Get started
Author

Fanyu Meng

Observed name: Meng, Fanyu
Observed institution: Jiuquan Iron & Steel (China)
ORCID: 0009-0007-7120-7075
Observed ORCID: 0009-0007-7120-7075
OpenAlex ID: A5128048379
A*-Thought-V2: Efficient Latent Reasoning via Geometric Dynamics of LLM
2026 · Xu, Xiaoang, Liu, Siyuan, et al. · arXiv (Cornell University)
PDF
EnterpriseRAG: Benchmarking LLM Instruction Adherence and Robustness under Non-Ideal Enterprise Retrieval
2026 · Miao, Huiqi, Sun, Xinbao, et al. · arXiv (Cornell University)
PDF
Beyond One-Size-Fits-All: Adaptive Subgraph Denoising for Zero-Shot Graph Learning with Large Language Models
2026 · Fengzhi Li, Liang Zhang, et al. · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD)
Thinking-Based Non-Thinking: Solving the Reward Hacking Problem in Training Hybrid Reasoning Models via Reinforcement Learning
2026 · Association for Computational Linguistics 2026, Feng, Junlan, et al. · Underline Science Inc.
JT-SAFE-V2: Safety-by-Design Foundation Model with World-Context Data
2026 · Feng, Junlan, Meng, Fanyu, et al. · arXiv (Cornell University)
PDF
BadDLM: Backdooring Diffusion Language Models with Diverse Targets
2026 · Zhai, Shengfang, Ji, Xiaoyang, et al. · arXiv (Cornell University)
PDF
Strategy-Aware Optimization Modeling with Reasoning LLMs
2026 · Zhao, Ruiqing, Li, Fengzhi, et al. · arXiv (Cornell University)
PDF
CCR-Bench: A Comprehensive Benchmark for Evaluating LLMs on Complex Constraints, Control Flows, and Real-World Cases
2026 · Xue, Xiaona, Huang, Yiqiao, et al. · arXiv (Cornell University)
PDF
Beyond One-Size-Fits-All: Adaptive Subgraph Denoising for Zero-Shot Graph Learning with Large Language Models
2026 · Li, Fengzhi, Zhang, Liang, et al. · arXiv (Cornell University)
PDF
Thinking-Based Non-Thinking: Solving the Reward Hacking Problem in Training Hybrid Reasoning Models via Reinforcement Learning
2026 · Gan, Siyuan, Liu, Jiaheng, et al. · arXiv (Cornell University)
PDF
DR3-Eval: Towards Realistic and Reproducible Deep Research Evaluation
2026 · Qianqian Xie, He Zhu, et al. · Conference on Empirical Methods in Natural Language Processing (EMNLP)
PDF
Thinking-Based Non-Thinking: Solving the Reward Hacking Problem in Training Hybrid Reasoning Models via Reinforcement Learning
2026 · Siyuan Gan, Jiaheng Liu, et al. · Proceedings of the conference - Association for Computational Linguistics. Meeting
PDF
Active Adaptation, Not Static Defense: Temporal Dynamics of Preventative Steering in Adversarial Fine-Tuning
2026 · Jing Guan, Yachao Yang, et al. · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)
PDF
Reconsidering Overthinking: Penalizing Internal and External Redundancy in CoT Reasoning
2025 · Zhen, Taihang, Hong, Jialiang, et al. · arXiv (Cornell University)
PDF
Works count: 14
Citation count:
H-index:
I10-index:
Year
Topic
Type