{"total":82,"rows":[{"id":"2402.11574","title":"Visual In-Context Learning for Large Vision-Language Models","created":"2024-02-18","cited_by_count":128,"area":"mllm"},{"id":"2406.11161","title":"Emotion-LLaMA: Multimodal Emotion Recognition and Reasoning with Instruction Tuning","created":"2024-06-17","cited_by_count":121,"area":"lr"},{"id":"2404.16670","title":"EmoVIT: Revolutionizing Emotion Insights with Visual Instruction Tuning","created":"2024-04-25","cited_by_count":43,"area":null},{"id":"2312.04293","title":"GPT-4V with Emotion: A Zero-shot Benchmark for Generalized Emotion Recognition","created":"2023-12-07","cited_by_count":38,"area":null},{"id":"2401.04608","title":"EmoGen: Emotional Image Content Generation with Text-to-Image Diffusion Models","created":"2024-01-09","cited_by_count":37,"area":"diffusion"},{"id":"2405.12661","title":"EmoEdit: Evoking Emotions through Image Manipulation","created":"2024-05-21","cited_by_count":30,"area":null},{"id":"2502.05660","title":"Evaluating Vision-Language Models for Emotion Recognition","created":"2025-02-08","cited_by_count":19,"area":"lr"},{"id":"2507.23372","title":"UniEmo: Unifying Emotional Understanding and Generation with Learnable Expert Queries","created":"2025-07-31","cited_by_count":18,"area":null},{"id":"2505.19694","title":"Knowledge-Aligned Counterfactual-Enhancement Diffusion Perception for Unsupervised Cross-Domain Visual Emotion Recognition","created":"2025-05-26","cited_by_count":17,"area":null},{"id":"2403.08255","title":"Make Me Happier: Evoking Emotions Through Image Diffusion Models","created":"2024-03-13","cited_by_count":16,"area":"diffusion"},{"id":"2504.16405","title":"EEmo-Bench: A Benchmark for Multi-modal Large Language Models on Image Evoked Emotion Assessment","created":"2025-04-23","cited_by_count":15,"area":"mllm"},{"id":"2401.04716","title":"Low-Resource Vision Challenges for Foundation Models","created":"2024-01-09","cited_by_count":13,"area":null},{"id":"2505.18699","title":"Affective Image Editing: Shaping Emotional Factors via Text Descriptions","created":"2025-05-24","cited_by_count":12,"area":null},{"id":"2409.14083","title":"SURf: Teaching Large Vision-Language Models to Selectively Utilize Retrieved Information","created":"2024-09-21","cited_by_count":11,"area":"mllm"},{"id":"2506.03652","title":"EmoArt: A Multidimensional Dataset for Emotion-Aware Artistic Generation","created":"2025-06-04","cited_by_count":11,"area":"diffusion"},{"id":"2509.18849","title":"MAPO: Mixed Advantage Policy Optimization","created":"2025-09-23","cited_by_count":11,"area":"lr"},{"id":"2508.03535","title":"CoEmoGen: Towards Semantically-Coherent and Scalable Emotional Image Content Generation","created":"2025-08-05","cited_by_count":9,"area":null},{"id":"2409.00304","title":"StimuVAR: Spatiotemporal Stimuli-aware Video Affective Reasoning with Multimodal Large Language Models","created":"2024-08-31","cited_by_count":8,"area":"lr"},{"id":"2412.15677","title":"AI-generated Image Quality Assessment in Visual Communication","created":"2024-12-20","cited_by_count":7,"area":null},{"id":"2511.12554","title":"EmoVerse: A MLLMs-Driven Emotion Representation Dataset for Interpretable Visual Emotion Analysis","created":"2025-11-16","cited_by_count":7,"area":null},{"id":"2607.07907","title":"Multimodal Unlearning Across Vision, Language, Video, and Audio: Survey of Methods, Datasets, and