HMVLM: Human Motion-Vision-Lanuage Model via MoE LoRA

• URL: http://arxiv.org/abs/2511.01463v1
• Date: Mon, 03 Nov 2025 11:22:10 GMT
• Title: HMVLM: Human Motion-Vision-Lanuage Model via MoE LoRA
• Authors: Lei Hu, Yongjing Ye, Shihong Xia,
• Abstract summary: 3D human motion is being progressively integrated with foundation models to enhance multimodal understanding and cross-modal generation capabilities.<n>We propose the Human Motion-Vision-Language Model (HMVLM), a unified framework based on the Mixture of Expert Low-Rank Adaption(MoE LoRA) strategy.<n>We show that our method effectively alleviates knowledge forgetting during instruction-tuning and achieves remarkable performance across diverse human motion downstream tasks.
• Score: 19.21746661300773
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The expansion of instruction-tuning data has enabled foundation language models to exhibit improved instruction adherence and superior performance across diverse downstream tasks. Semantically-rich 3D human motion is being progressively integrated with these foundation models to enhance multimodal understanding and cross-modal generation capabilities. However, the modality gap between human motion and text raises unresolved concerns about catastrophic forgetting during this integration. In addition, developing autoregressive-compatible pose representations that preserve generalizability across heterogeneous downstream tasks remains a critical technical barrier. To address these issues, we propose the Human Motion-Vision-Language Model (HMVLM), a unified framework based on the Mixture of Expert Low-Rank Adaption(MoE LoRA) strategy. The framework leverages the gating network to dynamically allocate LoRA expert weights based on the input prompt, enabling synchronized fine-tuning of multiple tasks. To mitigate catastrophic forgetting during instruction-tuning, we introduce a novel zero expert that preserves the pre-trained parameters for general linguistic tasks. For pose representation, we implement body-part-specific tokenization by partitioning the human body into different joint groups, enhancing the spatial resolution of the representation. Experiments show that our method effectively alleviates knowledge forgetting during instruction-tuning and achieves remarkable performance across diverse human motion downstream tasks.

