AI Paper Atlas

Research map / Video / Video generation

SOSControl: Enhancing Human Motion Generation Through Saliency-Aware Symbolic Orientation and Timing Control

Ho Yin Au, Junkun Jiang, Jie Chen

AAAI 2026 · Video › Video generation · approach: Text-to-motion diffusion · 2 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 SMS-based training data processing (ablation)SOSControl · HumanML3D testL2-Rot6D / FID: 0.499 -> 0.325 L2-Rot6D; 13.494 -> 3.892 FIDImproved
add SMS-based training data processing (ablation)SOSControl · HumanML3D testSOS-Acc: 0.991 -> 0.988No clear effect
add SMS-based training data processing (ablation)OmniControl · HumanML3D testSOS-Acc: 0.225 -> 0.873Improved
add test-time iterative optimization (ablation)SOSControl · HumanML3D testSOS-Acc: 0.531 -> 0.988Improved
add diffusion-time iterative optimization (ablation)SOSControl · HumanML3D testSOS-Acc: 0.531 -> 0.535No clear effect
add diffusion-time on top of test-time optimization (ablation)SOSControl · HumanML3D testFID / MMD: FID 4.209 -> 3.892; MMD 6.125 -> 6.199Mixed
add diffusion-time iterative optimization (ablation)GMD 1-stage · HumanML3D testSOS-Acc: 0.111 -> 0.113No clear effect
use text-only MDM instead of SOS-conditioned modelMDM · HumanML3D testFID: FID 2.592 vs 3.892; SOS-Acc 0.151 vs 0.988Mixed

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