Fengyu Cai
7 papers · 2021–2026 · 4 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
🌍
Conference Polyglot · Bronze
🏃
Academic Marathon · Sprint
🌉
Interdisciplinary Bridge · Silver
🗺️
Taxonomy Completionist
(15)
Top co-authors
Research topics
Natural Language Processing
(5)
Artificial Intelligence
(4)
Applications · Natural Language Processing
(4)
Core AI
(3)
Machine Learning
(2)
Learning Types · Machine Learning
(2)
Computer Science
(1)
Deep Learning
(1)
Applications · Computer Science
(1)
Core Methods
(1)
Generation
(1)
Learning Paradigms
(1)
Learning Types · Deep Learning
(1)
Resources & Methods
(1)
Keywords
information retrieval
(2)
retrieval-augmented generation
(2)
model calibration
(1)
factual accuracy
(1)
code generation
(1)
intent classification
(1)
dense retrieval
(1)
code retrieval
(1)
multimodal retrieval
(1)
semantic similarity
(1)
multimodal alignment
(1)
retrieval augmentation
(1)
confidence estimation
(1)
sparse retriever
(1)
task-oriented dialog
(1)
text augmentation
(1)
dialog system
(1)
multilingual benchmark
(1)
code search
(1)
dense retriever
(1)
Papers
CodeMMR: Bridging Natural Language, Code, and Image for Unified Retrieval
CVPR 2026
CoQuIR: A Comprehensive Benchmark for Code Quality-Aware Information Retrieval
ACL 2026
MoR: Better Handling Diverse Queries with a Mixture of Sparse, Dense, and Human Retrievers
EMNLP 2025
A Survey of Confidence Estimation and Calibration in Large Language Models
NAACL 2024
GeoHard: Towards Measuring Class-wise Hardness through Modelling Class Semantics
ACL 2024
MixGR: Enhancing Retriever Generalization for Scientific Domain through Complementary Granularity
EMNLP 2024
Self-training Improves Pre-training for Few-shot Learning in Task-oriented Dialog Systems
EMNLP 2021