{"list":"other","total":74,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"1807.03748","title":"Representation Learning with Contrastive Predictive Coding","created":"2018-07-10","cited_by_count":7777},{"id":"2310.03744","title":"Improved Baselines with Visual Instruction Tuning","created":"2023-10-05","cited_by_count":4418},{"id":"2205.01068","title":"OPT: Open Pre-trained Transformer Language Models","created":"2022-05-02","cited_by_count":3512},{"id":"2309.16609","title":"Qwen Technical Report","created":"2023-09-28","cited_by_count":3344},{"id":"2403.05530","title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","created":"2024-03-08","cited_by_count":3224},{"id":"2304.10592","title":"MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models","created":"2023-04-20","cited_by_count":2711},{"id":"2311.16502","title":"MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI","created":"2023-11-27","cited_by_count":2080},{"id":"1306.5151","title":"Fine-Grained Visual Classification of Aircraft","created":"2013-06-21","cited_by_count":1726},{"id":"2311.05232","title":"A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions","created":"2023-11-09","cited_by_count":1601},{"id":"2111.02114","title":"LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairs","created":"2021-11-03","cited_by_count":1555},{"id":"1504.00325","title":"Microsoft COCO Captions: Data Collection and Evaluation Server","created":"2015-04-01","cited_by_count":1462},{"id":"2311.10122","title":"Video-LLaVA: Learning United Visual Representation by Alignment Before Projection","created":"2023-11-16","cited_by_count":1402},{"id":"1908.03557","title":"VisualBERT: A Simple and Performant Baseline for Vision and Language","created":"2019-08-09","cited_by_count":1296},{"id":"2206.10789","title":"Scaling Autoregressive Models for Content-Rich Text-to-Image Generation","created":"2022-06-22","cited_by_count":1295},{"id":"2405.09818","title":"Chameleon: Mixed-Modal Early-Fusion Foundation Models","created":"2024-05-16","cited_by_count":927},{"id":"2402.09353","title":"DoRA: Weight-Decomposed Low-Rank Adaptation","created":"2024-02-14","cited_by_count":758},{"id":"2309.14525","title":"Aligning Large Multimodal Models with Factually Augmented RLHF","created":"2023-09-25","cited_by_count":712},{"id":"2310.09478","title":"MiniGPT-v2: large language model as a unified interface for vision-language multi-task learning","created":"2023-10-14","cited_by_count":625},{"id":"2304.15010","title":"LLaMA-Adapter V2: Parameter-Efficient Visual Instruction Model","created":"2023-04-28","cited_by_count":602},{"id":"2305.03726","title":"Otter: A Multi-Modal Model with In-Context Instruction Tuning","created":"2023-05-05","cited_by_count":550},{"id":"2010.14701","title":"Scaling Laws for Autoregressive Generative Modeling","created":"2020-10-28","cited_by_count":522},{"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":"2306.14565","title":"Mitigating Hallucination in Large Multi-Modal Models via Robust Instruction Tuning","created":"2023-06-26","cited_by_count":445},{"id":"2110.05208","title":"Supervision Exists Everywhere: A Data Efficient Contrastive Language-Image Pre-training Paradigm","created":"2021-10-11","cited_by_count":405},{"id":"2311.06607","title":"Monkey: Image Resolution and Text Label Are Important Things for Large Multi-modal Models","created":"2023-11-11","cited_by_count":357},{"id":"2305.16355","title":"PandaGPT: One Model To Instruction-Follow Them All","created":"2023-05-25","cited_by_count":334},{"id":"2306.03514","title":"Recognize Anything: A Strong Image Tagging Model","created":"2023-06-06","cited_by_count":309},{"id":"2401.05561","title":"TrustLLM: Trustworthiness in Large Language Models","created":"2024-01-10","cited_by_count":285},{"id":"2309.15807","title":"Emu: Enhancing Image Generation Models Using Photogenic Needles in a Haystack","created":"2023-09-27","cited_by_count":279},{"id":"2306.17107","title":"LLaVAR: Enhanced Visual Instruction Tuning for Text-Rich Image Understanding","created":"2023-06-29","cited_by_count":274},{"id":"2306.05425","title":"MIMIC-IT: Multi-Modal In-Context Instruction Tuning","created":"2023-06-08","cited_by_count":267},{"id":"2303.07909","title":"Text-to-image Diffusion Models in Generative AI: A Survey","created":"2023-03-14","cited_by_count":265},{"id":"1601.07140","title":"COCO-Text: Dataset and Benchmark for Text Detection and Recognition in Natural Images","created":"2016-01-26","cited_by_count":236},{"id":"2403.09611","title":"MM1: Methods, Analysis & Insights from Multimodal LLM Pre-training","created":"2024-03-14","cited_by_count":232},{"id":"2309.02591","title":"Scaling Autoregressive Multi-Modal Models: Pretraining and Instruction Tuning","created":"2023-09-05","cited_by_count":170},{"id":"2402.09739","title":"QuRating: Selecting High-Quality Data for Training Language Models","created":"2024-02-15","cited_by_count":157},{"id":"2211.09110","title":"Holistic Evaluation of Language