mlsanityData to 7 Oct 2026

Multimodal emotion understanding

90 papers0 this weekHigh confidence in this grouping: the papers form one clear topicHigh confidence in this grouping: the papers form one clear topic · About

Keywords: emotion, emotional, emotions, affective, multimodal

Key facts. Multimodal emotion understanding: 90 papers on arXiv since 2023 (data through 7 Oct 2026). 11 of its 90 mapped papers (12%) cite “AffectGPT: A New Dataset, Model, and Benchmark for Emotion Understanding with Multimodal Large Language Models” (2025, arXiv 2501.16566). 10 of its 90 mapped papers (11%) cite “R1-Omni: Explainable Omni-Multimodal Emotion Recognition with Reinforcement Learning” (2025, arXiv 2503.05379). 3 new papers 17 Sep–7 Oct.

What’s new

17 Sep – 7 Oct 2026

3 new since 17 Sep

  1. LongEmo: Towards Emotion Understanding and Reasoning in Long Videos
  2. Decoding Affective Nuances: Enhancing MLLMs via Hierarchical Emotion Reasoning and Contrastive Discriminative Pruning
  3. Do Emotion Concepts Generalize Across Sources, Modalities, and Architectures in Vision-Language Models?

Foundations

Most cited by papers here

  1. AffectGPT: A New Dataset, Model, and Benchmark for Emotion Understanding with Multimodal Large Language Models2025cited by 11 here
  2. R1-Omni: Explainable Omni-Multimodal Emotion Recognition with Reinforcement Learning2025cited by 10 here
  3. EmoLLM: Multimodal Emotional Understanding Meets Large Language Models2024cited by 7 here
  4. MME-Emotion: A Holistic Evaluation Benchmark for Emotional Intelligence in Multimodal Large Language Models2025cited by 5 here
  5. EmoBench-M: Benchmarking Emotional Intelligence for Multimodal Large Language Models2025cited by 4 here

Lineage

The papers this direction builds on, oldest first.

Each paper on the line cites the one before.

  1. 2022Flamingo: a Visual Language Model for Few-Shot Learningcited by 7 here
  2. 2023InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuningcited by 8 here
  3. 2023MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Modelscited by 5 here
  4. 2023Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyondcited by 6 here
  5. 2024Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolutioncited by 12 here
  6. 2024MOSABench: Multi-Object Sentiment Analysis Benchmark for Evaluating Multimodal Large Language Models Understanding of Complex Imagecited by 5 here
  7. 2025MME-Emotion: A Holistic Evaluation Benchmark for Emotional Intelligence in Multimodal Large Language Modelscited by 5 here
17 more it builds on, not in this chain
  1. 2023Vision-Language Models for Vision Tasks: A Surveycited by 5 here
  2. 2023Otter: A Multi-Modal Model with In-Context Instruction Tuningcited by 4 here
  3. 2023Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understandingcited by 7 here
  4. 2023A Survey on Multimodal Large Language Modelscited by 4 here
  5. 2023Improved Baselines with Visual Instruction Tuningcited by 12 here
  6. 2023Video-LLaVA: Learning United Visual Representation by Alignment Before Projectioncited by 8 here
  7. 2023MVBench: A Comprehensive Multi-modal Video Understanding Benchmarkcited by 7 here
  8. 2023OneLLM: One Framework to Align All Modalities with Languagecited by 5 here
  9. 2023InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Taskscited by 4 here
  10. 2024MM-LLMs: Recent Advances in MultiModal Large Language Modelscited by 4 here
  11. 2024EmoLLM: Multimodal Emotional Understanding Meets Large Language Modelscited by 7 here
  12. 2024MiniCPM-V: A GPT-4V Level MLLM on Your Phonecited by 6 here
  13. 2024LLaVA-OneVision: Easy Visual Task Transfercited by 6 here
  14. 2025AffectGPT: A New Dataset, Model, and Benchmark for Emotion Understanding with Multimodal Large Language Modelscited by 11 here
  15. 2025R1-Omni: Explainable Omni-Multimodal Emotion Recognition with Reinforcement Learningcited by 10 here
  16. 2025HumanOmniV2: From Understanding to Omni-Modal Reasoning with Contextcited by 5 here
  17. 2025Qwen3-VL Technical Reportcited by 8 here

The 24 most cited of 226.

