial Forms
2025 · Guanghui Wang, Jinze Yu, et al. · IEEE International Conference on Computer Vision Workshops · 1
FundRecLLM: Fund Recommendation Based on Financial News and Research Analyst Report
2023 · Guang Yang, Peiyang He, et al. · Frontiers in artificial intelligence and applications · 1
PDF
UnitBoost: Managing Compound LLM Systems with a Merge Operator, Not a Model
2026 · Zhang, Xing, Wang, Guanghui, et al. · arXiv (Cornell University)
PDF
Metrics That Write Themselves: Evolving an Evaluator from Its Own Blind Spots
2026 · Zhang, Xing, Cui, Yanwei, et al. · arXiv (Cornell University)
PDF
Reconcile Once, Write Anytime: A Trust-Tiered Librarian and a Multi-Agent Writer for Drift-Free, Point-in-Time Research
2026 · Zhang, Xing, Cui, Yanwei, et al. · arXiv (Cornell University)
PDF
Better Literary Translation: A Multi-Aspect Data Generation and LLM Training Approach
2026 · Association for Computational Linguistics 2026, He, Peiyang, et al. · Underline Science Inc.
Hindsight Preference Optimization for Financial Time Series Advisory
2026 · Cui, Yanwei, Wang, Guanghui, et al. · arXiv (Cornell University)
PDF
Better Literary Translation: A Multi-Aspect Data Generation and LLM Training Approach
2026 · Zhihao Lin, Ziqi Zhu, et al. · Proceedings of the conference - Association for Computational Linguistics. Meeting
PDF
BNB Agent Studio: An Open Toolchain for Provisioning, Deploying, and Operating Economically Autonomous LLM Agents
2026 · H Zhao, Guanghui Wang, et al. · Conference on Empirical Methods in Natural Language Processing: System Demonstrations (EMNLP)
PDF
Topic Knowledge Based Controlled Generation for Long Documents Using Retrieval-Based Language Models
2023 · Xuefei Zhang, Peiyang He, et al. · Frontiers in artificial intelligence and applications
PDF
Works count: 23
Citation count: 105
H-index: 6
I10-index: 4
Year
Topic
Type