Related papers

• Toward Enhancing Representation Learning in Federated Multi-Task Settings [13.483094713610322]
  Federated multi-task learning (FMTL) seeks to collaboratively train customized models for users with different tasks.<n>We propose Muscle loss, a contrastive learning objective that simultaneously aligns representations from all participating models.<n>We develop FedMuscle, a practical and communication-efficient FMTL algorithm that naturally handles both model and task.
  arXiv  Detail & Related papers  (2026-02-02T04:39:36Z)
• Zero-Shot Open-Vocabulary Human Motion Grounding with Test-Time Training [39.7658823121591]
  ZOMG is a framework that segments motion sequences into semantically meaningful sub-actions without requiring any annotations or fine-tuning.<n>ZOMG integrates (1) language semantic partition, which leverages large language models to decompose instructions into ordered sub-action units, and (2) soft masking optimization.<n>Experiments on three motion-language datasets demonstrate state-of-the-art effectiveness and efficiency of motion grounding performance, outperforming prior methods by +8.7% mAP on HumanML3D benchmark.
  arXiv  Detail & Related papers  (2025-11-19T12:11:36Z)
• MotionVerse: A Unified Multimodal Framework for Motion Comprehension, Generation and Editing [53.98607267063729]
  MotionVerse is a framework to comprehend, generate, and edit human motion in both single-person and multi-person scenarios.<n>We employ a motion tokenizer with residual quantization, which converts continuous motion sequences into multi-stream discrete tokens.<n>We also introduce a textitDelay Parallel Modeling strategy, which temporally staggers the encoding of residual token streams.
  arXiv  Detail & Related papers  (2025-09-28T04:20:56Z)
• Foundation Model for Skeleton-Based Human Action Understanding [56.89025287217221]
  This paper presents a Unified Skeleton-based Dense Representation Learning framework.<n>USDRL consists of a Transformer-based Dense Spatio-Temporal (DSTE), Multi-Grained Feature Decorrelation (MG-FD), and Multi-Perspective Consistency Training (MPCT)
  arXiv  Detail & Related papers  (2025-08-18T02:42:16Z)
• DreamVLA: A Vision-Language-Action Model Dreamed with Comprehensive World Knowledge [41.030494146004806]
  We propose DreamVLA, a novel VLA framework that integrates comprehensive world knowledge forecasting to enable inverse dynamics modeling.<n>DreamVLA introduces a dynamic-region-guided world knowledge prediction, integrated with the spatial and semantic cues, which provide compact yet comprehensive representations for action planning.<n>Experiments on both real-world and simulation environments demonstrate that DreamVLA achieves 76.7% success rate on real robot tasks.
  arXiv  Detail & Related papers  (2025-07-06T16:14:29Z)
• GENMO: A GENeralist Model for Human MOtion [64.16188966024542]
  We present GENMO, a unified Generalist Model for Human Motion that bridges motion estimation and generation in a single framework.<n>Our key insight is to reformulate motion estimation as constrained motion generation, where the output motion must precisely satisfy observed conditioning signals.<n>Our novel architecture handles variable-length motions and mixed multimodal conditions (text, audio, video) at different time intervals, offering flexible control.
  arXiv  Detail & Related papers  (2025-05-02T17:59:55Z)
• Astrea: A MOE-based Visual Understanding Model with Progressive Alignment [10.943104653307294]
  Vision-Language Models (VLMs) based on Mixture-of-Experts (MoE) architectures have emerged as a pivotal paradigm in multimodal understanding.<n>We propose Astrea, a novel multi-expert collaborative VLM architecture based on progressive pre-alignment.
  arXiv  Detail & Related papers  (2025-03-12T14:44:52Z)
• Unified Generative and Discriminative Training for Multi-modal Large Language Models [88.84491005030316]
  Generative training has enabled Vision-Language Models (VLMs) to tackle various complex tasks. Discriminative training, exemplified by models like CLIP, excels in zero-shot image-text classification and retrieval. This paper proposes a unified approach that integrates the strengths of both paradigms.
  arXiv  Detail & Related papers  (2024-11-01T01:51:31Z)
• COLLAGE: Collaborative Human-Agent Interaction Generation using Hierarchical Latent Diffusion and Language Models [14.130327598928778]
  Large language models (LLMs) and hierarchical motion-specific vector-quantized variational autoencoders (VQ-VAEs) are proposed. Our framework generates realistic and diverse collaborative human-object-human interactions, outperforming state-of-the-art methods. Our work opens up new possibilities for modeling complex interactions in various domains, such as robotics, graphics and computer vision.
  arXiv  Detail & Related papers  (2024-09-30T17:02:13Z)
• CrowdMoGen: Zero-Shot Text-Driven Collective Motion Generation [43.12717215650305]
  We present CrowdMoGen, the first zero-shot framework for collective motion generation.<n>CrowdMoGen effectively groups individuals and generates event-aligned motion sequences from text prompts.<n>As the first framework of collective motion generation, CrowdMoGen has the potential to advance applications in urban simulation, crowd planning, and other large-scale interactive environments.
  arXiv  Detail & Related papers  (2024-07-08T17:59:36Z)
• Move as You Say, Interact as You Can: Language-guided Human Motion Generation with Scene Affordance [48.986552871497]
  We introduce a novel two-stage framework that employs scene affordance as an intermediate representation. By leveraging scene affordance maps, our method overcomes the difficulty in generating human motion under multimodal condition signals. Our approach consistently outperforms all baselines on established benchmarks, including HumanML3D and HUMANISE.
  arXiv  Detail & Related papers  (2024-03-26T18:41:07Z)
• DiverseMotion: Towards Diverse Human Motion Generation via Discrete Diffusion [70.33381660741861]
  We present DiverseMotion, a new approach for synthesizing high-quality human motions conditioned on textual descriptions. We show that our DiverseMotion achieves the state-of-the-art motion quality and competitive motion diversity.
  arXiv  Detail & Related papers  (2023-09-04T05:43:48Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.