{"list":"other","total":62,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2102.05918","title":"Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision","created":"2021-02-11","cited_by_count":3864},{"id":"2309.16609","title":"Qwen Technical Report","created":"2023-09-28","cited_by_count":3344},{"id":"2310.06825","title":"Mistral 7B","created":"2023-10-10","cited_by_count":3164},{"id":"2303.15343","title":"Sigmoid Loss for Language Image Pre-Training","created":"2023-03-27","cited_by_count":3109},{"id":"2404.14219","title":"Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone","created":"2024-04-22","cited_by_count":1917},{"id":"2205.01917","title":"CoCa: Contrastive Captioners are Image-Text Foundation Models","created":"2022-05-04","cited_by_count":1274},{"id":"2112.03857","title":"Grounded Language-Image Pre-training","created":"2021-12-07","cited_by_count":1156},{"id":"2311.12793","title":"ShareGPT4V: Improving Large Multi-Modal Models with Better Captions","created":"2023-11-21","cited_by_count":1005},{"id":"2303.15389","title":"EVA-CLIP: Improved Training Techniques for CLIP at Scale","created":"2023-03-27","cited_by_count":798},{"id":"2209.06794","title":"PaLI: A Jointly-Scaled Multilingual Language-Image Model","created":"2022-09-14","cited_by_count":766},{"id":"2106.13884","title":"Multimodal Few-Shot Learning with Frozen Language Models","created":"2021-06-25","cited_by_count":661},{"id":"2111.07783","title":"FILIP: Fine-grained Interactive Language-Image Pre-Training","created":"2021-11-09","cited_by_count":627},{"id":"2111.07991","title":"LiT: Zero-Shot Transfer with Locked-image text Tuning","created":"2021-11-15","cited_by_count":577},{"id":"2202.11094","title":"GroupViT: Semantic Segmentation Emerges from Text Supervision","created":"2022-02-22","cited_by_count":531},{"id":"2204.03162","title":"Winoground: Probing Vision and Language Models for Visio-Linguistic Compositionality","created":"2022-04-07","cited_by_count":529},{"id":"2112.12750","title":"SLIP: Self-supervision meets Language-Image Pre-training","created":"2021-12-23","cited_by_count":436},{"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":"2404.05961","title":"LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders","created":"2024-04-09","cited_by_count":404},{"id":"2212.00794","title":"Scaling Language-Image Pre-training via Masking","created":"2022-12-01","cited_by_count":317},{"id":"2401.00368","title":"Improving Text Embeddings with Large Language Models","created":"2023-12-31","cited_by_count":303},{"id":"2403.15378","title":"Long-CLIP: Unlocking the Long-Text Capability of CLIP","created":"2024-03-22","cited_by_count":300},{"id":"2306.14610","title":"SugarCrepe: Fixing Hackable Benchmarks for Vision-Language Compositionality","created":"2023-06-26","cited_by_count":243},{"id":"2402.09906","title":"Generative Representational Instruction Tuning","created":"2024-02-15","cited_by_count":233},{"id":"2305.20088","title":"Improving CLIP Training with Language Rewrites","created":"2023-05-31","cited_by_count":217},{"id":"2208.12262","title":"MaskCLIP: Masked Self-Distillation Advances Contrastive Language-Image Pretraining","created":"2022-08-25","cited_by_count":187},{"id":"2306.00984","title":"StableRep: Synthetic Images from Text-to-Image Models Make Strong Visual Representation Learners","created":"2023-06-01","cited_by_count":177},{"id":"1707.09700","title":"Scene Graph Generation from Objects, Phrases and Region Captions","created":"2017-07-31","cited_by_count":154},{"id":"2404.19753","title":"DOCCI: Descriptions of Connected and Contrasting Images","created":"2024-04-30","cited_by_count":132},{"id":"2211.01335","title":"Chinese CLIP: Contrastive Vision-Language Pretraining in