Fanqi Wan
18 papers · 2023–2026 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+7 more ↓ Show less ↑
π Renaissance Researcher (6) π Interdisciplinary Bridge π Cross-Pollinator (14) π Conference Polyglot (4) πΊοΈ Taxonomy Completionist (39)
π
Cross-Pollinator
(14)
π£
Hot Topic Early Bird
π±
Topic Pioneer
π€
Dynamic Duo
(14)
π
Century Club
(15)
ποΈ
Keyword Collector
(68)
β‘
Prolific Year
(7)
Conferences
EMNLP (7)
ACL (6)
ICLR (3)
AAAI (2)
Top co-authors
Keywords
large language model
(10)
hallucination mitigation
(2)
reinforcement learning
(2)
knowledge distillation
(2)
preference optimization
(2)
response generation
(2)
policy optimization
(1)
reward modeling
(1)
contrastive learning
(1)
attention mechanism
(1)
mathematical reasoning
(1)
chain-of-thought reasoning
(1)
zero-shot learning
(1)
text analysis
(1)
policy learning
(1)
knowledge extraction
(1)
factual knowledge
(1)
task-oriented dialogue
(1)
instruction following
(1)
k-means clustering
(1)
Papers
ProactiveEval: A Unified Evaluation Framework for Proactive Dialogue Agents
ACL 2026
PaCoRe: Learning to Scale Test-Time Compute with Parallel Coordinated Reasoning
ACL 2026
ProFuser: Progressive Fusion of Large Language Models
AAAI 2026
Empowering Self-Learning of LLMs: Inner Knowledge Explicitation as a Catalyst
AAAI 2025
Mutual-Taught for Co-adapting Policy and Reward Models
ACL 2025
BlockPruner: Fine-grained Pruning for Large Language Models
ACL 2025
FuseChat: Knowledge Fusion of Chat Models
EMNLP 2025
ReAlign: Structured Revision for Small Language Model Alignment
EMNLP 2025
Advantage-Guided Distillation for Preference Alignment in Small Language Models
ICLR 2025
Weighted-Reward Preference Optimization for Implicit Model Fusion
ICLR 2025
Knowledge Fusion of Large Language Models
ICLR 2024
Knowledge Verification to Nip Hallucination in the Bud
EMNLP 2024
Self-Evolution Fine-Tuning for Policy Optimization
EMNLP 2024
Multi-Grained Knowledge Retrieval for End-to-End Task-Oriented Dialog
ACL 2023
PsyCoT: Psychological Questionnaire as Powerful Chain-of-Thought for Personality Detection
EMNLP 2023
Explore-Instruct: Enhancing Domain-Specific Instruction Coverage through Active Exploration
EMNLP 2023
Retrieval-Generation Alignment for End-to-End Task-Oriented Dialogue System
EMNLP 2023
Clustering-Aware Negative Sampling for Unsupervised Sentence Representation
ACL 2023