Chengzhi Liu
7 papers · 2025–2025 · 6 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 · Bronze 🗺️ Taxonomy Completionist (19) ⭐ Rising Star (7) 👥 Mega-Team · Squad
⚡
Prolific Year · Productive
Top co-authors
Research topics
Artificial Intelligence
(6)
Core AI
(6)
Deep Learning
(3)
Machine Learning
(2)
Natural Language Processing
(2)
Learning Types · Machine Learning
(2)
Models
(2)
Healthcare & Medicine
(1)
Application Areas
(1)
Applications
(1)
Clinical
(1)
Core Methods
(1)
Generation
(1)
Learning Types · Deep Learning
(1)
Resources & Methods
(1)
Keywords
multimodal large language model
(3)
hallucination mitigation
(2)
attention mechanism
(2)
visual question answering
(1)
medical imaging
(1)
information extraction
(1)
multimodal learning
(1)
medical image analysis
(1)
visual context
(1)
adversarial attack
(1)
multimodal representation
(1)
decoding strategy
(1)
missing modality
(1)
safety assessment
(1)
prompt injection
(1)
disease diagnosis
(1)
causal mask
(1)
multi-turn reasoning
(1)
conversation benchmark
(1)
large reasoning model
(1)
Papers
Incomplete Modality Disentangled Representation for Ophthalmic Disease Grading and Diagnosis
AAAI 2025
Intervening Anchor Token: Decoding Strategy in Alleviating Hallucinations for MLLMs
ICLR 2025
MMRC: A Large-Scale Benchmark for Understanding Multimodal Large Language Model in Real-World Conversation
ACL 2025
Multimodal Situational Safety
ICLR 2025
Robust Multimodal Learning for Ophthalmic Disease Grading via Disentangled Representation
MICCAI 2025
Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decoding
CVPR 2025
The Hidden Risks of Large Reasoning Models: A Safety Assessment of R1
IJCNLP 2025