Jinsong Li
7 papers · 2024–2026 · 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 ↓
🌍
Conference Polyglot · Silver
🌉
Interdisciplinary Bridge · Silver
🗺️
Taxonomy Completionist
(25)
❓
The Questioner
Venues
Top co-authors
Research topics
Computer Vision
(4)
Artificial Intelligence
(3)
Deep Learning
(3)
Machine Learning
(3)
Application Areas
(3)
Core AI · Artificial Intelligence
(3)
Core AI · Computer Vision
(2)
Generation
(2)
Processing
(2)
Techniques
(2)
Natural Language Processing
(1)
Applications
(1)
Architectures
(1)
Core Methods
(1)
Domain-Specific
(1)
Keywords
large vision-language model
(2)
multimodal learning
(2)
image classification
(1)
benchmark evaluation
(1)
few-shot learning
(1)
domain adaptation
(1)
video captioning
(1)
parameter-efficient fine-tuning
(1)
attention mechanism
(1)
video generation
(1)
video understanding
(1)
diffusion model
(1)
memory efficiency
(1)
data leakage
(1)
reinforcement learning
(1)
vision-language model
(1)
token pruning
(1)
transformer architecture
(1)
visual prompt tuning
(1)
model compression
(1)
Papers
Game Ground Bench: Probing the Limits of LVLMs in Complex Semantic Grounding Across Game Universes
AAAI 2026
Light-A-Video: Training-free Video Relighting via Progressive Light Fusion
ICCV 2025
Towards Storage-Efficient Visual Document Retrieval: An Empirical Study on Reducing Patch-Level Embeddings
ACL 2025
Are We on the Right Way for Evaluating Large Vision-Language Models?
NeurIPS 2024
SA²VP: Spatially Aligned-and-Adapted Visual Prompt
AAAI 2024
ShareGPT4Video: Improving Video Understanding and Generation with Better Captions
NeurIPS 2024
ShareGPT4V: Improving Large Multi-Modal Models with Better Captions
ECCV 2024