Get started
Author

Fengyu Cai

Observed name: Cai, Fengyu
ORCID: 0009-0009-7943-439X
Observed ORCID: 0009-0009-7943-439X
OpenAlex ID: A5067158103
A Survey of Confidence Estimation and Calibration in Large Language Models
2024 · Jiahui Geng, Fengyu Cai, et al. · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) · 88
PDF
Slim: Explicit Slot-Intent Mapping with Bert for Joint Multi-Intent Detection and Slot Filling
2022 · Fengyu Cai, Wanhao Zhou, et al. · IEEE International Conference on Acoustics Speech and Signal Processing · 25
Self-training Improves Pre-training for Few-shot Learning in Task-oriented Dialog Systems
2021 · Fei Mi, Wanhao Zhou, et al. · Conference on Empirical Methods in Natural Language Processing (EMNLP) · 21
PDF
Aligning Large Language Model with Direct Multi-Preference Optimization for Recommendation
2024 · Zhuoxi Bai, Ning Wu, et al. · ACM International Conference on Information and Knowledge Management (CIKM) · 14
SLIM: Explicit Slot-Intent Mapping with BERT for Joint Multi-Intent Detection and Slot Filling
2021 · Cai, Fengyu, Zhou, Wanhao, et al. · arXiv (Cornell University) · 7
PDF
MoR: Better Handling Diverse Queries with a Mixture of Sparse, Dense, and Human Retrievers
2025 · Jushaan Singh Kalra, Xinran Zhao, et al. · Conference on Empirical Methods in Natural Language Processing (EMNLP) · 6
PDF
CRASH: A Collaborative Aerial-Ground Exploration System Using Hybrid-Frontier Method
2018 · Luqi Wang, Fei Gao, et al. · IEEE International Conference on Robotics and Biomimetics (ROBIO) · 6
A Survey of Confidence Estimation and Calibration in Large Language Models
2023 · Geng, Jiahui, Cai, Fengyu, et al. · arXiv (Cornell University) · 4
PDF
A Comprehensive Survey of Machine Unlearning Techniques for Large Language Models
2025 · Geng, Jiahui, Li, Qing, et al. · arXiv (Cornell University) · 1
PDF
World Embedding Benchmark
2026 · Liu, Yiqi, Yuan, Ruifeng, et al. · arXiv (Cornell University)
PDF
AutoDataBench: A Data-centric Testbed for Accelerating Auto Research
2026 · Yuan, Ruifeng, Li, Yizhi, et al. · arXiv (Cornell University)
PDF
ElicitR: Unlocking Latent Reasoning in Dense Retrievers via Generative Regularization
2026 · Cai, Fengyu, Gurevych, Iryna, et al. · TUbilio (Technical University of Darmstadt)
CoQuIR: A Comprehensive Benchmark for Code Quality-Aware Information Retrieval
2026 · Association for Computational Linguistics 2026, Cai, Fengyu, et al. · Underline Science Inc.
Crayotter: Traceable Multi-Agent Workflows for Long-Form Video Editing
2026 · Yan, Lecheng, Zhang, Yichong, et al. · arXiv (Cornell University)
PDF
CodeMMR: Bridging Natural Language, Code, and Image for Unified Retrieval
2026 · Geng, Jiahui, Li, Qing, et al. · arXiv (Cornell University)
PDF
Epistemic Gain, Aleatoric Cost: Uncertainty Decomposition in Multi-Agent Debate for Math Reasoning
2026 · Qiao, Dan, Chen, Binbin, et al. · arXiv (Cornell University)
PDF
CoQuIR: A Comprehensive Benchmark for Code Quality-Aware Information Retrieval
2026 · Jiahui Geng, Fengyu Cai, et al. · Proceedings of the conference - Association for Computational Linguistics. Meeting
PDF
Revela: Dense Retriever Learning via Language Modeling
2025 · Cai, Fengyu, Chen, Tong, et al. · arXiv (Cornell University)
PDF
SAUCE: Selective Concept Unlearning in Vision-Language Models with Sparse Autoencoders
2025 · Li, Qing, Geng, Jiahui, et al. · arXiv (Cornell University)
PDF
$\textit{GeoHard}$: Towards Measuring Class-wise Hardness through Modelling Class Semantics
2024 · Cai, Fengyu, Zhao, Xinran, et al. · arXiv (Cornell University)
PDF
$\texttt{MixGR}$: Enhancing Retriever Generalization for Scientific Domain through Complementary Granularity
2024 · Cai, Fengyu, Zhao, Xinran, et al. · arXiv (Cornell University)
PDF
Finetuning Large Language Model for Personalized Ranking
2024 · Bai, Zhuoxi, Wu, Ning, et al. · arXiv (Cornell University)
PDF
GeoHard: Towards Measuring Class-wise Hardness through Modelling Class Semantics
2024 · Fengyu Cai, Xinran Zhao, et al. · Findings of the Association for Computational Linguistics: ACL (Findings of ACL)
PDF
MixGR: Enhancing Retriever Generalization for Scientific Domain through Complementary Granularity
2024 · Fengyu Cai, Xinran Zhao, et al. · Conference on Empirical Methods in Natural Language Processing (EMNLP)
PDF
Works count: 27
Citation count: 172
H-index: 6
I10-index: 4
Year
Topic
Type