Benchmarks","created":"2026-07-08","cited_by_count":7,"area":"safety"},{"id":"2308.16741","title":"Socratis: Are large multimodal models emotionally aware?","created":"2023-08-31","cited_by_count":5,"area":"mllm"},{"id":"2511.19982","title":"EmoFeedback$^2$: Reinforcement of Continuous Emotional Image Generation via LVLM-based Reward and Textual Feedback","created":"2025-11-25","cited_by_count":5,"area":null},{"id":"2601.16449","title":"Emotion-LLaMAv2 and MMEVerse: A New Framework and Benchmark for Multimodal Emotion Understanding","created":"2026-01-23","cited_by_count":5,"area":null},{"id":"2506.11162","title":"VIBE: Can a VLM Read the Room?","created":"2025-06-11","cited_by_count":4,"area":null},{"id":"2507.18929","title":"MGHFT: Multi-Granularity Hierarchical Fusion Transformer for Cross-Modal Sticker Emotion Recognition","created":"2025-07-25","cited_by_count":4,"area":"mllm"},{"id":"2508.17718","title":"Instant Preference Alignment for Text-to-Image Diffusion Models","created":"2025-08-25","cited_by_count":4,"area":"diffusion"},{"id":"2512.15528","title":"EmoCaliber: Advancing Reliable Visual Emotion Comprehension via Confidence Verbalization and Calibration","created":"2025-12-17","cited_by_count":4,"area":null},{"id":"2512.22437","title":"EmoCtrl: Controllable Emotional Image Content Generation","created":"2025-12-27","cited_by_count":4,"area":null},{"id":"2601.12326","title":"EmoKGEdit: Training-free Affective Injection via Visual Cue Transformation","created":"2026-01-18","cited_by_count":4,"area":null},{"id":"2602.01173","title":"EEmo-Logic: A Unified Dataset and Multi-Stage Framework for Comprehensive Image-Evoked Emotion Assessment","created":"2026-02-01","cited_by_count":4,"area":null},{"id":"2409.18877","title":"UniEmoX: Cross-modal Semantic-Guided Large-Scale Pretraining for Universal Scene Emotion Perception","created":"2024-09-27","cited_by_count":3,"area":null},{"id":"2501.15519","title":"Fuzzy-aware Loss for Source-free Domain Adaptation in Visual Emotion Recognition","created":"2025-01-26","cited_by_count":3,"area":null},{"id":"2503.11290","title":"EmoAgent: A Multi-Agent Framework for Diverse Affective Image Manipulation","created":"2025-03-14","cited_by_count":3,"area":null},{"id":"2508.20765","title":"Looking Beyond the Obvious: A Survey on Abstract Concept Recognition for Video Understanding","created":"2025-08-28","cited_by_count":3,"area":null},{"id":"2509.21950","title":"Customizing Visual Emotion Evaluation for MLLMs: An Open-vocabulary, Multifaceted, and Scalable Approach","created":"2025-09-26","cited_by_count":3,"area":"mllm"},{"id":"2511.21051","title":"MUSE: Manipulating Unified Framework for Synthesizing Emotions in Images via Test-Time Optimization","created":"2025-11-26","cited_by_count":3,"area":"diffusion"},{"id":"2604.05900","title":"AICA-Bench: Holistically Examining the Capabilities of VLMs in Affective Image Content Analysis","created":"2026-04-07","cited_by_count":3,"area":"mllm"},{"id":"2607.10165","title":"EmoStyle: Affective Conditioning of Style-Specialist Experts for Emotional Image Generation","created":"2026-07-11","cited_by_count":3,"area":null},{"id":"2405.00942","title":"Teaching Human Behavior Improves Content Understanding Abilities Of LLMs","created":"2024-05-02","cited_by_count":2,"area":null},{"id":"2503.13260","title":"Don't Judge Before You CLIP: A Unified Approach for Perceptual Tasks","created":"2025-03-17","cited_by_count":2,"area":null},{"id":"2604.10454","title":"AIM-Bench: