Multimodality · 2023
Open Production VLMs (Qwen-VL/InternVL/PaLI/Kosmos)
A family of open production vision-language models (represented by Qwen-VL, with InternVL, PaLI, and Kosmos) packaged image encoders plus LLMs into openly released, instruction-tuned multimodal assistants, removing the reliance on closed APIs for capable general-purpose VLMs.
Editorial record
Plain-language summary
These models connect a strong vision encoder to a language model and train through staged image-text pretraining followed by multimodal instruction tuning, adding capabilities such as higher-resolution input, region grounding, OCR, and multilingual support. Represented by Qwen-VL, the family shipped weights, tooling, and reproducible recipes that made competitive image understanding, document reading, and grounded visual dialogue available to build on directly rather than only behind proprietary services.
Knowledge graph
Relationships
Antecedents
Parallel workEvidence: Probable
Native/Omni Multimodality (Gemini / GPT-4V / GPT-4o)
Open VLMs parallel closed native multimodal
P-309
Descendants
ExtendsEvidence: Strongly supported
BLIP / BLIP-2 (Q-Former)
Q-Former pattern feeds production VLMs
P-306
ExtendsEvidence: Strongly supported
LLaVA: Visual Instruction Tuning
LLaVA recipe scaled to production VLMs
P-306
Source record
Provenance
- Record ID
- P-306
- Record created
- 2026-07-13
- Last reviewed
- 2026-07-14
- Record version
- 2
- https://arxiv.org/abs/2308.12966
- arXiv:2308.12966
Citation caveat: Citation metadata is approximate and marked unverified in the source dataset.