{"list":"other","total":60,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2307.01952","title":"SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis","created":"2023-07-04","cited_by_count":4356},{"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":"2305.06500","title":"InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning","created":"2023-05-11","cited_by_count":2876},{"id":"2212.10560","title":"Self-Instruct: Aligning Language Models with Self-Generated Instructions","created":"2022-12-20","cited_by_count":2724},{"id":"2304.10592","title":"MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models","created":"2023-04-20","cited_by_count":2711},{"id":"2312.14238","title":"InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks","created":"2023-12-21","cited_by_count":2565},{"id":"2208.01626","title":"Prompt-to-Prompt Image Editing with Cross Attention Control","created":"2022-08-02","cited_by_count":2431},{"id":"2504.10479","title":"InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models","created":"2025-04-14","cited_by_count":1834},{"id":"1905.00414","title":"Similarity of Neural Network Representations Revisited","created":"2019-05-01","cited_by_count":1755},{"id":"1904.08920","title":"Towards VQA Models That Can Read","created":"2019-04-18","cited_by_count":1718},{"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":"2203.10244","title":"ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoning","created":"2022-03-19","cited_by_count":1479},{"id":"2007.00398","title":"DocVQA: A Dataset for VQA on Document Images","created":"2020-07-01","cited_by_count":1317},{"id":"2306.00890","title":"LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day","created":"2023-06-01","cited_by_count":1305},{"id":"1906.00067","title":"OK-VQA: A Visual Question Answering Benchmark Requiring External Knowledge","created":"2019-05-31","cited_by_count":1121},{"id":"1802.08218","title":"VizWiz Grand Challenge: Answering Visual Questions from Blind People","created":"2018-02-22","cited_by_count":858},{"id":"2406.16860","title":"Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs","created":"2024-06-24","cited_by_count":838},{"id":"1901.11196","title":"EDA: Easy Data Augmentation Techniques for Boosting Performance on Text Classification Tasks","created":"2019-01-31","cited_by_count":807},{"id":"2312.07533","title":"VILA: On Pre-training for Visual Language Models","created":"2023-12-12","cited_by_count":692},{"id":"2203.02053","title":"Mind the Gap: Understanding the Modality Gap in Multi-modal Contrastive Representation Learning","created":"2022-03-03","cited_by_count":561},{"id":"2312.14150","title":"DriveLM: Driving with Graph Visual Question Answering","created":"2023-12-21","cited_by_count":536},{"id":"2305.07895","title":"OCRBench: On the Hidden Mystery of OCR in Large Multimodal Models","created":"2023-05-13","cited_by_count":476},{"id":"2404.01291","title":"Evaluating Text-to-Visual Generation with Image-to-Text Generation","created":"2024-04-01","cited_by_count":474},{"id":"2104.12756","title":"InfographicVQA","created":"2021-04-26","cited_by_count":437},{"id":"2303.11897","title":"TIFA: Accurate and Interpretable Text-to-Image Faithfulness Evaluation with Question Answering","created":"2023-03-21","cited_by_count":428},{"id":"2407.12772","title":"LMMs-Eval: Reality Check on the Evaluation of Large Multimodal Models","created":"2024-07-17","cited_by_count":353},{"id":"2302.07944","title":"Effective Data Augmentation With Diffusion Models","created":"2023-02-07","cited_by_count":283},{"id":"2306.17107","title":"LLaVAR: Enhanced Visual Instruction Tuning for Text-Rich Image Understanding","created":"2023-06-29","cited_by_count":274},{"id":"2211.13977","title":"CLIP-ReID: Exploiting Vision-Language Model for Image Re-Identification without Concrete Text Labels","created":"2022-11-25","cited_by_count":181},{"id":"2504.02160","title":"Less-to-More Generalization: Unlocking More Controllability by In-Context