{"list":"other","total":54,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2402.03300","title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","created":"2024-02-05","cited_by_count":9379},{"id":"2505.09388","title":"Qwen3 Technical Report","created":"2025-05-14","cited_by_count":8820},{"id":"2306.05685","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","created":"2023-06-09","cited_by_count":8626},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2301.12597","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","created":"2023-01-30","cited_by_count":6137},{"id":"2502.13923","title":"Qwen2.5-VL Technical Report","created":"2025-02-19","cited_by_count":5587},{"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":"2507.06261","title":"Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities","created":"2025-07-07","cited_by_count":3796},{"id":"2305.06500","title":"InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning","created":"2023-05-11","cited_by_count":2876},{"id":"2408.03326","title":"LLaVA-OneVision: Easy Visual Task Transfer","created":"2024-08-06","cited_by_count":2719},{"id":"2303.16634","title":"G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment","created":"2023-03-29","cited_by_count":2276},{"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":"2307.06281","title":"MMBench: Is Your Multi-modal Model an All-around Player?","created":"2023-07-12","cited_by_count":2141},{"id":"2508.18265","title":"InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency","created":"2025-08-25","cited_by_count":1510},{"id":"2506.05176","title":"Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models","created":"2025-06-05","cited_by_count":1261},{"id":"1608.05442","title":"Semantic Understanding of Scenes through the ADE20K Dataset","created":"2016-08-18","cited_by_count":1069},{"id":"2601.03267","title":"OpenAI GPT-5 System Card","created":"2025-12-19","cited_by_count":989},{"id":"2501.17811","title":"Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scaling","created":"2025-01-29","cited_by_count":812},{"id":"2202.10054","title":"Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution","created":"2022-02-21","cited_by_count":739},{"id":"2403.05525","title":"DeepSeek-VL: Towards Real-World Vision-Language Understanding","created":"2024-03-08","cited_by_count":733},{"id":"2407.07895","title":"LLaVA-NeXT-Interleave: Tackling Multi-image, Video, and 3D in Large Multimodal Models","created":"2024-07-10","cited_by_count":584},{"id":"1708.03985","title":"AffectNet: A Database for Facial Expression, Valence, and Arousal Computing in the Wild","created":"2017-08-14","cited_by_count":492},{"id":"2106.01144","title":"Towards Emotional Support Dialog Systems","created":"2021-06-02","cited_by_count":299},{"id":"2408.04840","title":"mPLUG-Owl3: Towards Long Image-Sequence Understanding in Multi-Modal Large Language Models","created":"2024-08-09","cited_by_count":291},{"id":"2309.14181","title":"Q-Bench: A Benchmark for General-Purpose Foundation Models on Low-level Vision","created":"2023-09-25","cited_by_count":249},{"id":"2509.23661","title":"LLaVA-OneVision-1.5: Fully Open Framework for Democratized Multimodal Training","created":"2025-09-28","cited_by_count":244},{"id":"2102.09554","title":"Delving into Deep Imbalanced Regression","created":"2021-02-18","cited_by_count":158},{"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":"2101.07396","title":"ArtEmis: Affective Language for Visual Art","created":"2021-01-19","cited_by_count":104},{"id":"2503.05379","title":"R1-Omni: Explainable Omni-Multimodal Emotion Recognition with Reinforcement Learning","created":"2025-03-07","cited_by_count":100},{"id":"2503.22679","title":"Q-Insight: Understanding Image Quality via Visual Reinforcement Learning","created":"2025-03-28","cited_by_count":98},{"id":"2505.03318","title":"Unified Multimodal Chain-of-Thought Reward Model through Reinforcement Fine-Tuning","created":"2025-05-06","cited_by_count":90},{"id":"2307.07961","title":"EmoSet: A Large-scale Visual Emotion Dataset with Rich Attributes","created":"2023-07-16","cited_by_count":82},{"id":"1605.02677","title":"Building a Large Scale Dataset for Image Emotion Recognition: The Fine Print and The Benchmark","created":"2016-05-09","cited_by_count":71},{"id":"2401.08276","title":"AesBench: An Expert Benchmark for Multimodal Large Language Models on Image Aesthetics Perception","created":"2024-01-16","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":"2501.16566","title":"AffectGPT: A New Dataset, Model, and Benchmark for Emotion Understanding with Multimodal Large Language Models","created":"2025-01-27","cited_by_count":44},{"id":"2404.16670","title":"EmoVIT: Revolutionizing Emotion Insights with Visual Instruction Tuning","created":"2024-04-25","cited_by_count":43},{"id":"2404.09619","title":"UNIAA: A Unified Multi-modal Image Aesthetic Assessment Baseline and Benchmark","created":"2024-04-15","cited_by_count":42},{"id":"2402.06599","title":"On the Out-Of-Distribution Generalization of Multimodal Large Language Models","created":"2024-02-09","cited_by_count":30},{"id":"2506.18564","title":"VQ-Insight: Teaching VLMs for AI-Generated Video Quality Understanding via Progressive Visual Reinforcement Learning","created":"2025-06-23","cited_by_count":26},{"id":"2402.01355","title":"FindingEmo: An Image Dataset for Emotion Recognition in the Wild","created":"2024-02-02","cited_by_count":22},{"id":"2210.01946","title":"Affection: Learning Affective Explanations for Real-World Visual Data","created":"2022-10-04","cited_by_count":19},{"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},{"id":"2508.01318","title":"AffectGPT-R1: Leveraging Reinforcement Learning for Open-Vocabulary Multimodal Emotion Recognition","created":"2025-08-02","cited_by_count":15},{"id":"2507.20025","title":"Region-based Cluster Discrimination for Visual Representation Learning","created":"2025-07-26","cited_by_count":13},{"id":"2505.06685","title":"Emotion-Qwen: A Unified Framework for Emotion and Vision Understanding","created":"2025-05-10","cited_by_count":11},{"id":"2508.06051","title":"VQAThinker: Exploring Generalizable and Explainable Video Quality Assessment via Reinforcement Learning","created":"2025-08-08","cited_by_count":10}],"next_cursor":null}