# ReMoMask: Retrieval-Augmented Masked Motion Generation

arXiv: https://arxiv.org/abs/2508.02605 · HTML: https://mlsanity.com/paper/2508.02605/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal RAG, one of 15 directions in Retrieval-augmented generation.
- Builds on 29 of its 40 references that are in the map.
- First posted on arXiv 4 Aug 2025.

## Placed in

- Retrieval-augmented generation / [Multimodal RAG](https://mlsanity.com/rag/multimodal-rag/)

## Builds on (most cited first, 29 of 29)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter](https://mlsanity.com/paper/1910.01108/) (2019)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [Retrieval-Augmented Generation for Large Language Models: A Survey](https://mlsanity.com/paper/2312.10997/) (2023)
- [MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Model](https://mlsanity.com/paper/2208.15001/) (2022)
- [Muse: Text-To-Image Generation via Masked Generative Transformers](https://mlsanity.com/paper/2301.00704/) (2023)
- [Passage Re-ranking with BERT](https://mlsanity.com/paper/1901.04085/) (2019)
- [T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representations](https://mlsanity.com/paper/2301.06052/) (2023)
- [MotionGPT: Human Motion as a Foreign Language](https://mlsanity.com/paper/2306.14795/) (2023)
- [MoCoGAN: Decomposing Motion and Content for Video Generation](https://mlsanity.com/paper/1707.04993/) (2017)
- [MotionCLIP: Exposing Human Motion Generation to CLIP Space](https://mlsanity.com/paper/2203.08063/) (2022)
- [MoMask: Generative Masked Modeling of 3D Human Motions](https://mlsanity.com/paper/2312.00063/) (2023)
- [TM2T: Stochastic and Tokenized Modeling for the Reciprocal Generation of 3D Human Motions and Texts](https://mlsanity.com/paper/2207.01696/) (2022)
- [The KIT Motion-Language Dataset](https://mlsanity.com/paper/1607.03827/) (2016)
- [ReMoDiffuse: Retrieval-Augmented Motion Diffusion Model](https://mlsanity.com/paper/2304.01116/) (2023)
- [Language2Pose: Natural Language Grounded Pose Forecasting](https://mlsanity.com/paper/1907.01108/) (2019)
- [TMR: Text-to-Motion Retrieval Using Contrastive 3D Human Motion Synthesis](https://mlsanity.com/paper/2305.00976/) (2023)
- [Text2Gestures: A Transformer-Based Network for Generating Emotive Body Gestures for Virtual Agents](https://mlsanity.com/paper/2101.11101/) (2021)
- [FineMoGen: Fine-Grained Spatio-Temporal Motion Generation and Editing](https://mlsanity.com/paper/2312.15004/) (2023)
- [VideoRAG: Retrieval-Augmented Generation with Extreme Long-Context Videos](https://mlsanity.com/paper/2502.01549/) (2025)
- [ParCo: Part-Coordinating Text-to-Motion Synthesis](https://mlsanity.com/paper/2403.18512/) (2024)
- [Motion Anything: Any to Motion Generation](https://mlsanity.com/paper/2503.06955/) (2025)
- [MoGenTS: Motion Generation based on Spatial-Temporal Joint Modeling](https://mlsanity.com/paper/2409.17686/) (2024)
- [InfiniMotion: Mamba Boosts Memory in Transformer for Arbitrary Long Motion Generation](https://mlsanity.com/paper/2407.10061/) (2024)
- [Motion Avatar: Generate Human and Animal Avatars with Arbitrary Motion](https://mlsanity.com/paper/2405.11286/) (2024)
- [KMM: Key Frame Mask Mamba for Extended Motion Generation](https://mlsanity.com/paper/2411.06481/) (2024)
- [MoRAG -- Multi-Fusion Retrieval Augmented Generation for Human Motion](https://mlsanity.com/paper/2409.12140/) (2024)
- [RMD: A Simple Baseline for More General Human Motion Generation via Training-free Retrieval-Augmented Motion Diffuse](https://mlsanity.com/paper/2412.04343/) (2024)

## Built on by (most cited first, 11 of 11)

- [Causal Motion Diffusion Models for Autoregressive Motion Generation](https://mlsanity.com/paper/2602.22594/) (2026)
- [IRG-MotionLLM: Interleaving Motion Generation, Assessment and Refinement for Text-to-Motion Generation](https://mlsanity.com/paper/2512.10730/) (2025)
- [SafeMo: Linguistically Grounded Unlearning for Trustworthy Text-to-Motion Generation](https://mlsanity.com/paper/2601.00590/) (2026)
- [Multimodal Data Storage and Retrieval for Embodied AI: A Survey](https://mlsanity.com/paper/2508.13901/) (2025)
- [PartRAG: Retrieval-Augmented Part-Level 3D Generation and Editing](https://mlsanity.com/paper/2602.17033/) (2026)
- [Retrieving and Refining Winning Noise Tickets for Diffusion-Based Motion Generation](https://mlsanity.com/paper/2607.06843/) (2026)
- [MoRL: Reinforced Reasoning for Unified Motion Understanding and Generation](https://mlsanity.com/paper/2602.14534/) (2026)
- [Towards Highly-Constrained Human Motion Generation with Retrieval-Guided Diffusion Noise Optimization](https://mlsanity.com/paper/2605.08054/) (2026)
- [InterCMDM: Block-Causal Diffusion for Autoregressive Human Interaction Generation](https://mlsanity.com/paper/2607.01743/) (2026)
- [ReMoMask-2: Latent Retrieval-Augmented Masked Motion Generation](https://mlsanity.com/paper/2609.08365/) (2026)
- [BiMoGen: Bidirectional Motion-Text Generation via Unified Masked Discrete Diffusion](https://mlsanity.com/paper/2609.35407/) (2026)

## Abstract (arXiv)

Text-to-Motion (T2M) generation aims to synthesize realistic and semantically aligned human motion sequences from natural language descriptions. However, current approaches face dual challenges: Generative models (e.g., diffusion models) suffer from limited diversity, error accumulation, and physical implausibility, while Retrieval-Augmented Generation (RAG) methods exhibit diffusion inertia, partial-mode collapse, and asynchronous artifacts. To address these limitations, we propose ReMoMask, a unified framework integrating three key innovations: 1) A Bidirectional Momentum Text-Motion Model decouples negative sample scale from batch size via momentum queues, substantially improving cross-modal retrieval precision; 2) A Semantic Spatio-temporal Attention mechanism enforces biomechanical constraints during part-level fusion to eliminate asynchronous artifacts; 3) RAG-Classier-Free Guidance incorporates minor unconditional generation to enhance generalization. Built upon MoMask's RVQ-VAE, ReMoMask efficiently generates temporally coherent motions in minimal steps. Extensive experiments on standard benchmarks demonstrate the state-of-the-art performance of ReMoMask, achieving a 3.88% and 10.97% improvement in FID scores on HumanML3D and KIT-ML, respectively, compared to the previous SOTA method RAG-T2M. Code: https://github.com/AIGeeksGroup/ReMoMask. Website: https://aigeeksgroup.github.io/ReMoMask.