Chinese","created":"2022-11-02","cited_by_count":109},{"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":"2204.14095","title":"PyramidCLIP: Hierarchical Feature Alignment for Vision-language Model Pretraining","created":"2022-04-29","cited_by_count":104},{"id":"2205.12522","title":"Crossmodal-3600: A Massively Multilingual Multimodal Evaluation Dataset","created":"2022-05-25","cited_by_count":100},{"id":"2211.06679","title":"AltCLIP: Altering the Language Encoder in CLIP for Extended Language Capabilities","created":"2022-11-12","cited_by_count":85},{"id":"2307.16645","title":"Scaling Sentence Embeddings with Large Language Models","created":"2023-07-31","cited_by_count":85},{"id":"2403.20327","title":"Gecko: Versatile Text Embeddings Distilled from Large Language Models","created":"2024-03-29","cited_by_count":83},{"id":"2305.07017","title":"An Inverse Scaling Law for CLIP Training","created":"2023-05-11","cited_by_count":77},{"id":"2201.00443","title":"Scene Graph Generation: A Comprehensive Survey","created":"2022-01-03","cited_by_count":73},{"id":"2402.15449","title":"Repetition Improves Language Model Embeddings","created":"2024-02-23","cited_by_count":72},{"id":"2403.17007","title":"DreamLIP: Language-Image Pre-training with Long Captions","created":"2024-03-25","cited_by_count":72},{"id":"2308.08428","title":"ALIP: Adaptive Language-Image Pre-training with Synthetic Caption","created":"2023-08-16","cited_by_count":70},{"id":"2310.07699","title":"VeCLIP: Improving CLIP Training via Visual-enriched Captions","created":"2023-10-11","cited_by_count":70},{"id":"2312.17133","title":"ARTrackV2: Prompting Autoregressive Tracker Where to Look and How to Describe","created":"2023-12-28","cited_by_count":59},{"id":"2303.17561","title":"SoftCLIP: Softer Cross-modal Alignment Makes CLIP Stronger","created":"2023-03-30","cited_by_count":56},{"id":"2306.17842","title":"SPAE: Semantic Pyramid AutoEncoder for Multimodal Generation with Frozen LLMs","created":"2023-06-30","cited_by_count":55},{"id":"2209.13430","title":"UniCLIP: Unified Framework for Contrastive Language-Image Pre-training","created":"2022-09-27","cited_by_count":54},{"id":"2405.20204","title":"Jina CLIP: Your CLIP Model Is Also Your Text Retriever","created":"2024-05-30","cited_by_count":46},{"id":"2303.02995","title":"HiCLIP: Contrastive Language-Image Pretraining with Hierarchy-aware Attention","created":"2023-03-06","cited_by_count":44},{"id":"2404.18424","title":"PromptReps: Prompting Large Language Models to Generate Dense and Sparse Representations for Zero-Shot Document Retrieval","created":"2024-04-29","cited_by_count":30},{"id":"2302.00902","title":"Language Quantized AutoEncoders: Towards Unsupervised Text-Image Alignment","created":"2023-02-02","cited_by_count":29},{"id":"2404.03921","title":"Simple Techniques for Enhancing Sentence Embeddings in Generative Language Models","created":"2024-04-05","cited_by_count":26},{"id":"2309.01859","title":"NLLB-CLIP -- train performant multilingual image retrieval model on a budget","created":"2023-09-04","cited_by_count":24},{"id":"2403.07874","title":"Beyond Text: Frozen Large Language Models in Visual Signal Comprehension","created":"2024-03-12","cited_by_count":23},{"id":"2311.18765","title":"MLLMs-Augmented Visual-Language Representation Learning","created":"2023-11-30","cited_by_count":21},{"id":"2405.18361","title":"Is a 3D-Tokenized LLM the Key to Reliable Autonomous Driving?","created":"2024-05-28","cited_by_count":20},{"id":"2402.18458","title":"Meta-Task Prompting Elicits Embeddings from Large Language Models","created":"2024-02-28","cited_by_count":16},{"id":"2312.12661","title":"Misalign, Contrast then Distill: Rethinking Misalignments in Language-Image Pretraining","created":"2023-12-19","cited_by_count":10}],"next_cursor":null}