Yuxin Song
8 papers
· 2023–2025
· 4 conferences
· across top CS/AI conferences
Achievements
πΊοΈ
Taxonomy Completionist
(24)
π
Renaissance Researcher
(5)
π
Interdisciplinary Bridge
π§
Keyword Pioneer
π£
Hot Topic Early Bird
π
Conference Polyglot
(4)
π
Cross-Pollinator
(12)
β
The Questioner
Conferences
ICCV (3)
NIPS (3)
CVPR (1)
ICML (1)
Top co-authors
Keywords
multimodal large language model
(3)
video understanding
(2)
vision-language model
(2)
vision transformer
(1)
feature extraction
(1)
object detection
(1)
uncertainty modeling
(1)
preference learning
(1)
direct preference optimization
(1)
video captioning
(1)
video classification
(1)
attention mechanism
(1)
text generation
(1)
preference optimization
(1)
image captioning
(1)
multimodal learning
(1)
visual question answering
(1)
visual grounding
(1)
reinforcement learning from human feedback
(1)
temporal modeling
(1)
Papers
Dense Connector for MLLMs
NIPS 2024