# AULLM++: Structured-Token-Conditioned Large Language Models for Micro-Expression Action Unit Detection

arXiv: https://arxiv.org/abs/2603.08387 · HTML: https://mlsanity.com/paper/2603.08387/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 48 references that are in the map.
- First posted on arXiv 9 Mar 2026.

## Builds on (most cited first, 25 of 25)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [Learning to Prompt for Vision-Language Models](https://mlsanity.com/paper/2109.01134/) (2021)
- [Visual Prompt Tuning](https://mlsanity.com/paper/2203.12119/) (2022)
- [FitNets: Hints for Thin Deep Nets](https://mlsanity.com/paper/1412.6550/) (2014)
- [Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfer](https://mlsanity.com/paper/1612.03928/) (2016)
- [Large Language Models: A Survey](https://mlsanity.com/paper/2402.06196/) (2024)
- [Similarity-Preserving Knowledge Distillation](https://mlsanity.com/paper/1907.09682/) (2019)
- [Counterfactual VQA: A Cause-Effect Look at Language Bias](https://mlsanity.com/paper/2006.04315/) (2020)
- [Counterfactual Explanations and Algorithmic Recourses for Machine Learning: A Review](https://mlsanity.com/paper/2010.10596/) (2020)
- [Semantic Relationships Guided Representation Learning for Facial Action Unit Recognition](https://mlsanity.com/paper/1904.09939/) (2019)
- [Representation Flow for Action Recognition](https://mlsanity.com/paper/1810.01455/) (2018)
- [Domain Adversarial Neural Networks for Domain Generalization: When It Works and How to Improve](https://mlsanity.com/paper/2102.03924/) (2021)
- [AUFormer: Vision Transformers are Parameter-Efficient Facial Action Unit Detectors](https://mlsanity.com/paper/2403.04697/) (2024)
- [UniEmo: Unifying Emotional Understanding and Generation with Learnable Expert Queries](https://mlsanity.com/paper/2507.23372/) (2025)
- [H-GAR: A Hierarchical Interaction Framework via Goal-Driven Observation-Action Refinement for Robotic Manipulation](https://mlsanity.com/paper/2511.17079/) (2025)
- [ExpLLM: Towards Chain of Thought for Facial Expression Recognition](https://mlsanity.com/paper/2409.02828/) (2024)
- [Objective Class-based Micro-Expression Recognition through Simultaneous Action Unit Detection and Feature Aggregation](https://mlsanity.com/paper/2012.13148/) (2020)
- [Data Leakage and Evaluation Issues in Micro-Expression Analysis](https://mlsanity.com/paper/2211.11425/) (2022)
- [AU-LLM: Micro-Expression Action Unit Detection via Enhanced LLM-Based Feature Fusion](https://mlsanity.com/paper/2507.21778/) (2025)
- [Infused Suppression Of Magnification Artefacts For Micro-AU Detection](https://mlsanity.com/paper/2504.09326/) (2025)
- [Temporal and Spatial Feature Fusion Framework for Dynamic Micro Expression Recognition](https://mlsanity.com/paper/2505.16372/) (2025)

## Built on by (most cited first, 4 of 4)

- [Faithful Action-unit Causal Reasoning for Counterfactually Faithful Emotion Explanations](https://mlsanity.com/paper/2606.15779/) (2026)
- [GMoT: Gated Motion-Aware Tokenization for Fine-Grained Micro-Gesture Video Reasoning with Multimodal LLMs](https://mlsanity.com/paper/2607.16322/) (2026)
- [CardiacMamba: Fair and Robust RGB-RF Fusion for Remote Heart Rate Estimation via State Space Modeling](https://mlsanity.com/paper/2608.15831/) (2026)
- [FLOW: Feature-Level Optimal Warping for Generalized Remote Physiological Measurement](https://mlsanity.com/paper/2609.38913/) (2026)

## Abstract (arXiv)

Micro-expression Action Unit (AU) detection identifies localized AUs from subtle facial muscle activations, providing a foundation for decoding affective cues. Previous methods face three key limitations: (1) heavy reliance on low-density visual information, rendering discriminative evidence vulnerable to background noise; (2) coarse-grained feature processing that misaligns with the demand for fine-grained representations; and (3) neglect of inter-AU correlations, restricting the parsing of complex expression patterns. We propose AULLM++, a reasoning-oriented framework leveraging Large Language Models (LLMs), which injects visual features into textual prompts as actionable semantic premises to guide inference. It formulates AU prediction into three stages: evidence construction, structure modeling, and deduction-based prediction. Specifically, a Multi-Granularity Evidence-Enhanced Fusion Projector (MGE-EFP) fuses mid-level texture cues with high-level semantics, distilling them into a compact Content Token (CT). Furthermore, inspired by micro- and macro-expression AU correspondence, we encode AU relationships as a sparse structural prior and learn interaction strengths via a Relation-Aware AU Graph Neural Network (R-AUGNN), producing an Instruction Token (IT). We then fuse CT and IT into a structured textual prompt and introduce Counterfactual Consistency Regularization (CCR) to construct counterfactual samples, enhancing the model's generalization. Extensive experiments demonstrate AULLM++ achieves state-of-the-art performance on standard benchmarks and exhibits superior cross-domain generalization.