mlsanityData to 14 Oct 2026

Evaluating point-light biological motion in multimodal large language models

arXiv 2509.23517 ↗First posted 27 Sep 2025cs.CV cs.AIcited by 0

On the map: Multimodal LLMs / vision-language models → Embodied and 3D vision-language models

Abstract (arXiv)

Humans can extract rich semantic information from minimal visual cues, as demonstrated by point-light displays (PLDs), which consist of sparse sets of dots localized to key joints of the human body. This ability emerges early in development and is largely attributed to human embodied experience. Since PLDs isolate body motion as the sole source of meaning, they represent key stimuli for testing the constraints of action understanding in these systems. Here we introduce ActPLD, the first benchmark to evaluate action processing in MLLMs from human PLDs. Tested models include state-of-the-art proprietary and open-source systems on single-actor and socially interacting PLDs. Our results reveal consistently low performance across models, introducing fundamental gaps in action and spatiotemporal understanding.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Embodied and 3D vision-language models, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 18 of its 49 references that are in the map. First posted on arXiv 27 Sep 2025.

Builds on

18 of 49 references.

Closest ancestors · 7

Same direction, newest first

  1. 2025VLM4D: Towards Spatiotemporal Awareness in Vision Language Models4 Aug
  2. 2025EmbodiedBench: Comprehensive Benchmarking Multi-modal Large Language Models for Vision-Driven Embodied Agents13 Feb
  3. 2025EmbodiedEval: Evaluate Multimodal LLMs as Embodied Agents21 Jan
  4. 2025ECBench: Can Multi-modal Foundation Models Understand the Egocentric World? A Holistic Embodied Cognition Benchmark9 Jan
  5. 2024VisualAgentBench: Towards Large Multimodal Models as Visual Foundation Agents12 Aug
  6. 2023RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control28 Jul
  7. 2023PaLM-E: An Embodied Multimodal Language Model6 Mar

Other references · 11

  1. 2022Flamingo: a Visual Language Model for Few-Shot Learningcited by 4,386
  2. 2024Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysiscited by 1,413
  3. 2023MVBench: A Comprehensive Multi-modal Video Understanding Benchmarkcited by 1,109
  4. 2024LongVideoBench: A Benchmark for Long-context Interleaved Video-Language Understandingcited by 665
  5. 2024LVBench: An Extreme Long Video Understanding Benchmarkcited by 410
  6. 2024PLLaVA : Parameter-free LLaVA Extension from Images to Videos for Video Dense Captioningcited by 322
  7. 2024MLVU: Benchmarking Multi-task Long Video Understandingcited by 292
  8. 2024CogVLM2: Visual Language Models for Image and Video Understandingcited by 217
  9. 2025MotionBench: Benchmarking and Improving Fine-grained Video Motion Understanding for Vision Language Modelscited by 70
  10. 2024SportQA: A Benchmark for Sports Understanding in Large Language Modelscited by 15
  11. 2025Can Large Models Fool the Eye? A New Turing Test for Biological Animationcited by 6

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026GIVE: Grounding Human Gestures in Vision-Language-Action Models
  2. 2025Beyond Description: Cognitively Benchmarking Fine-Grained Action for Embodied Agents
  3. 2025Igniting VLMs toward the Embodied Space
  4. 2025ChatMotion: A Multimodal Multi-Agent for Human Motion Analysis
  5. 2024The Language of Motion: Unifying Verbal and Non-verbal Language of 3D Human Motion
  6. 2026HumanCLAW: Can Vision-Language Models Act Through a Body?
  7. 2024MotionLLM: Understanding Human Behaviors from Human Motions and Videos
  8. 2025A Survey on Vision-Language-Action Models: An Action Tokenization Perspective