MVAP-G: Generating Multi-view Adversarial Examples for VGGT (ECCV'26)
kwangmoo_yi · x · 2026-08-25
Song et al. released "MVAP-G" (ECCV'26 Oral), a method to generate multi-view adversarial examples against Visual Geometry Grounded Transformers. The official implementation is available on GitHub, including pre-training code. The author suggests this could be used to create adversarial stickers.
Related event: ECCV Paper Proposes MVAP-G to Attack Visual Geometry Transformers(2 posts)→
More from Research
- Tencent releases GameXpert-Bench to evaluate coding agents in game development — Tencent-Hunyuan · 2026-08-25
- ARC improves fairness in group-based RL for open-ended agents — ant-intl · 2026-08-25
- Improving diffusion-based image editing via concept scaling and dense supervision — inclusionAI · 2026-08-25
- Thinky offers up to $50k grants for open-weights AI safety research on Tinker — ZhongRuiqi · 2026-08-25
- REGRIND Improves Dexterous RL Sample Efficiency via Human Trajectory Initialization — HaozhiQ · 2026-08-25
- Real-time voice AI hears emotion but ignores it: 119 of 120 runs followed the script — Once_ina_Lifetime · 2026-08-25