AI News HubLIVE
Original source2 min read

MotionMERGE: A Multi-granular Framework for Human Motion Editing, Reasoning, Generation, and Explanation

MotionMERGE is a unified framework that bridges the granularity gap in motion-language models by explicitly modeling motion at part and temporal levels within a single LLM. It introduces Reasoning-Aware Granularity-Synergy pre-training and the MotionFineEdit dataset (981K triplets) with fine-grained corrective instructions and chain-of-thought annotations. Experiments demonstrate superior precision in motion generation, understanding, and editing, with compelling zero-shot generalization.

SourcearXiv Computer VisionAuthor: Bizhu Wu, Jinheng Xie, Wenting Chen, Zhe Kong, Jianfeng Ren, Linlin Shen, Ruibin Bai, Rong Qu

[2605.18956] MotionMERGE: A Multi-granular Framework for Human Motion Editing, Reasoning, Generation, and Explanation

[Submitted on 18 May 2026]

Title:MotionMERGE: A Multi-granular Framework for Human Motion Editing, Reasoning, Generation, and Explanation

View a PDF of the paper titled MotionMERGE: A Multi-granular Framework for Human Motion Editing, Reasoning, Generation, and Explanation, by Bizhu Wu and 7 other authors

View PDF HTML (experimental)

Abstract:Recent motion-language models unify tasks like comprehension and generation but operate at a coarse granularity, lacking fine-grained understanding and nuanced control over body parts needed for animation or interaction. This stems from fundamental issues in both the model and the data, in which the model can't focus on motion's localized pattern, and the training data lacks fine-grained supervision. To tackle this, we propose MotionMERGE, a unified framework that bridges the granularity gap. First, we pioneer the study of fine-grained languageguided motion control, including detailed understanding and localized editing, by explicitly modeling motion at part and temporal levels within a single LLM, thereby endowing the model with robust priors for precise control. Second, we design ReasoningAware Granularity-Synergy pre-training, a novel strategy that employs joint supervision for cross-granularity alignment, temporal grounding, localized alignment, motion coherency, and motion-grounded chain-of-thought (CoT) reasoning. This equips the model with fine-grained motion-language alignment, crossgranularity synergy, and explicit reasoning ability. Third, we curate MotionFineEdit, a large-scale dataset (837K atomic + 144K complex triplets) with the first fine-grained spatio-temporal corrective instructions and motion-grounded CoT annotations, establishing a new benchmark for fine-grained text-driven motion editing and motion-grounded reasoning. Extensive experiments demonstrate the capability of MotionMERGE for more precise motion generation, understanding, and editing, and compelling zero-shot generalization to other complex motion tasks. This work represents a significant step toward models that interact with motion in finer granularity and human-like reasoning.

Subjects:

Computer Vision and Pattern Recognition (cs.CV)

Cite as: arXiv:2605.18956 [cs.CV]

(or arXiv:2605.18956v1 [cs.CV] for this version)

https://doi.org/10.48550/arXiv.2605.18956

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Bizhu Wu [view email] [v1] Mon, 18 May 2026 18:00:04 UTC (20,301 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled MotionMERGE: A Multi-granular Framework for Human Motion Editing, Reasoning, Generation, and Explanation, by Bizhu Wu and 7 other authors

View PDF

HTML (experimental)

TeX Source

view license

Current browse context:

cs.CV

new | recent | 2026-05

Change to browse by:

cs

References & Citations

NASA ADS

Google Scholar

Semantic Scholar

Loading...

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)