Training a vision encoder against a small surrogate made from a target LLM's early layers lets the encoder be grafted into the full LLM with no fine-tuning, matching some full-training results at roughly half the cost.
InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Zero-Shot Vision Encoder Grafting via LLM Surrogates
Training a vision encoder against a small surrogate made from a target LLM's early layers lets the encoder be grafted into the full LLM with no fine-tuning, matching some full-training results at roughly half the cost.