Benchmarking and Improving Affective Image Manipulation via Fine-Grained Hierarchical Control","created":"2026-04-12","cited_by_count":2,"area":null},{"id":"2607.23920","title":"What Can I Edit? Open-Ended Strategy Discovery and the Emotion Editability Landscape","created":"2026-07-27","cited_by_count":2,"area":null},{"id":"2411.05985","title":"Generating Fearful Images: Investigating Potential Emotional Biases in Image-Generation Models","created":"2024-11-08","cited_by_count":1,"area":null},{"id":"2503.00049","title":"Omni-SILA: Towards Omni-scene Driven Visual Sentiment Identifying, Locating and Attributing in Videos","created":"2025-02-26","cited_by_count":1,"area":null},{"id":"2505.14660","title":"EmoGist: Efficient In-Context Learning for Visual Emotion Understanding","created":"2025-05-20","cited_by_count":1,"area":null},{"id":"2505.24342","title":"VAEER: Visual Attention-Inspired Emotion Elicitation Reasoning","created":"2025-05-30","cited_by_count":1,"area":null},{"id":"2507.14024","title":"Moodifier: MLLM-Enhanced Emotion-Driven Image Editing","created":"2025-07-18","cited_by_count":1,"area":"mllm"},{"id":"2602.11658","title":"EmoSpace: Immersive Affective Image Generation Guided by Fine-Grained Emotion Prototypes","created":"2026-02-12","cited_by_count":1,"area":null},{"id":"2603.10349","title":"EmoStory: Emotion-Aware Story Generation","created":"2026-03-11","cited_by_count":1,"area":null},{"id":"2604.00933","title":"EmoScene: A Dual-space Dataset for Controllable Affective Image Generation","created":"2026-04-01","cited_by_count":1,"area":"diffusion"},{"id":"2607.21061","title":"MVEI & EmObserver: Empowering MLLM-Oriented Visual Emotional Intelligence via Emotion Statement Judgement","created":"2026-07-23","cited_by_count":1,"area":null},{"id":"2609.02616","title":"AffectDelta: Beyond Emotion Labels for Image Editing","created":"2026-09-02","cited_by_count":1,"area":null},{"id":"2609.22135","title":"Read-Best Is Not Steer-Best: A Probing--Steering Layer Dissociation in Omni-Modal Large Language Models","created":"2026-08-24","cited_by_count":1,"area":"mechinterp"},{"id":"2410.07062","title":"TinyEmo: Scaling down Emotional Reasoning via Metric Projection","created":"2024-10-09","cited_by_count":0,"area":"lr"},{"id":"2504.06578","title":"Attributes-aware Visual Emotion Representation Learning","created":"2025-04-09","cited_by_count":0,"area":null},{"id":"2505.11959","title":"EmoHopeSpeech: An Annotated Dataset of Emotions and Hope Speech in English and Arabic","created":"2025-05-17","cited_by_count":0,"area":null},{"id":"2511.03423","title":"Seeing What You Say: Expressive Image Generation from Speech","created":"2025-11-05","cited_by_count":0,"area":null},{"id":"2512.14665","title":"Enhancing Visual Sentiment Analysis via Semiotic Isotopy-Guided Dataset Construction","created":"2025-12-16","cited_by_count":0,"area":null},{"id":"2601.12079","title":"EmoLat: Text-driven Image Sentiment Transfer via Emotion Latent Space","created":"2026-01-17","cited_by_count":0,"area":null},{"id":"2602.00123","title":"Visual Affect Analysis: Predicting Emotions of Image Viewers with Vision-Language Models","created":"2026-01-27","cited_by_count":0,"area":"mllm"},{"id":"2602.18016","title":"Towards LLM-centric Affective Visual Customization via Efficient and Precise Emotion Manipulating","created":"2026-02-20","cited_by_count":0,"area":null},{"id":"2604.12568","title":"Evolution-Inspired