Browse

30 of 90, ranked 6–35

  1. 6Evaluating Vision-Language Models for Emotion Recognition20254
  2. 7Why We Feel: Breaking Boundaries in Emotional Reasoning with Multimodal Large Language Models20253
  3. 8FEALLM: Advancing Facial Emotion Analysis in Multimodal Large Language Models with Emotional Synergy and Reasoning20253
  4. 9Emotion-Coherent Reasoning for Multimodal LLMs via Emotional Rationale Verifier20253
  5. 10GPT as Psychologist? Preliminary Evaluations for GPT-4V on Visual Affective Computing20243
  6. 11EMO-R3: Reflective Reinforcement Learning for Emotional Reasoning in Multimodal Large Language Models20262
  7. 12EEmo-Bench: A Benchmark for Multi-modal Large Language Models on Image Evoked Emotion Assessment20252
  8. 13Benchmarking and Bridging Emotion Conflicts for Multimodal Emotion Reasoning20252
  9. 14Multimodal Large Language Models Meet Multimodal Emotion Recognition and Reasoning: A Survey20252
  10. 15Large Vision-Language Models as Emotion Recognizers in Context Awareness20242
All 30
  1. 16MEMO-Bench: A Multiple Benchmark for Text-to-Image and Multimodal Large Language Models on Human Emotion Analysis20242
  2. 17EmoVerse: Exploring Multimodal Large Language Models for Sentiment and Emotion Understanding20242
  3. 18Socratis: Are large multimodal models emotionally aware?20232
  4. 19Nano-EmoX: Unifying Multimodal Emotional Intelligence from Perception to Empathy20261
  5. 20Contrastive Language-Image Learning with Augmented Textual Prompts for 3D/4D FER Using Vision-Language Model20251
  6. 21Unsupervised Multiview Contrastive Language-Image Joint Learning with Pseudo-Labeled Prompts Via Vision-Language Model for 3D/4D Facial Expression Recognition20251
  7. 22Beyond Emotion Recognition: A Multi-Turn Multimodal Emotion Understanding and Reasoning Benchmark20251
  8. 23Rethinking Facial Expression Recognition in the Era of Multimodal Large Language Models: Benchmark, Datasets, and Beyond20251
  9. 24MIPS at SemEval-2024 Task 3: Multimodal Emotion-Cause Pair Extraction in Conversations with Multimodal Language Models20241
  10. 25Contextual Emotion Recognition using Large Vision Language Models20241
  11. 26QASA: Quality-Aware Semantic Augmentation for Robust Multimodal Sentiment Analysis20260
  12. 27Visual Affect Analysis: Predicting Emotions of Image Viewers with Vision-Language Models20260
  13. 28Unveiling the Cognitive Compass: Theory-of-Mind-Guided Multimodal Emotion Reasoning20260
  14. 29MEGC2026: Micro-Expression Grand Challenge on Visual Question Answering20260
  15. 30MA-Bench: Towards Fine-grained Micro-Action Understanding20260
  16. 31AICA-Bench: Holistically Examining the Capabilities of VLMs in Affective Image Content Analysis20260
  17. 32ActFER: Agentic Facial Expression Recognition via Active Tool-Augmented Visual Reasoning20260
  18. 33Why Do Vision Language Models Struggle To Recognize Human Emotions?20260
  19. 34EmoTrans: A Benchmark for Understanding, Reasoning, and Predicting Emotion Transitions in Multimodal LLMs20260
  20. 35Multimodal Large Language Models as Synthetic Participants in Video-Based Studies: An Evaluation20260