# GMoT: Gated Motion-Aware Tokenization for Fine-Grained Micro-Gesture Video Reasoning with Multimodal LLMs

arXiv: https://arxiv.org/abs/2607.16322 · HTML: https://mlsanity.com/paper/2607.16322/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Multimodal reasoning, one of 17 directions in LLM reasoning.
- Builds on 31 of its 64 references that are in the map.
- First posted on arXiv 15 Jul 2026.

## Placed in

- LLM reasoning / [Multimodal reasoning](https://mlsanity.com/lr/multimodal-reasoning/)
- Multimodal LLMs / vision-language models / [Video understanding with MLLMs](https://mlsanity.com/mllm/video-understanding-with-mllms/)

## Builds on (most cited first, 30 of 31)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [Qwen3-VL Technical Report](https://mlsanity.com/paper/2511.21631/) (2025)
- [Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond](https://mlsanity.com/paper/2308.12966/) (2023)
- [Is Space-Time Attention All You Need for Video Understanding?](https://mlsanity.com/paper/2102.05095/) (2021)
- [Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling](https://mlsanity.com/paper/2412.05271/) (2024)
- [ZeRO: Memory Optimizations Toward Training Trillion Parameter Models](https://mlsanity.com/paper/1910.02054/) (2019)
- [SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features](https://mlsanity.com/paper/2502.14786/) (2025)
- [Video Swin Transformer](https://mlsanity.com/paper/2106.13230/) (2021)
- [Video-R1: Reinforcing Video Reasoning in MLLMs](https://mlsanity.com/paper/2503.21776/) (2025)
- [SWIFT:A Scalable lightWeight Infrastructure for Fine-Tuning](https://mlsanity.com/paper/2408.05517/) (2024)
- [VideoLLM: Modeling Video Sequence with Large Language Models](https://mlsanity.com/paper/2305.13292/) (2023)
- [LVAgent: Long Video Understanding by Multi-Round Dynamical Collaboration of MLLM Agents](https://mlsanity.com/paper/2503.10200/) (2025)
- [Joint Skeletal and Semantic Embedding Loss for Micro-gesture Classification](https://mlsanity.com/paper/2307.10624/) (2023)
- [UniEmo: Unifying Emotional Understanding and Generation with Learnable Expert Queries](https://mlsanity.com/paper/2507.23372/) (2025)
- [DeltaVLA: Prior-Guided Vision-Language-Action Models via World Knowledge Variation](https://mlsanity.com/paper/2603.08361/) (2026)
- [EALD-MLLM: Emotion Analysis in Long-sequential and De-identity videos with Multi-modal Large Language Model](https://mlsanity.com/paper/2405.00574/) (2024)
- [AffectAgent: Collaborative Multi-Agent Reasoning for Retrieval-Augmented Multimodal Emotion Recognition](https://mlsanity.com/paper/2604.12735/) (2026)
- [OmniOPSD: Rationale-Privileged On-Policy Self-Distillation for Affective Computing](https://mlsanity.com/paper/2606.15920/) (2026)
- [AULLM++: Structured-Token-Conditioned Large Language Models for Micro-Expression Action Unit Detection](https://mlsanity.com/paper/2603.08387/) (2026)
- [Navigating the Emotion Tree: Hierarchical Hyperbolic RAG for Multimodal Emotion Recognition](https://mlsanity.com/paper/2605.18884/) (2026)
- [TinyLLaVA-Video: Towards Smaller LMMs for Video Understanding with Group Resampler](https://mlsanity.com/paper/2501.15513/) (2025)
- [DFM: Difference Feature Modeling with Text-Guided Gated Contrastive Loss for Remote Sensing Image Change Captioning](https://mlsanity.com/paper/2606.27410/) (2026)
- [Reflect-R1: Evidence-Driven Reflection for Self-Correction in Long Video Understanding](https://mlsanity.com/paper/2606.27922/) (2026)
- [RSICCLLM: A Multimodal Large Language Model for Remote Sensing Image Change Captioning](https://mlsanity.com/paper/2606.28266/) (2026)

## Abstract (arXiv)

Micro-gesture recognition demands the detection of fleeting, spatially localized movements that are frequently overwhelmed by dominant static appearances and background noise. While Multimodal Large Language Models (MLLMs) excel at general video understanding, they inherently struggle with subtle kinematics and often rely on static posture priors. To this end, we propose GMoT, a Gated Motion-Aware Tokenization module that explicitly distills sparse kinematic evidence into a compact sequence prior to temporal modeling. GMoT dynamically spotlights action-relevant regions via spatially weighted pooling, extracts adjacent-frame temporal differencing to capture precise motion energy, and adaptively fuses these cues into the visual stream using a conservatively initialized semantic gate. To transition from simple classification to evidence-grounded reasoning, we further introduce a progressive reward-guided policy refinement paradigm, supported by a semi-supervised annotation pipeline that generates anatomically focused captions. Beyond achieving the best Top-1 accuracy among the compared methods on iMiGUE (67.32%) and SMG (73.11%), improving the Qwen3-VL-8B baseline by +6.80 and +3.11 points, our framework introduces Body-Region Grounding (BRG) Recall as an anatomical-grounding proxy conditioned on correct predictions, together with an overlapping-label cross-domain transfer protocol between iMiGUE and SMG. Extensive evaluations demonstrate that our GMoT-augmented model improves in-domain accuracy, retains clear gains under label-preserving corruptions, and improves accuracy-oriented cross-domain transfer under explicit small-split caveats while maintaining high anatomical grounding in its generated rationales.