Sample Competition for Deep Neural Network Optimization","created":"2026-04-14","cited_by_count":0,"area":null},{"id":"2604.15823","title":"Watching Movies Like a Human: Egocentric Emotion Understanding for Embodied Companions","created":"2026-04-17","cited_by_count":0,"area":null},{"id":"2605.03131","title":"EMOVIS: Emotion-Optimized Image Processing","created":"2026-05-04","cited_by_count":0,"area":null},{"id":"2605.05593","title":"Causal Probing for Internal Visual Representations in Multimodal Large Language Models","created":"2026-05-07","cited_by_count":0,"area":"mllm"},{"id":"2605.14635","title":"MultiEmo-Bench: Multi-label Visual Emotion Analysis for Multi-modal Large Language Models","created":"2026-05-14","cited_by_count":0,"area":"mllm"},{"id":"2605.15755","title":"Attribute-Grounded Selective Reasoning for Artwork Emotion Understanding with Multimodal Large Language Models","created":"2026-05-15","cited_by_count":0,"area":"lr"},{"id":"2605.26262","title":"Dimensional Distribution Emotion State: Leveraging Valence and Arousal as a Common Embedding Space for Visual Emotion Analysis","created":"2026-05-25","cited_by_count":0,"area":null},{"id":"2606.02171","title":"InsightVQA: High-Dimensional Emotion-Cognitive Visual Question Answering Benchmark","created":"2026-06-01","cited_by_count":0,"area":null},{"id":"2606.13081","title":"Emotional regulation improves deep learning-based image classification","created":"2026-06-11","cited_by_count":0,"area":null},{"id":"2607.08572","title":"Switch-Reasoner: Learn When to Think in Multitask Mixtures via Reinforcement Learning","created":"2026-07-09","cited_by_count":0,"area":"lr"},{"id":"2608.03358","title":"ArtECulture: Benchmarking Culture-Conditioned Visual Emotion Understanding in Multimodal Large Language Models","created":"2026-08-04","cited_by_count":0,"area":"mllm"},{"id":"2608.12724","title":"MAG: MAnifold Guided Semi-Supervised Multi-modal In-Context Learning","created":"2026-08-13","cited_by_count":0,"area":"mllm"},{"id":"2608.13974","title":"ProFocus: Interpreting Affective Experience in Artistic Images with Progressive Visual Focusing","created":"2026-08-14","cited_by_count":0,"area":null},{"id":"2608.18090","title":"Nine Emotion Centroids: A Label-Free Valence Axis That Transfers Across Four Modalities","created":"2026-06-05","cited_by_count":0,"area":null},{"id":"2608.22329","title":"ReART: Reference-Guided Retrieval and Refinement for Emotion-Aware Art Generation","created":"2026-08-23","cited_by_count":0,"area":null},{"id":"2609.13240","title":"ArtSociety: Multi-Agent Multimodal Collaboration for Art Emotion Understanding","created":"2026-09-03","cited_by_count":0,"area":"agents"},{"id":"2609.24215","title":"Beyond Emotion Prompts: Fine-Grained Text-to-Image Generation Driven by Valence-Arousal-Dominance","created":"2026-09-21","cited_by_count":0,"area":null},{"id":"2609.36775","title":"DSPO: Diversity-aware Subjective Policy Optimization for Robust Emotional Reasoning","created":"2026-09-29","cited_by_count":0,"area":"lr"},{"id":"2609.36782","title":"Decoding Affective Nuances: Enhancing MLLMs via Hierarchical Emotion Reasoning and Contrastive Discriminative Pruning","created":"2026-09-29","cited_by_count":0,"area":"lr"},{"id":"2610.16892","title":"Barycentric Guidance: Turning Foundation Image Editors into Continuous Affective Controllers","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}