Duanyu Feng
8 papers · 2024–2026 · 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 ↓+1 more ↓ Show less ↑
🌍 Conference Polyglot · Silver 🌉 Interdisciplinary Bridge · Silver 🗺️ Taxonomy Completionist (21) 🐣 Hot Topic Early Bird 👥 Mega-Team · Squad
📈
Trend Setter
Top co-authors
Research topics
Artificial Intelligence
(7)
Core AI
(7)
Machine Learning
(6)
Natural Language Processing
(3)
Resources & Methods
(3)
Deep Learning
(2)
Application Areas
(2)
Applications · Natural Language Processing
(2)
Core Methods
(2)
Learning Types
(2)
Data Science & Analytics
(1)
Applications · Data Science & Analytics
(1)
Architectures
(1)
Models
(1)
Optimization & Theory
(1)
Keywords
large language model
(4)
chinese legal
(2)
legal reasoning
(2)
risk management
(1)
question answering
(1)
text generation
(1)
information extraction
(1)
language model alignment
(1)
concept representation
(1)
deep learning
(1)
synthetic data generation
(1)
ranking accuracy
(1)
linear transformation
(1)
reward model
(1)
tabular data
(1)
representation engineering
(1)
privacy protection
(1)
weak-to-strong generalization
(1)
retrieval-augmented generation
(1)
preference optimization
(1)
Papers
AMaPO: Adaptive Margin-attached Preference Optimization for Language Model Alignment
AAAI 2026
MicroEvoEval: A Systematic Evaluation Framework for Image-Based Microstructure Evolution Prediction
AAAI 2026
Cross-model Transferability among Large Language Models on the Platonic Representations of Concepts
ACL 2025
LAiW: A Chinese Legal Large Language Models Benchmark
COLING 2025
LEGEND: Leveraging Representation Engineering to Annotate Safety Margin for Preference Datasets
AAAI 2025
UCL-Bench: A Chinese User-Centric Legal Benchmark for Large Language Models
NAACL 2025
FinBen: A Holistic Financial Benchmark for Large Language Models
NeurIPS 2024
HARMONIC: Harnessing LLMs for Tabular Data Synthesis and Privacy Protection
NeurIPS 2024