Models","created":"2022-11-16","cited_by_count":131},{"id":"2108.02818","title":"Evaluating CLIP: Towards Characterization of Broader Capabilities and Downstream Implications","created":"2021-08-05","cited_by_count":128},{"id":"2404.03413","title":"MiniGPT4-Video: Advancing Multimodal LLMs for Video Understanding with Interleaved Visual-Textual Tokens","created":"2024-04-04","cited_by_count":118},{"id":"2312.08578","title":"A Picture is Worth More Than 77 Text Tokens: Evaluating CLIP-Style Models on Dense Captions","created":"2023-12-14","cited_by_count":108},{"id":"2402.13217","title":"VideoPrism: A Foundational Visual Encoder for Video Understanding","created":"2024-02-20","cited_by_count":105},{"id":"2402.09668","title":"How to Train Data-Efficient LLMs","created":"2024-02-15","cited_by_count":93},{"id":"2302.02503","title":"Leaving Reality to Imagination: Robust Classification via Generated Datasets","created":"2023-02-05","cited_by_count":91},{"id":"2311.08370","title":"SimpleSafetyTests: a Test Suite for Identifying Critical Safety Risks in Large Language Models","created":"2023-11-14","cited_by_count":76},{"id":"2404.04125","title":"No \"Zero-Shot\" Without Exponential Data: Pretraining Concept Frequency Determines Multimodal Model Performance","created":"2024-04-04","cited_by_count":75},{"id":"2312.17742","title":"Learning Vision from Models Rivals Learning Vision from Data","created":"2023-12-28","cited_by_count":71},{"id":"2401.12915","title":"Red Teaming Visual Language Models","created":"2024-01-23","cited_by_count":65},{"id":"2402.01832","title":"SynthCLIP: Are We Ready for a Fully Synthetic CLIP Training?","created":"2024-02-02","cited_by_count":64},{"id":"2002.08911","title":"Measuring Social Biases in Grounded Vision and Language Embeddings","created":"2020-02-20","cited_by_count":61},{"id":"2402.11337","title":"Learning by Reconstruction Produces Uninformative Features For Perception","created":"2024-02-17","cited_by_count":55},{"id":"2305.15328","title":"Visual Programming for Text-to-Image Generation and Evaluation","created":"2023-05-24","cited_by_count":54},{"id":"2104.08666","title":"Worst of Both Worlds: Biases Compound in Pre-trained Vision-and-Language Models","created":"2021-04-18","cited_by_count":52},{"id":"2303.14465","title":"Equivariant Similarity for Vision-Language Foundation Models","created":"2023-03-25","cited_by_count":52},{"id":"2309.00810","title":"RenAIssance: A Survey into AI Text-to-Image Generation in the Era of Large Model","created":"2023-09-02","cited_by_count":47},{"id":"2208.08831","title":"Discovering Bugs in Vision Models using Off-the-shelf Image Generation and Captioning","created":"2022-08-18","cited_by_count":45},{"id":"2307.03132","title":"T-MARS: Improving Visual Representations by Circumventing Text Feature Learning","created":"2023-07-06","cited_by_count":43},{"id":"2405.00740","title":"Modeling Caption Diversity in Contrastive Vision-Language Pretraining","created":"2024-04-30","cited_by_count":42},{"id":"2207.07635","title":"Is a Caption Worth a Thousand Images? A Controlled Study for Representation Learning","created":"2022-07-15","cited_by_count":39},{"id":"2310.00158","title":"Feedback-guided Data Synthesis for Imbalanced Classification","created":"2023-09-29","cited_by_count":33},{"id":"2310.01779","title":"HallE-Control: Controlling Object Hallucination in Large Multimodal Models","created":"2023-10-03","cited_by_count":32},{"id":"2303.18190","title":"Assessing Language Model Deployment with Risk Cards","created":"2023-03-31","cited_by_count":30},{"id":"2305.15407","title":"Balancing the Picture: Debiasing Vision-Language Datasets with Synthetic Contrast Sets","created":"2023-05-24","cited_by_count":27},{"id":"2311.16102","title":"Diffusion-TTA: Test-time Adaptation of Discriminative Models via Generative Feedback","created":"2023-11-27","cited_by_count":27},{"id":"2403.13499","title":"Improved Baselines for Data-efficient Perceptual Augmentation of LLMs","created":"2024-03-20","cited_by_count":18},{"id":"2311.08172","title":"Vision-Language Instruction Tuning: A Review and Analysis","created":"2023-11-14","cited_by_count":17},{"id":"2310.02239","title":"MiniGPT-5: Interleaved Vision-and-Language Generation via Generative Vokens","created":"2023-10-03","cited_by_count":15},{"id":"2310.09929","title":"Prompting Scientific Names for Zero-Shot Species Recognition","created":"2023-10-15","cited_by_count":14},{"id":"2405.01582","title":"Text Quality-Based Pruning for Efficient Training of Language Models","created":"2024-04-26","cited_by_count":9},{"id":"2402.08017","title":"Lumos : Empowering Multimodal LLMs with Scene Text Recognition","created":"2024-02-12","cited_by_count":8},{"id":"2402.07329","title":"The Bias of Harmful Label Associations in Vision-Language Models","created":"2024-02-11","cited_by_count":5},{"id":"2305.03204","title":"VideoOFA: Two-Stage Pre-Training for Video-to-Text Generation","created":"2023-05-04","cited_by_count":3}],"next_cursor":null}