conftrace_

vision-language connector

3 papers

Explore in graph

Co-occurring keywords

multimodal large language model (966) vision-language model (2348) vision transformer (1106) visual anchor (1) visual encoder (35) multi-layer feature (3) zero-shot capability (20) image understanding (87) information aggregation (27) large language model (13587)

Papers

Visual Anchors Are Strong Information Aggregators For Multimodal Large Language Model NIPS 2024
Dense Connector for MLLMs NIPS 2024
Improved Baselines with Visual Instruction Tuning CVPR 2024