Priority-guided byte-pair encoding of quantized image patches plus curriculum training yields an 8B discrete-token MLLM competitive with continuous-embedding models on VQA and multimodal benchmarks.
Vision transformer with quadrangle attention.IEEE Transactions on Pattern Analysis and Machine Intelligence, 2024
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Unified Multimodal Understanding via Byte-Pair Visual Encoding
Priority-guided byte-pair encoding of quantized image patches plus curriculum training yields an 8B discrete-token MLLM competitive with continuous-embedding models on VQA and multimodal benchmarks.