Han Peng
8 papers · 2021–2026 · 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 ↓
🌍
Conference Polyglot · Silver
🏃
Academic Marathon · Sprint
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(23)
👥
Mega-Team · Squad
Venues
Top co-authors
Research topics
Machine Learning
(5)
Deep Learning
(4)
Artificial Intelligence
(3)
Natural Language Processing
(3)
Core AI
(3)
Application Areas
(2)
Applications · Natural Language Processing
(2)
Architectures
(2)
Core Methods
(2)
Learning Types · Deep Learning
(2)
Learning Types · Machine Learning
(2)
Computer Science
(1)
Mathematics & Optimization
(1)
Applications · Computer Science
(1)
Models
(1)
Keywords
code representation
(2)
positional encoding
(2)
information bottleneck
(1)
attention mechanism
(1)
knowledge transfer
(1)
question answering
(1)
model evaluation
(1)
text generation
(1)
information retrieval
(1)
document retrieval
(1)
outlier detection
(1)
document ranking
(1)
source code
(1)
network structure
(1)
k-median clustering
(1)
approximation algorithm
(1)
tree structure
(1)
inductive bia
(1)
vision-language model
(1)
retrieval-augmented generation
(1)
Papers
A More Efficient Reduction from Outlier-Aware to Outlier-Free k-Median
AAAI 2026
Improving Vision-language Models with Perception-centric Process Reward Models
CVPR 2026
SeD-UD: An Influence-Driven and Hierarchically-Decoupled Information Bottleneck for Multimodal Intent Recognition
CVPR 2026
CAFE: Retrieval Head-based Coarse-to-Fine Information Seeking to Enhance Multi-Document QA Capability
EMNLP 2025
LLMBox: A Comprehensive Library for Large Language Models
ACL 2024
Rethinking Positional Encoding in Tree Transformer for Code Representation
EMNLP 2022
BNS: Building Network Structures Dynamically for Continual Learning
NeurIPS 2021
Integrating Tree Path in Transformer for Code Representation
NeurIPS 2021