Dingjie Song
6 papers · 2025–2025 · 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
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(12)
⭐
Rising Star
(6)
⚡
Prolific Year · Productive
Top co-authors
Research topics
Artificial Intelligence
(5)
Core AI
(5)
Machine Learning
(4)
Application Areas
(4)
Deep Learning
(2)
Natural Language Processing
(2)
Learning Types · Deep Learning
(2)
Learning Types · Machine Learning
(2)
Resources & Methods
(2)
Healthcare & Medicine
(1)
Clinical
(1)
Learning Paradigms
(1)
Models
(1)
Keywords
multimodal large language model
(5)
benchmark evaluation
(2)
medical imaging
(1)
computational efficiency
(1)
compositional generalization
(1)
pairwise comparison
(1)
state space model
(1)
memory efficiency
(1)
vision-language model
(1)
visual question answering
(1)
data contamination
(1)
hybrid architecture
(1)
multi-task training
(1)
knowledge recombination
(1)
token reduction
(1)
cross-modal contamination
(1)
detection framework
(1)
training data leakage
(1)
human evaluation agreement
(1)
Papers
Both Text and Images Leaked! A Systematic Analysis of Data Contamination in Multimodal LLM
EMNLP 2025
Exploring Compositional Generalization of Multimodal LLMs for Medical Imaging
ACL 2025
Less is More: A Simple yet Effective Token Reduction Method for Efficient Multi-modal LLMs
COLING 2025
LongLLaVA: Scaling Multi-modal LLMs to 1000 Images Efficiently via a Hybrid Architecture
EMNLP 2025
MLLM-Bench: Evaluating Multimodal LLMs with Per-sample Criteria
NAACL 2025
SAMed-2: Selective Memory Enhanced Medical Segment Anything Model
MICCAI 2025