Dingjie Song
6 papers · 2025–2025 · 5 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+3 more ↓ Show less ↑
π Renaissance Researcher (5) π Interdisciplinary Bridge π§ Keyword Pioneer π Conference Polyglot (5) πΊοΈ Taxonomy Completionist (13)
π
Cross-Pollinator
(10)
β
Rising Star
(6)
β‘
Prolific Year
(6)
Conferences
EMNLP (2)
ACL (1)
COLING (1)
MICCAI (1)
NAACL (1)
Top co-authors
Keywords
multimodal large language model
(4)
benchmark evaluation
(2)
medical imaging
(1)
computational efficiency
(1)
compositional generalization
(1)
pairwise comparison
(1)
state space model
(1)
memory efficiency
(1)
multi-modal large language model
(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
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
Both Text and Images Leaked! A Systematic Analysis of Data Contamination in Multimodal LLM
EMNLP 2025
LongLLaVA: Scaling Multi-modal LLMs to 1000 Images Efficiently via a Hybrid Architecture
EMNLP 2025
SAMed-2: Selective Memory Enhanced Medical Segment Anything Model
MICCAI 2025
MLLM-Bench: Evaluating Multimodal LLMs with Per-sample Criteria
NAACL 2025