Dayuan Fu
11 papers · 2022–2026 · 5 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+3 more ↓ Show less ↑
๐ Cross-Pollinator (15) ๐ Interdisciplinary Bridge ๐บ๏ธ Taxonomy Completionist (18) ๐งญ Keyword Pioneer ๐ Conference Polyglot (4)
โก
Prolific Year
(5)
๐
Century Club
(10)
โ
The Questioner
Conferences
EMNLP (4)
COLING (2)
ICLR (2)
NAACL (2)
ACL (1)
Top co-authors
Keywords
large language model
(7)
dialogue system
(2)
task-oriented dialogue
(2)
language model
(2)
agent system
(2)
representation learning
(2)
knowledge distillation
(1)
dialogue generation
(1)
code generation
(1)
knowledge base
(1)
instruction tuning
(1)
web search
(1)
autonomous agent
(1)
tool use
(1)
embodied agent
(1)
data quality
(1)
mechanistic interpretability
(1)
data pruning
(1)
hallucination detection
(1)
residual stream
(1)
Papers
AgencyBench: Benchmarking the Frontiers of Autonomous Agents in 1M-Token Real-World Contexts
ACL 2026
PreAct: Prediction Enhances Agentโs Planning Ability
COLING 2025
DeepResearcher: Scaling Deep Research via Reinforcement Learning in Real-world Environments
EMNLP 2025
AgentRefine: Enhancing Agent Generalization through Refinement Tuning
ICLR 2025
CS-Bench: A Comprehensive Benchmark for Large Language Models towards Computer Science Mastery
ICLR 2025
BootTOD: Bootstrap Task-oriented Dialogue Representations by Aligning Diverse Responses
COLING 2024
DivTOD: Unleashing the Power of LLMs for Diversifying Task-Oriented Dialogue Representations
NAACL 2024
On Large Language Modelsโ Hallucination with Regard to Known Facts
NAACL 2024
MSI-Agent: Incorporating Multi-Scale Insight into Embodied Agents for Superior Planning and Decision-Making
EMNLP 2024
How Do Your Code LLMs perform? Empowering Code Instruction Tuning with Really Good Data
EMNLP 2024
Semi-Supervised Knowledge-Grounded Pre-training for Task-Oriented Dialog Systems
EMNLP 2022