{"list":"other","total":64,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"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":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"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":"1711.00937","title":"Neural Discrete Representation Learning","created":"2017-11-02","cited_by_count":4712},{"id":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"id":"1907.05600","title":"Generative Modeling by Estimating Gradients of the Data Distribution","created":"2019-07-12","cited_by_count":4101},{"id":"2201.03545","title":"A ConvNet for the 2020s","created":"2022-01-10","cited_by_count":3579},{"id":"2012.09841","title":"Taming Transformers for High-Resolution Image Synthesis","created":"2020-12-17","cited_by_count":3253},{"id":"2303.15343","title":"Sigmoid Loss for Language Image Pre-Training","created":"2023-03-27","cited_by_count":3109},{"id":"2206.00364","title":"Elucidating the Design Space of Diffusion-Based Generative Models","created":"2022-06-01","cited_by_count":3045},{"id":"1602.07332","title":"Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations","created":"2016-02-23","cited_by_count":2656},{"id":"1612.00837","title":"Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering","created":"2016-12-02","cited_by_count":2516},{"id":"2407.10671","title":"Qwen2 Technical Report","created":"2024-07-15","cited_by_count":2120},{"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":"2305.10355","title":"Evaluating Object Hallucination in Large Vision-Language Models","created":"2023-05-17","cited_by_count":1729},{"id":"1904.08920","title":"Towards VQA Models That Can Read","created":"2019-04-18","cited_by_count":1718},{"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":"1906.00067","title":"OK-VQA: A Visual Question Answering Benchmark Requiring External Knowledge","created":"2019-05-31","cited_by_count":1121},{"id":"2310.00426","title":"PixArt-$\\alpha$: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis","created":"2023-09-30","cited_by_count":864},{"id":"1603.07396","title":"A Diagram Is Worth A Dozen Images","created":"2016-03-24","cited_by_count":804},{"id":"2406.06525","title":"Autoregressive Model Beats Diffusion: Llama for Scalable Image Generation","created":"2024-06-10","cited_by_count":777},{"id":"2403.05525","title":"DeepSeek-VL: Towards Real-World Vision-Language Understanding","created":"2024-03-08","cited_by_count":733},{"id":"2206.01718","title":"A-OKVQA: A Benchmark for Visual Question Answering using World Knowledge","created":"2022-06-03","cited_by_count":710},{"id":"2302.12288","title":"ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depth","created":"2023-02-23","cited_by_count":657},{"id":"2406.11838","title":"Autoregressive Image Generation without Vector Quantization","created":"2024-06-17","cited_by_count":651},{"id":"2310.14566","title":"HallusionBench: An Advanced Diagnostic Suite for Entangled Language Hallucination and Visual Illusion in Large Vision-Language Models","created":"2023-10-23","cited_by_count":583},{"id":"2402.14804","title":"Measuring Multimodal Mathematical Reasoning with MATH-Vision Dataset","created":"2024-02-22","cited_by_count":526},{"id":"2407.11691","title":"VLMEvalKit: An Open-Source Toolkit for Evaluating Large Multi-Modality Models","created":"2024-07-16","cited_by_count":455},{"id":"2204.07118","title":"DeiT III: Revenge of the ViT","created":"2022-04-14","cited_by_count":419},{"id":"2105.04165","title":"Inter-GPS: Interpretable Geometry Problem Solving with Formal Language and Symbolic Reasoning","created":"2021-05-10","cited_by_count":383},{"id":"2303.11331","title":"EVA-02: A Visual Representation for Neon Genesis","created":"2023-03-20","cited_by_count":381},{"id":"2403.18814","title":"Mini-Gemini: Mining the Potential of Multi-modality Vision Language Models","created":"2024-03-27","cited_by_count":365},{"id":"2209.14610","title":"Dynamic Prompt Learning via Policy Gradient for Semi-structured Mathematical Reasoning","created":"2022-09-29","cited_by_count":350},{"id":"1801.08163","title":"DVQA: Understanding Data Visualizations via Question Answering","created":"2018-01-24","cited_by_count":340},{"id":"2404.14396","title":"SEED-X: Multimodal Models with Unified Multi-granularity Comprehension and Generation","created":"2024-04-22","cited_by_count":331},{"id":"2105.14517","title":"GeoQA: A Geometric Question Answering Benchmark Towards Multimodal Numerical Reasoning","created":"2021-05-30","cited_by_count":228},{"id":"2402.11684","title":"ALLaVA: Harnessing GPT4V-Synthesized Data for Lite Vision-Language Models","created":"2024-02-18","cited_by_count":205},{"id":"2310.01218","title":"Making LLaMA SEE and Draw with SEED Tokenizer","created":"2023-10-02","cited_by_count":185},{"id":"2302.07194","title":"Score Approximation, Estimation and Distribution Recovery of Diffusion Models on Low-Dimensional Data","created":"2023-02-14","cited_by_count":174},{"id":"2307.14460","title":"MiDaS v3.1 -- A Model Zoo for Robust Monocular Relative Depth Estimation","created":"2023-07-26","cited_by_count":174},{"id":"2307.05222","title":"Emu: Generative Pretraining in Multimodality","created":"2023-07-11","cited_by_count":157},{"id":"2406.13642","title":"SpatialBot: Precise Spatial Understanding with Vision Language Models","created":"2024-06-19","cited_by_count":152},{"id":"2403.00231","title":"Multimodal ArXiv: A Dataset for Improving Scientific Comprehension of Large Vision-Language Models","created":"2024-03-01","cited_by_count":139},{"id":"2406.08487","title":"Beyond LLaVA-HD: Diving into High-Resolution Large Multimodal Models","created":"2024-06-12","cited_by_count":76},{"id":"2112.12494","title":"LaTr: Layout-Aware Transformer for Scene-Text VQA","created":"2021-12-23","cited_by_count":72},{"id":"1912.03879","title":"AI2D-RST: A multimodal corpus of 1000 primary school science diagrams","created":"2019-12-09","cited_by_count":60},{"id":"2304.05919","title":"Hard Patches Mining for Masked Image Modeling","created":"2023-04-12","cited_by_count":57},{"id":"2309.03576","title":"DropPos: Pre-Training Vision Transformers by Reconstructing Dropped Positions","created":"2023-09-07","cited_by_count":19},{"id":"2312.13714","title":"Bootstrap Masked Visual Modeling via Hard Patches Mining","created":"2023-12-21","cited_by_count":5}],"next_cursor":null}