Pu Jian
5 papers · 2024–2025 · 2 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 · Bronze
🌉
Interdisciplinary Bridge · Silver
🗺️
Taxonomy Completionist
(17)
🌈
Renaissance Researcher
(5)
Top co-authors
Research topics
Artificial Intelligence
(4)
Machine Learning
(4)
Core AI · Artificial Intelligence
(4)
Computer Vision
(3)
Deep Learning
(3)
Natural Language Processing
(3)
Applications · Natural Language Processing
(3)
Learning Types · Machine Learning
(3)
Applications · Computer Vision
(2)
Learning Types · Deep Learning
(2)
Computer Science
(1)
Reinforcement Learning
(1)
Application Areas
(1)
Applications · Computer Science
(1)
Core AI · Computer Vision
(1)
Keywords
vision-language model
(3)
retrieval-augmented generation
(2)
visual question answering
(2)
ambiguity resolution
(1)
visual reasoning
(1)
visual attention
(1)
multimodal retrieval
(1)
multi-hop reasoning
(1)
token compression
(1)
external knowledge
(1)
heterogeneous document
(1)
visual token pruning
(1)
table reasoning
(1)
table processing
(1)
large language model
(1)
clarification question
(1)
key visual entity
(1)
visual reflection
(1)
sql-based reasoning
(1)
key entity extraction
(1)
Papers
CROP: Contextual Region-Oriented Visual Token Pruning
EMNLP 2025
Look Again, Think Slowly: Enhancing Visual Reflection in Vision-Language Models
EMNLP 2025
TableRAG: A Retrieval Augmented Generation Framework for Heterogeneous Document Reasoning
EMNLP 2025
Teaching Vision-Language Models to Ask: Resolving Ambiguity in Visual Questions
ACL 2025
Large Language Models Know What is Key Visual Entity: An LLM-assisted Multimodal Retrieval for VQA
EMNLP 2024