SSMI inserts Mamba-based state space modules into LVLMs, fine-tunes only 0.5% of parameters, and reports higher captioning, VQA, and retrieval scores than its baselines.
Llm-adapters: An adapter family for parameter-efficient fine-tuning of large language models
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Selective State Space Memory for Large Vision-Language Models
SSMI inserts Mamba-based state space modules into LVLMs, fine-tunes only 0.5% of parameters, and reports higher captioning, VQA, and retrieval scores than its baselines.