Get started
Author

Runyu Peng

Observed name: Peng, Runyu
OpenAlex ID: A5065443067
Inference-Time Decontamination: Reusing Leaked Benchmarks for Large Language Model Evaluation
2024 · Qin Zhu, Qinyuan Cheng, et al. · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · 3
PDF
Intern-S1-Pro: Scientific Multimodal Foundation Model at Trillion Scale
2026 · Zou, Yicheng, Zhu, Dongsheng, et al. · arXiv (Cornell University) · 1
PDF
Implicit Reward as the Bridge: A Unified View of SFT and DPO Connections
2025 · Bo Wang, Qinyuan Cheng, et al. · neural information processing systems · 1
PDF
Intern-S2-Preview: Scientific Agentic Foundation Model
2026 · Bai, Lei, Cao, Jiaqi, et al. · arXiv (Cornell University)
PDF
Synthetic Pre-Pre-Training Improves Language Model Robustness to Noisy Pre-Training Data
2026 · Guo, Xu, Peng, Runyu, et al. · arXiv (Cornell University)
PDF
What Makes Position Zero Special? A Mechanistic Study of Position Zero Attention Sinks in LLMs
2026 · Peng, Runyu, Li, Ruixiao, et al. · arXiv (Cornell University)
PDF
Explicit Multi-head Attention for Inter-head Interaction in Large Language Models
2026 · Peng, Runyu, Zhou, Yunhua, et al. · arXiv (Cornell University)
PDF
AutoLogi: Automated Generation of Logic Puzzles for Evaluating Reasoning Abilities of Large Language Models
2025 · Zhu, Qin, Huang, Fei, et al. · arXiv (Cornell University)
PDF
Firewall Routing: Blocking Leads to Better Hybrid Inference for LLMs
2025 · Runyu Peng, Yunhua Zhou, et al. · Conference on Empirical Methods in Natural Language Processing (EMNLP)
PDF
Data-free Weight Compress and Denoise for Large Language Models
2024 · Peng, Runyu, Zhou, Yunhua, et al. · arXiv (Cornell University)
PDF
Look into Multi-Person: A New Benchmark for Pose Estimation and Human Parsing
2020 · Yanlu Cai, Yuqing Li, et al. · IEEE International Conference on Big Data (BigData)
Works count: 12
Citation count: 6
H-index: 1
I10-index:
Year
Topic
Type