AI Paper Atlas

Research map / Architectures and efficiency / Quantization

Quantized Visual Geometry Grounded Transformer

Weilun Feng, Haotong Qin, Mingqiang Wu, Chuanguang Yang, Yuqi Li, Xiangqi Li, Zhulin An, Libo Huang, Yulun Zhang, Michele Magno, Yongjun Xu

ICLR 2026 · Architectures and efficiency › Quantization · approach: Post-training quantization of ViTs

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 rotation + scale smoothing (DSFQ) to naive W4A4 quantization (ablation)VGGT-1B W4A4 · CO3Dv2 10 framesAUC@3: 9.7 -> 43.6Improved
add post-local scaling on top of rotation (ablation)VGGT-1B W4A4 · CO3Dv2 10 framesAUC@3: 32.5 -> 43.6Improved
add Hadamard rotation on top of scaling (ablation)VGGT-1B W4A4 · CO3Dv2 10 framesAUC@3: 21.2 -> 43.6Improved
rotate first then smooth (instead of smooth then rotate) (ablation)VGGT-1B W4A4 · CO3Dv2 10 framesAUC@3: 42.9 -> 43.6Improved
QuantVGGT vs QuaRot at W4A4VGGT-1B · CO3Dv2 20 framesAUC@30: 81.6 -> 88.2Improved
QuantVGGT vs QuaRot at W4A4VGGT-1B · DTU point mapAcc. mean (lower better): 1.593 -> 1.282Improved
QuantVGGT at W8A8VGGT-1B · DTU point mapAcc. mean (lower better): 1.185 -> 1.182No clear effect
noise-filtered diverse sampling vs random calibration sampling (ablation)QuantVGGT · CO3Dv2 W4A4AUC variance across seedsImproved
apply SmoothQuant at W4A4VGGT-1B · CO3Dv2 10 framesAUC@30: vs RTN 77.7 -> 75.4Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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