AI Paper Atlas

Research map / Vision-language and multimodal / Human and embodied modeling

UniMotion: A Unified Framework for Motion-Text-Vision Understanding and Generation

Ziyi Wang, Xinshun Wang, Shuang Chen, Yang Cong, Mengyuan Liu

ECCV 2026 · Vision-language and multimodal › Human and embodied modeling · approach: Text-driven human motion generation · 3 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 Dual-Posterior KL Alignment (DPA) (ablation)UniMotion · HumanML3D text-to-motionR-Precision Top-3: 0.818 -> 0.841Improved
add DPA (ablation)UniMotion · MotionFix motion editingR@3: 80.35 -> 84.94Improved
add DPA (ablation)UniMotion · Vision-to-motionMPJPE: 83.1 -> 75.0Improved
add Latent Reconstruction Alignment (LRA) pre-training (ablation)UniMotion · HumanML3D text-to-motionR-Precision Top-3: 0.801 -> 0.841Improved
add LRA pre-training (ablation)UniMotion · Motion predictionADE: 3.777 -> 3.172Improved
add LRA pre-training (ablation)UniMotion · Vision-to-motionMPJPE: 84.3 -> 75.0Improved
use hybrid attention (full within motion spans) instead of global causal only (ablation)UniMotion · MotionFix motion editingR@3: 79.6 -> 84.94Improved
use modality-routed LoRA instead of shared LoRA (ablation)UniMotion · Vision-to-motionMPJPE: 90.4 -> 75.0Improved
add LoRA adaptation to frozen LLM (ablation)UniMotion · HumanML3D text-to-motionR-Precision Top-3: 0.752 -> 0.818Improved
replace VQ-VAE with continuous CMA-VAE (ablation)UniMotion Gen-Branch embedder · HumanML3D text-to-motionR-Precision Top-3: 0.752 -> 0.824Improved
add the second embedder branch (dual-path) to generation branch only (ablation)UniMotion with CMA-VAE · Motion predictionADE: 4.862 -> 3.172Improved
add semantic branch to generation-only: M2T trade-off between branches (ablation)UniMotion with CMA-VAE · HumanML3D motion-to-text vs text-to-motionBertScore / R@3: 40.1 vs 36.3; 0.824 vs 0.798Mixed

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