Xinyi Dai
11 papers · 2019–2025 · 5 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 ↓+7 more ↓ Show less ↑
🗺️ Taxonomy Completionist (38) 🏃 Academic Marathon · Sprint 🌍 Conference Polyglot · Silver 🌉 Interdisciplinary Bridge · Silver 🐣 Hot Topic Early Bird
🤝
Dynamic Duo
(10)
🚀
Conference Pioneer
❓
The Questioner
⚡
Prolific Year · Productive
💎
Century Club · Bronze
🌈
Renaissance Researcher
(6)
🗃️
Keyword Collector
(55)
Top co-authors
Research topics
Machine Learning
(10)
Artificial Intelligence
(8)
Core AI
(8)
Application Areas
(6)
Learning Types · Machine Learning
(6)
Natural Language Processing
(5)
Deep Learning
(4)
Learning Types · Deep Learning
(4)
Generation
(3)
Computer Science
(2)
Applications · Computer Science
(2)
Applications · Natural Language Processing
(2)
Learning Paradigms
(2)
Optimization & Theory
(2)
Resources & Methods
(2)
Keywords
code generation
(5)
large language model
(5)
multi-agent system
(2)
recommender system
(2)
reasoning process
(2)
benchmark evaluation
(2)
reinforcement learning
(2)
policy gradient
(1)
instruction following
(1)
natural language processing
(1)
hierarchical clustering
(1)
instruction tuning
(1)
markov decision process
(1)
code retrieval
(1)
multi-agent debate
(1)
domain adaptation
(1)
llm fine-tuning
(1)
recommendation system
(1)
information retrieval
(1)
tree search
(1)
Papers
Boost, Disentangle, and Customize: A Robust System2-to-System1 Pipeline for Code Generation
ACL 2025
CodePRM: Execution Feedback-enhanced Process Reward Model for Code Generation
ACL 2025
CoIR: A Comprehensive Benchmark for Code Information Retrieval Models
ACL 2025
DebateCoder: Towards Collective Intelligence of LLMs via Test Case Driven LLM Debate for Code Generation
ACL 2025
Humanity’s Last Code Exam: Can Advanced LLMs Conquer Human’s Hardest Code Competition?
EMNLP 2025
Instruction-Tuning Data Synthesis from Scratch via Web Reconstruction
ACL 2025
LLMTreeRec: Unleashing the Power of Large Language Models for Cold-Start Recommendations
COLING 2025
NL-Debugging: Exploiting Natural Language as an Intermediate Representation for Code Debugging
EMNLP 2025
RethinkMCTS: Refining Erroneous Thoughts in Monte Carlo Tree Search for Code Generation
EMNLP 2025
Towards Return Parity in Markov Decision Processes
AISTATS 2022
Large-Scale Interactive Recommendation with Tree-Structured Policy Gradient
AAAI 2019