Generation","created":"2025-04-02","cited_by_count":154},{"id":"2403.02469","title":"Vision-Language Models for Medical Report Generation and Visual Question Answering: A Review","created":"2024-03-04","cited_by_count":125},{"id":"2212.10773","title":"MultiInstruct: Improving Multi-Modal Zero-Shot Learning via Instruction Tuning","created":"2022-12-21","cited_by_count":109},{"id":"2206.02574","title":"On the duality between contrastive and non-contrastive self-supervised learning","created":"2022-06-03","cited_by_count":108},{"id":"2312.04567","title":"Scaling Laws of Synthetic Images for Model Training ... for Now","created":"2023-12-07","cited_by_count":108},{"id":"2211.00575","title":"Text-Only Training for Image Captioning using Noise-Injected CLIP","created":"2022-11-01","cited_by_count":91},{"id":"2303.03032","title":"DeCap: Decoding CLIP Latents for Zero-Shot Captioning via Text-Only Training","created":"2023-03-06","cited_by_count":84},{"id":"2308.12714","title":"VIGC: Visual Instruction Generation and Correction","created":"2023-08-24","cited_by_count":80},{"id":"2402.11690","title":"Vision-Flan: Scaling Human-Labeled Tasks in Visual Instruction Tuning","created":"2024-02-18","cited_by_count":73},{"id":"2501.01904","title":"Virgo: A Preliminary Exploration on Reproducing o1-like MLLM","created":"2025-01-03","cited_by_count":68},{"id":"2402.01832","title":"SynthCLIP: Are We Ready for a Fully Synthetic CLIP Training?","created":"2024-02-02","cited_by_count":64},{"id":"2302.04269","title":"Diagnosing and Rectifying Vision Models using Language","created":"2023-02-08","cited_by_count":58},{"id":"2211.15388","title":"Shifted Diffusion for Text-to-image Generation","created":"2022-11-24","cited_by_count":37},{"id":"2501.11347","title":"EndoChat: Grounded Multimodal Large Language Model for Endoscopic Surgery","created":"2025-01-20","cited_by_count":37},{"id":"2402.14162","title":"On Large Visual Language Models for Medical Imaging Analysis: An Empirical Study","created":"2024-02-21","cited_by_count":28},{"id":"2502.18411","title":"OmniAlign-V: Towards Enhanced Alignment of MLLMs with Human Preference","created":"2025-02-25","cited_by_count":28},{"id":"2401.08567","title":"Connect, Collapse, Corrupt: Learning Cross-Modal Tasks with Uni-Modal Data","created":"2024-01-16","cited_by_count":27},{"id":"2107.08685","title":"Constructing Multi-Modal Dialogue Dataset by Replacing Text with Semantically Relevant Images","created":"2021-07-19","cited_by_count":26},{"id":"2412.07909","title":"Explaining and Mitigating the Modality Gap in Contrastive Multimodal Learning","created":"2024-12-10","cited_by_count":26},{"id":"2312.03631","title":"Mitigating Open-Vocabulary Caption Hallucinations","created":"2023-12-06","cited_by_count":19},{"id":"2212.04119","title":"DialogCC: An Automated Pipeline for Creating High-Quality Multi-Modal Dialogue Dataset","created":"2022-12-08","cited_by_count":17},{"id":"2311.08172","title":"Vision-Language Instruction Tuning: A Review and Analysis","created":"2023-11-14","cited_by_count":17},{"id":"2210.14124","title":"Lafite2: Few-shot Text-to-Image Generation","created":"2022-10-25","cited_by_count":13},{"id":"2312.06731","title":"Genixer: Empowering Multimodal Large Language Models as a Powerful Data Generator","created":"2023-12-11","cited_by_count":11},{"id":"2503.06260","title":"From Captions to Rewards (CAREVL): Leveraging Large Language Model Experts for Enhanced Reward Modeling in Large Vision-Language Models","created":"2025-03-08","cited_by_count":11},{"id":"2403.03194","title":"MAGID: An Automated Pipeline for Generating Synthetic Multi-modal Datasets","created":"2024-03-05","cited_by_count":10},{"id":"2504.19276","title":"Anyprefer: An Agentic Framework for Preference Data Synthesis","created":"2025-04-27","cited_by_count":10},{"id":"2403.19880","title":"Vision-Language Synthetic Data Enhances Echocardiography Downstream Tasks","created":"2024-03-28","cited_by_count":6}],"next_cursor":null}