Research map / Vision-language and multimodal / Multimodal LLMs
Vary: Scaling up the Vision Vocabulary for Large Vision-Language Models
Haoran Wei, Lingyu Kong, Jinyue Chen, Liang Zhao, Zheng Ge, Jinrong Yang, Jianjian Sun, Chunrui Han, Xiangyu Zhang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add new SAM-based vision vocabulary alongside CLIP (Vary-base with Vicuna-7B and LLaVA-665k SFT) | LLaVA-1.5-style LVLM · MM-Vet | total score: 30.5 -> 32.9 | Improved |
| use Qwen-7B and LLaVA-80k instead of Vicuna-7B and LLaVA-665k | Vary-base · MM-Vet | total score: 32.9 -> 36.2 | Improved |
| scale up vision vocabulary, Vary-base versus Nougat on markdown conversion | Vary-base · Markdown conversion average (own test set) | edit distance: 0.245 -> 0.181 | Improved |
| scale up vision vocabulary, Vary-base versus Nougat on English plain-text OCR F1 | Vary-base · Document OCR English (own test set) | F1-score: 89.91 -> 88.24 | No clear effect |
| use 665k instead of 80k SFT data (ablation) | Vary-base · DocVQA val | ANLS: 78.2 -> 78.1 | No clear effect |
| use 665k instead of 80k SFT data (ablation) | Vary-base · ChartQA average | relaxed accuracy: 65.3 -> 66.1 | Improved |
Closest papers by meaning
- Synthesize Diagnose and Optimize: Towards Fine-Grained Vision-Language Understanding (CVPR 2024 · similarity 0.89)
- Are We on the Right Way for Evaluating Large Vision-Language Models? (NeurIPS 2024 · similarity 0.89)
- MMLongBench: Benchmarking Long-Context Vision-Language Models Effectively and Thoroughly (NeurIPS 2025 · similarity 0.88)
- VladVA: Discriminative Fine-tuning of LVLMs (CVPR 2025 · similarity 0.88)
- From Head to Tail: Towards Balanced Representation in Large Vision-Language Models through Adaptive Data Calibration (CVPR 2025 · similarity 0.88)
- From Pixels to Words -- Towards Native Vision-Language Primitives at Scale (ICLR 2026 · similarity 0.88)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
