mlsanityData to 7 Oct 2026

Mojito: LLM-Aided Motion Instructor with Jitter-Reduced Inertial Tokens

arXiv 2502.16175 ↗First posted 22 Feb 2025cs.CV cs.AI cs.GRcited by 4

Not on the map. Why?

Abstract (arXiv)

Human bodily movements convey critical insights into action intentions and cognitive processes, yet existing multimodal systems primarily focused on understanding human motion via language, vision, and audio, which struggle to capture the dynamic forces and torques inherent in 3D motion. Inertial measurement units (IMUs) present a promising alternative, offering lightweight, wearable, and privacy-conscious motion sensing. However, processing of streaming IMU data faces challenges such as wireless transmission instability, sensor noise, and drift, limiting their utility for long-term real-time motion capture (MoCap), and more importantly, online motion analysis. To address these challenges, we introduce Mojito, an intelligent motion agent that integrates inertial sensing with large language models (LLMs) for interactive motion capture and behavioral analysis.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 70 of its 93 references that are in the map. First posted on arXiv 22 Feb 2025.

Builds on

70 of 93 references.

References · 70

  1. 2017Attention Is All You Needcited by 59,932
  2. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  3. 2024The Llama 3 Herd of Modelscited by 14,192
  4. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  5. 2020Denoising Diffusion Implicit Modelscited by 9,655
  6. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 4,993
  7. 2017Neural Discrete Representation Learningcited by 4,650
  8. 2022Robust Speech Recognition via Large-Scale Weak Supervisioncited by 3,972
  9. 2016Categorical Reparameterization with Gumbel-Softmaxcited by 2,708
  10. 2024Qwen2 Technical Reportcited by 2,076
  11. 2019Expressive Body Capture: 3D Hands, Face, and Body from a Single Imagecited by 1,600
  12. 2019Generating Diverse High-Fidelity Images with VQ-VAE-2cited by 1,376
38 more
  1. 2019AMASS: Archive of Motion Capture as Surface Shapescited by 1,208
  2. 2018On the Continuity of Rotation Representations in Neural Networkscited by 1,186
  3. 2023ImageBind: One Embedding Space To Bind Them Allcited by 1,162
  4. 2023MVBench: A Comprehensive Multi-modal Video Understanding Benchmarkcited by 1,086
  5. 2022Human Motion Diffusion Modelcited by 1,062
  6. 2022MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Modelcited by 768
  7. 2023MotionGPT: Human Motion as a Foreign Languagecited by 521
  8. 2022MotionCLIP: Exposing Human Motion Generation to CLIP Spacecited by 406
  9. 2024InternLM-XComposer2: Mastering Free-form Text-Image Composition and Comprehension in Vision-Language Large Modelcited by 326
  10. 2021HuMoR: 3D Human Motion Model for Robust Pose Estimationcited by 319
  11. 2023InternLM-XComposer: A Vision-Language Large Model for Advanced Text-image Comprehension and Compositioncited by 297
  12. 2021BABEL: Bodies, Action and Behavior with English Labelscited by 261
  13. 2023OmniControl: Control Any Joint at Any Time for Human Motion Generationcited by 233
  14. 2023Motion-X: A Large-scale 3D Expressive Whole-body Human Motion Datasetcited by 220
  15. 2024InternLM-XComposer-2.5: A Versatile Large Vision Language Model Supporting Long-Contextual Input and Outputcited by 195
  16. 2023OneLLM: One Framework to Align All Modalities with Languagecited by 185
  17. 2021SpeechT5: Unified-Modal Encoder-Decoder Pre-Training for Spoken Language Processingcited by 177
  18. 2024InternLM-XComposer2-4KHD: A Pioneering Large Vision-Language Model Handling Resolutions from 336 Pixels to 4K HDcited by 156
  19. 2023MotionGPT: Finetuned LLMs Are General-Purpose Motion Generatorscited by 145
  20. 2022Physical Inertial Poser (PIP): Physics-aware Real-time Human Motion Tracking from Sparse Inertial Sensorscited by 144
  21. 2023ImageBind-LLM: Multi-modality Instruction Tuningcited by 142
  22. 2017Sparse Inertial Poser: Automatic 3D Human Pose Estimation from Sparse IMUscited by 108
  23. 2023Avatars Grow Legs: Generating Smooth Human Motion from Sparse Tracking Inputs with Diffusion Modelcited by 104
  24. 20233D Human Pose Estimation via Intuitive Physicscited by 100
  25. 2023AnyMAL: An Efficient and Scalable Any-Modality Augmented Language Modelcited by 93
  26. 2024MotionLLM: Understanding Human Behaviors from Human Motions and Videoscited by 89
  27. 2022Transformer Inertial Poser: Real-time Human Motion Reconstruction from Sparse IMUs with Simultaneous Terrain Generationcited by 75
  28. 2023ChatPose: Chatting about 3D Human Posecited by 71
  29. 2024CoMo: Controllable Motion Generation through Language Guided Pose Code Editingcited by 66
  30. 2021SmoothNet: A Plug-and-Play Network for Refining Human Poses in Videoscited by 64
  31. 2023AvatarGPT: All-in-One Framework for Motion Understanding, Planning, Generation and Beyondcited by 63
  32. 2024MotionFix: Text-Driven 3D Human Motion Editingcited by 63
  33. 2024LaMP: Language-Motion Pretraining for Motion Generation, Retrieval, and Captioningcited by 58
  34. 2024MotionGPT-2: A General-Purpose Motion-Language Model for Motion Generation and Understandingcited by 58
  35. 2023EgoLocate: Real-time Motion Capture, Localization, and Mapping with Sparse Body-mounted Sensorscited by 48
  36. 2022LiDAR-aid Inertial Poser: Large-scale Human Motion Capture by Sparse Inertial and LiDAR Sensorscited by 43
  37. 2023PoseFix: Correcting 3D Human Poses with Natural Languagecited by 38
  38. 2022IMU2CLIP: Multimodal Contrastive Learning for IMU Motion Sensors from Egocentric Videos and Textcited by 36

50 most cited of 70 All 70 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 2; 2026: 2.

4 papers.

  1. 2025RadarLLM: Empowering Large Language Models to Understand Human Motion from Millimeter-Wave Point Cloud Sequencecited by 7
  2. 2025MoLingo: Motion-Language Alignment for Text-to-Human Motion Generationcited by 2
  3. 2026Kepler-Encoder-v0.1: Towards a Multimodal Embedding Model for Robotscited by 1
  4. 2026MyoSem: Aligning Electromyography to Natural-Language Action Semantics for Hand Action Understandingcited by 0