AI Paper Atlas

Research map / Video / Video generation

CoMA: Compositional Human Motion Generation with Multi-modal Agents

Shanlin Sun, Jiaqi Xu, Gabriel de Araujo, Shenghan Zhou, Hanwen Zhang, Ziheng Huang, Chenyu You, Xiaohui Xie

AAAI 2026 · Video › Video generation · approach: Text-to-motion diffusion · 14 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 LLM Task Planner agent (recaption, segmentation, decomposition) on top of SPAM alone (ablation)SPAM · MTT complex motionR@1: 12.0 -> 30.1Improved
add Task Planner to SPAM (ablation)SPAM · MTT complex motionFID: 0.57 -> 0.48Improved
add Motion Reviewer self-correction (ablation)SPAM + Task Planner · MTT complex motionR@1: 30.1 -> 32.0Improved
add Motion Reviewer self-correction (ablation)SPAM + Task Planner · MTT complex motionFID: 0.48 -> 0.49Hurt
add further agent stage (+Task) to pipeline (ablation)CoMA · MTT complex motionR@3: 53.1 -> 54.6Improved
use spatially-aware SPAM instead of MoMask for generationtext-to-motion · HumanML3D testR-Precision Top-1: 0.521 -> 0.526Improved
use SPAM vs MoMask on FIDtext-to-motion · HumanML3D testFID: 0.045 -> 0.092Hurt
use full CoMA pipeline instead of baselinescomplex long prompts · User study, 42 promptsuser ratingImproved
use MVC motion captioner instead of MotionLLMmotion captioning · HumanML3D motion captioningRouge: 48.7 -> 45.79Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 3 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