VersaQ-3D quantizes VGGT to 4-bit weights using fused Walsh-Hadamard and DCT transforms without calibration data, and pairs it with a mixed-precision accelerator that reports 5.2x-10.8x speedups over edge GPUs.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AR 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
VersaQ-3D: Architecture Support for Visual Geometry Grounded Transformers via Versatile Quantization
VersaQ-3D quantizes VGGT to 4-bit weights using fused Walsh-Hadamard and DCT transforms without calibration data, and pairs it with a mixed-precision accelerator that reports 5.2x-10.8x speedups over edge GPUs.