AI Paper Atlas

Research map / Video / Video generation

S-VAM: Shortcut Video-Action Model by Self-Distilling Geometric and Semantic Foresight

Haodong Yan, Zhide Zhong, Jiaguan Zhu, Junjie He, Weilin Yuan, Wenxuan Song, Xin Gong, Yingjie CAI, Guanyi Zhao, Xu Yan, Liu Bingbing, Yingcong Chen and 1 more

ECCV 2026 · Video › Video generation · approach: World-model video generation · 18 citations (OpenAlex)

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 geometric distillation (ablation)S-VAM · CALVIN ABC->Daverage sequence length: 4.16 -> 4.01Improved
add semantic distillation (ablation)S-VAM · CALVIN ABC->Daverage sequence length: 4.16 -> 3.99Improved
add semantic distillation (5th task success) (ablation)S-VAM · CALVIN ABC->D5th task success rate: 68.9% -> 64.1%Improved
use self-distilled targets from own multi-step video instead of ground-truth future frame VFM targets (ablation)S-VAM · CALVIN ABC->Daverage sequence length: 4.16 -> 3.82Improved
add Uni-Perceiver (ablation)S-VAM · CALVIN ABC->Daverage sequence length: 4.16 -> 3.72Improved
keep original diffusion feature in condition (ablation)S-VAM · CALVIN ABC->Daverage sequence length: 4.16 -> 3.93Improved
use dense DINOv2 instead of global CLIP as semantic target (ablation)S-VAM · CALVIN ABC->D (VFM teacher targets)average sequence length: 4.01 vs. 3.72Improved
use DPAv3 instead of VGGT as geometric target (ablation)S-VAM · CALVIN ABC->D (VFM teacher targets)average sequence length: 3.99 vs. 3.74Improved
use video foundation model targets (VideoMAEv2, V-JEPA2) instead of DINOv2 (ablation)S-VAM · CALVIN ABC->D (VFM teacher targets)average sequence length: 3.90 and 3.74 vs. 4.01Hurt
use DPAv3 rather than VGGT in the combined target (ablation)S-VAM · CALVIN ABC->D (VFM teacher targets)average sequence length: 4.16 -> 4.04Improved
use DINOv2 rather than SigLIP in the combined target (ablation)S-VAM · CALVIN ABC->D (VFM teacher targets)average sequence length: 4.16 -> 4.06Improved
replace one-step features (VPP) with S-VAM geometric and semantic foresightVPP · MetaWorld hard taskssuccess rate: 52.6% -> 68.4%Improved

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