AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

Unified Multimodal Understanding via Byte-Pair Visual Encoding

Wanpeng Zhang, Yicheng Feng, Hao Luo, Yijiang Li, Zihao Yue, Sipeng Zheng, Zongqing Lu

ICCV 2025 · Vision-language and multimodal › Multimodal LLMs · approach: Instruction-tuned multimodal assistants · 10 citations (OpenAlex)

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 changedWhereMeasuredEffect
add BPE visual vocabulary on top of VQ tokens (ablation)Being-VL-0.5 · MMBenchaccuracy: 38.2 -> 71.8Improved
add BPE visual vocabulary on top of VQ tokens (ablation)Being-VL-0.5 · VQAv2accuracy: 54.3 -> 80.2Improved
add BPE visual vocabulary on top of VQ tokens (ablation)Being-VL-0.5 · MME-PMME-P score: 1301.2 -> 1525.8Improved
use priority-guided encoding and optimized training instead of frequency-only BPE (Being-VL-0)Being-VL-0.5 · MMBenchaccuracy: 44.0 -> 71.8Improved
use priority-guided encoding and optimized training instead of frequency-only BPE (Being-VL-0)Being-VL-0.5 · MME-PMME-P score: 1316.2 -> 1525.8Improved
increase BPE vocabulary from 8K to 16K (ablation)Being-VL-0.5 · POPEaccuracy: 84.3 -> 86.0Mixed
add curriculum-based data composition and progressive unfreezing (vs single stage) (ablation)Being-VL-0.5 · Perception avg scoreavg score: 71.2 -> 80.3Improved
add curriculum-based data composition (vs progressive only) (ablation)Being-VL-0.5 · Perception avg scoreavg score: 74.9 -> 80.3Improved
add progressive parameter unfreezing (vs curriculum only) (ablation)Being-VL-0.5 · Perception avg scoreavg score: 76.8 -> 80.3Improved
use foundation-to-instruction curriculum instead of reverse ordering (ablation)Being-VL-0.5 · Perception avg scoreavg score: 73.4 -> 80.3Improved
use foundation-to-instruction curriculum instead of random mixing (ablation)Being-VL-0.5 · Reasoning avg scoreavg score: 68.4 -> 71.1Improved
add selective fine-tuning stage (3-stage vs 2-stage unfreezing) (ablation)Being-VL-0.5 · Perception avg scoreavg score: 78.2 -> 80.3Improved

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy