Embodied Scene Understanding for Vision Language Models via MetaVQA
Paper
•
2501.09167
•
Published
Chenda Duan
Dadaism6
·
AI & ML interests
Multimodal Learning, Reinforcement Learning, Machine Autonumy, AI for Medicine
Recent Activity
authored
a paper
1 day ago
Embodied Scene Understanding for Vision Language Models via MetaVQA
authored
a paper
1 day ago
Learning from Active Human Involvement through Proxy Value Propagation
authored
a paper
1 day ago
Beyond Fact Retrieval: Episodic Memory for RAG with Generative Semantic Workspaces
Organizations
authored
5
papers
1 day ago
Learning from Active Human Involvement through Proxy Value Propagation
Paper
•
2502.03369
•
Published
Beyond Fact Retrieval: Episodic Memory for RAG with Generative Semantic Workspaces
Paper
•
2511.07587
•
Published
•
10
Omni-iEEG: A Large-Scale, Comprehensive iEEG Dataset and Benchmark for Epilepsy Research
Paper
•
2602.16072
•
Published
•
1
Panini: Continual Learning in Token Space via Structured Memory
Paper
•
2602.15156
•
Published
•
6
upvoted
2
papers
2 days ago
upvoted
a
paper
3 months ago
published
a
dataset
5 months ago
updated
2
datasets
5 months ago
published
a
dataset
5 months ago
updated
a
dataset
6 months ago
published
a
dataset
6 months ago
updated
a
model
over 1 year ago