Chengzu Li
10 papers · 2022–2026 · 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 ↓+3 more ↓ Show less ↑
🐣 Hot Topic Early Bird 🌍 Conference Polyglot · Silver 🌉 Interdisciplinary Bridge · Silver 🗺️ Taxonomy Completionist (23) 👥 Mega-Team · Squad
🗃️
Keyword Collector
(50)
💎
Century Club · Bronze
🔥
Unstoppable · Bronze
Venues
Top co-authors
Research topics
Artificial Intelligence
(9)
Core AI
(7)
Machine Learning
(4)
Natural Language Processing
(4)
Learning Paradigms
(3)
Computer Vision
(2)
Deep Learning
(2)
Application Areas
(2)
Applications
(2)
Resources & Methods
(2)
Knowledge & Reasoning
(1)
Analysis
(1)
Architectures
(1)
Core Methods
(1)
Generation
(1)
Keywords
large language model
(3)
vision-language model
(2)
spatial reasoning
(2)
in-context learning
(2)
semantic parsing
(2)
knowledge distillation
(2)
question answering
(2)
visual representation
(1)
image captioning
(1)
embedding space
(1)
text generation
(1)
code generation
(1)
visual question answering
(1)
program synthesis
(1)
knowledge graph
(1)
chain-of-thought reasoning
(1)
information loss
(1)
latent representation
(1)
knowledge base
(1)
symbolic reasoning
(1)
Papers
LoVeC: Reinforcement Learning for Better Verbalized Confidence in Long-Form Generation
ACL 2026
Enriching Patent Claim Generation with European Patent Dataset
EMNLP 2025
Imagine While Reasoning in Space: Multimodal Visualization-of-Thought
ICML 2025
Large Language Models are Miscalibrated In-Context Learners
ACL 2025
Lost in Embeddings: Information Loss in Vision–Language Models
EMNLP 2025
Semantic Map-based Generation of Navigation Instructions
COLING 2024
TopViewRS: Vision-Language Models as Top-View Spatial Reasoners
EMNLP 2024
Binding Language Models in Symbolic Languages
ICLR 2023
Generating Data for Symbolic Language with Large Language Models
EMNLP 2023
UnifiedSKG: Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language Models
EMNLP 2022