MPM merges mutual nearest-neighbor token pairs in cosine space for ViTs, records a merge map for reconstruction, and delivers up to 60% latency reduction on Raspberry Pi 5 and 20% throughput gain on H100 with under 3% mIoU drop on ADE20K.
Token cropr: Faster vits for quite a few tasks
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
MPM: Mutual Pair Merging for Efficient Vision Transformers
MPM merges mutual nearest-neighbor token pairs in cosine space for ViTs, records a merge map for reconstruction, and delivers up to 60% latency reduction on Raspberry Pi 5 and 20% throughput gain on H100 with under 3% mIoU drop on ADE20K.