{"list":"other","total":51,"rows":[{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"2309.06180","title":"Efficient Memory Management for Large Language Model Serving with PagedAttention","created":"2023-09-12","cited_by_count":5944},{"id":"2502.13923","title":"Qwen2.5-VL Technical Report","created":"2025-02-19","cited_by_count":5587},{"id":"2103.03874","title":"Measuring Mathematical Problem Solving With the MATH Dataset","created":"2021-03-05","cited_by_count":5371},{"id":"2310.03744","title":"Improved Baselines with Visual Instruction Tuning","created":"2023-10-05","cited_by_count":4418},{"id":"2409.12191","title":"Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution","created":"2024-09-18","cited_by_count":4234},{"id":"2308.12966","title":"Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond","created":"2023-08-24","cited_by_count":2224},{"id":"2306.13394","title":"MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models","created":"2023-06-23","cited_by_count":1652},{"id":"2306.02858","title":"Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding","created":"2023-06-05","cited_by_count":1471},{"id":"2405.21075","title":"Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis","created":"2024-05-31","cited_by_count":1413},{"id":"2311.10122","title":"Video-LLaVA: Learning United Visual Representation by Alignment Before Projection","created":"2023-11-16","cited_by_count":1402},{"id":"2406.07476","title":"VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs","created":"2024-06-11","cited_by_count":771},{"id":"2503.20215","title":"Qwen2.5-Omni Technical Report","created":"2025-03-26","cited_by_count":736},{"id":"1810.02508","title":"MELD: A Multimodal Multi-Party Dataset for Emotion Recognition in Conversations","created":"2018-10-05","cited_by_count":643},{"id":"2308.10792","title":"Instruction Tuning for Large Language Models: A Survey","created":"2023-08-21","cited_by_count":623},{"id":"2407.10759","title":"Qwen2-Audio Technical Report","created":"2024-07-15","cited_by_count":560},{"id":"2503.01785","title":"Visual-RFT: Visual Reinforcement Fine-Tuning","created":"2025-03-03","cited_by_count":513},{"id":"2408.13257","title":"MME-RealWorld: Could Your Multimodal LLM Challenge High-Resolution Real-World Scenarios that are Difficult for Humans?","created":"2024-08-23","cited_by_count":292},{"id":"2401.13601","title":"MM-LLMs: Recent Advances in MultiModal Large Language Models","created":"2024-01-24","cited_by_count":278},{"id":"1804.08348","title":"Deep Facial Expression Recognition: A Survey","created":"2018-04-23","cited_by_count":270},{"id":"2503.21460","title":"Large Language Model Agent: A Survey on Methodology, Applications and Challenges","created":"2025-03-27","cited_by_count":205},{"id":"2402.17193","title":"When Scaling Meets LLM Finetuning: The Effect of Data, Model and Finetuning Method","created":"2024-02-27","cited_by_count":204},{"id":"2311.13165","title":"Multimodal Large Language Models: A Survey","created":"2023-11-22","cited_by_count":195},{"id":"1606.06259","title":"MOSI: Multimodal Corpus of Sentiment Intensity and Subjectivity Analysis in Online Opinion Videos","created":"2016-06-20","cited_by_count":194},{"id":"2008.05924","title":"DFEW: A Large-Scale Database for Recognizing Dynamic Facial Expressions in the Wild","created":"2020-08-13","cited_by_count":128},{"id":"2502.09621","title":"MME-CoT: Benchmarking Chain-of-Thought in Large Multimodal Models for Reasoning Quality, Robustness, and Efficiency","created":"2025-02-13","cited_by_count":125},{"id":"2406.11161","title":"Emotion-LLaMA: Multimodal Emotion Recognition and Reasoning with Instruction Tuning","created":"2024-06-17","cited_by_count":121},{"id":"2504.15585","title":"A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment","created":"2025-04-22","cited_by_count":116},{"id":"1908.05913","title":"Context-Aware Emotion Recognition Networks","created":"2019-08-16","cited_by_count":99},{"id":"2503.02318","title":"Audio-Reasoner: Improving Reasoning Capability in Large Audio Language Models","created":"2025-03-04","cited_by_count":95},{"id":"2411.15296","title":"MME-Survey: A Comprehensive Survey on Evaluation of Multimodal LLMs","created":"2024-11-22","cited_by_count":72},{"id":"1704.08619","title":"End-to-End Multimodal Emotion Recognition using Deep Neural Networks","created":"2017-04-27","cited_by_count":70},{"id":"2208.00847","title":"MAFW: A Large-scale, Multi-modal, Compound Affective Database for Dynamic Facial Expression Recognition in the Wild","created":"2022-08-01","cited_by_count":65},{"id":"2501.15111","title":"HumanOmni: A Large Vision-Speech Language Model for Human-Centric Video Understanding","created":"2025-01-25","cited_by_count":60},{"id":"2308.03656","title":"Emotionally Numb or Empathetic? Evaluating How LLMs Feel Using EmotionBench","created":"2023-08-07","cited_by_count":54},{"id":"2402.12071","title":"EmoBench: Evaluating the Emotional Intelligence of Large Language Models","created":"2024-02-19","cited_by_count":53},{"id":"2209.02604","title":"Make Acoustic and Visual Cues Matter: CH-SIMS v2.0 Dataset and AV-Mixup Consistent Module","created":"2022-08-22","cited_by_count":44},{"id":"1808.09568","title":"ARBEE: Towards Automated Recognition of Bodily Expression of Emotion In the Wild","created":"2018-08-28","cited_by_count":34},{"id":"2505.24714","title":"FinMME: Benchmark Dataset for Financial Multi-Modal Reasoning Evaluation","created":"2025-05-30","cited_by_count":30},{"id":"2404.17113","title":"MER 2024: Semi-Supervised Learning, Noise Robustness, and Open-Vocabulary Multimodal Emotion Recognition","created":"2024-04-26","cited_by_count":23},{"id":"2407.02751","title":"Emotion and Intent Joint Understanding in Multimodal Conversation: A Benchmarking Dataset","created":"2024-07-03","cited_by_count":15},{"id":"2508.01318","title":"AffectGPT-R1: Leveraging Reinforcement Learning for Open-Vocabulary Multimodal Emotion Recognition","created":"2025-08-02","cited_by_count":15},{"id":"2405.07229","title":"MM-InstructEval: Zero-Shot Evaluation of (Multimodal) Large Language Models on Multimodal Reasoning Tasks","created":"2024-05-12","cited_by_count":11},{"id":"2407.07653","title":"AffectGPT: Dataset and Framework for Explainable Multimodal Emotion Recognition","created":"2024-07-10","cited_by_count":11},{"id":"2402.13589","title":"Affective Computing for Healthcare: Recent Trends, Applications, Challenges, and Beyond","created":"2024-02-21","cited_by_count":10},{"id":"2412.00060","title":"MOSABench: Multi-Object Sentiment Analysis Benchmark for Evaluating Multimodal Large Language Models Understanding of Complex Image","created":"2024-11-25","cited_by_count":9},{"id":"2507.04278","title":"EmoPrefer: Can Large Language Models Understand Human Emotion Preferences?","created":"2025-07-06","cited_by_count":6},{"id":"2505.07865","title":"CellVerse: Do Large Language Models Really Understand Cell Biology?","created":"2025-05-09","cited_by_count":5},{"id":"2404.15041","title":"LEAF: Unveiling Two Sides of the Same Coin in Semi-supervised Facial Expression Recognition","created":"2024-04-23","cited_by_count":2}],"next_cursor":null}