{"paper":{"title":"Not All Tasks Quantize Equally: Fisher-Guided Quantization for Visual Geometry Transformer","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chuanguang Yang, Jiehao Luo, Jintao Cheng, Weilun Feng, Wei Zhang, Yipu Zhang, Yongjun Xu, Zhulin An","submitted_at":"2026-05-15T10:27:10Z","abstract_excerpt":"Feed-forward 3D reconstruction models, represented by Visual Geometry Grounded Transformer (VGGT), jointly predict multiple visual geometry tasks such as depth estimation, camera pose prediction, and point cloud reconstruction in a single forward pass. They have been widely adopted in 3D vision applications, but their billion-scale parameters bring substantial memory and computation overhead, posing challenges for on-device deployment. Post-Training Quantization (PTQ) is an effective technique to reduce this overhead. Existing PTQ methods for feed-forward 3D models mainly focus on handling hea"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.15828","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.15828/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-19T17:33:48.720480Z","status":"skipped","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T17:21:55.862186Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"47d19887b6fb18b6f6f76b51b6e1541620dac60384b72b704e05bcae3c414767"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}