Fangyu Lei
14 papers · 2022–2026 · 8 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 ↓+6 more ↓ Show less ↑
🐣 Hot Topic Early Bird 🗺️ Taxonomy Completionist (28) 🌍 Conference Polyglot · Silver 🌉 Interdisciplinary Bridge · Silver 👥 Mega-Team · Squad
🗃️
Keyword Collector
(56)
⚡
Prolific Year · Productive
🔥
Unstoppable · Bronze
❓
The Questioner
💎
Century Club · Bronze
📈
Trend Setter
Top co-authors
Research topics
Artificial Intelligence
(10)
Core AI
(9)
Natural Language Processing
(8)
Machine Learning
(5)
Applications · Natural Language Processing
(5)
Deep Learning
(3)
Application Areas
(3)
Learning Types · Machine Learning
(3)
Resources & Methods
(3)
Computer Science
(2)
Applications · Computer Science
(2)
Learning Types · Deep Learning
(2)
Architectures
(1)
Core Methods
(1)
Learning Paradigms
(1)
Keywords
large language model
(6)
code generation
(5)
benchmark evaluation
(3)
multi-hop question answering
(2)
reasoning evaluation
(2)
multimodal agent
(2)
question answering
(2)
few-shot learning
(2)
question decomposition
(1)
incremental learning
(1)
temporal reasoning
(1)
dialect translation
(1)
autonomous agent
(1)
computer environment
(1)
evaluation benchmark
(1)
knowledge distillation
(1)
vision-language model
(1)
low-rank adaptation
(1)
parameter-efficient fine-tuning
(1)
open-ended task
(1)
Papers
GATE: Graph-based Adaptive Tool Evolution Across Diverse Tasks
ACL 2026
TaREx: Reinforcement Learning for Code-Driven Table Reasoning
AAAI 2026
Spider 2.0: Evaluating Language Models on Real-World Enterprise Text-to-SQL Workflows
ICLR 2025
Competition-Level Problems are Effective LLM Evaluators
ACL 2024
DA-Code: Agent Data Science Code Generation Benchmark for Large Language Models
EMNLP 2024
Neeko: Leveraging Dynamic LoRA for Efficient Multi-Character Role-Playing Agent
EMNLP 2024
OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
NeurIPS 2024
S3Eval: A Synthetic, Scalable, Systematic Evaluation Suite for Large Language Model
NAACL 2024
Spider2-V: How Far Are Multimodal Agents From Automating Data Science and Engineering Workflows?
NeurIPS 2024
Teaching Small Language Models to Reason for Knowledge-Intensive Multi-Hop Question Answering
ACL 2024
MenatQA: A New Dataset for Testing the Temporal Comprehension and Reasoning Abilities of Large Language Models
EMNLP 2023
Multi-Target Semantic Parsing with Collaborative Deliberation Network
IJCNLP 2023
S3HQA: A Three-Stage Approach for Multi-hop Text-Table Hybrid Question Answering
ACL 2023
Answering Numerical Reasoning Questions in Table-Text Hybrid Contents with Graph-based Encoder and Tree-based Decoder
COLING 2022