{"list":"other","total":81,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"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":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"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":"2310.03744","title":"Improved Baselines with Visual Instruction Tuning","created":"2023-10-05","cited_by_count":4418},{"id":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"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":"2307.15818","title":"RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control","created":"2023-07-28","cited_by_count":3080},{"id":"2305.06500","title":"InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning","created":"2023-05-11","cited_by_count":2876},{"id":"2304.10592","title":"MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models","created":"2023-04-20","cited_by_count":2711},{"id":"2303.03378","title":"PaLM-E: An Embodied Multimodal Language Model","created":"2023-03-06","cited_by_count":2071},{"id":"2306.02858","title":"Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding","created":"2023-06-05","cited_by_count":1471},{"id":"1505.04870","title":"Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Models","created":"2015-05-19","cited_by_count":1362},{"id":"2306.14824","title":"Kosmos-2: Grounding Multimodal Large Language Models to the World","created":"2023-06-26","cited_by_count":1089},{"id":"2311.12793","title":"ShareGPT4V: Improving Large Multi-Modal Models with Better Captions","created":"2023-11-21","cited_by_count":1005},{"id":"2306.13549","title":"A Survey on Multimodal Large Language Models","created":"2023-06-23","cited_by_count":909},{"id":"2306.15195","title":"Shikra: Unleashing Multimodal LLM's Referential Dialogue Magic","created":"2023-06-27","cited_by_count":906},{"id":"2305.06355","title":"VideoChat: Chat-Centric Video Understanding","created":"2023-05-10","cited_by_count":857},{"id":"2202.03052","title":"OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework","created":"2022-02-07","cited_by_count":745},{"id":"2311.03079","title":"CogVLM: Visual Expert for Pretrained Language Models","created":"2023-11-06","cited_by_count":708},{"id":"2401.02385","title":"TinyLlama: An Open-Source Small Language Model","created":"2024-01-04","cited_by_count":618},{"id":"2304.15010","title":"LLaMA-Adapter V2: Parameter-Efficient Visual Instruction Model","created":"2023-04-28","cited_by_count":602},{"id":"2302.14045","title":"Language Is Not All You Need: Aligning Perception with Language Models","created":"2023-02-27","cited_by_count":543},{"id":"2310.07704","title":"Ferret: Refer and Ground Anything Anywhere at Any Granularity","created":"2023-10-11","cited_by_count":509},{"id":"2305.11175","title":"VisionLLM: Large Language Model is also an Open-Ended Decoder for Vision-Centric Tasks","created":"2023-05-18","cited_by_count":501},{"id":"2312.13771","title":"AppAgent: Multimodal Agents as Smartphone Users","created":"2023-12-21","cited_by_count":415},{"id":"1908.07836","title":"PubLayNet: largest dataset ever for document layout analysis","created":"2019-08-16","cited_by_count":351},{"id":"2109.10852","title":"Pix2seq: A Language Modeling Framework for Object Detection","created":"2021-09-22","cited_by_count":349},{"id":"2305.15393","title":"LayoutGPT: Compositional Visual Planning and Generation with Large Language Models","created":"2023-05-24","cited_by_count":347},{"id":"2401.16158","title":"Mobile-Agent: Autonomous Multi-Modal Mobile Device Agent with Visual Perception","created":"2024-01-29","cited_by_count":293},{"id":"2311.12320","title":"A Survey on Multimodal Large Language Models for Autonomous Driving","created":"2023-11-21","cited_by_count":290},{"id":"2305.15021","title":"EmbodiedGPT: Vision-Language Pre-Training via Embodied Chain of Thought","created":"2023-05-24","cited_by_count":279},{"id":"2401.13601","title":"MM-LLMs: Recent Advances in MultiModal Large Language Models","created":"2024-01-24","cited_by_count":278},{"id":"2309.10020","title":"Multimodal Foundation Models: From Specialists to General-Purpose Assistants","created":"2023-09-18","cited_by_count":247},{"id":"2402.12226","title":"AnyGPT: Unified Multimodal LLM with Discrete Sequence Modeling","created":"2024-02-19","cited_by_count":217},{"id":"2312.17432","title":"Video Understanding with Large Language Models: A Survey","created":"2023-12-29","cited_by_count":206},{"id":"2306.15880","title":"Towards Open Vocabulary Learning: A Survey","created":"2023-06-28","cited_by_count":166},{"id":"2007.11301","title":"DeepSVG: A Hierarchical Generative Network for Vector Graphics Animation","created":"2020-07-22","cited_by_count":159},{"id":"2312.10032","title":"Osprey: Pixel Understanding with Visual Instruction Tuning","created":"2023-12-15","cited_by_count":159},{"id":"2307.05222","title":"Emu: Generative Pretraining in Multimodality","created":"2023-07-11","cited_by_count":157},{"id":"2303.08137","title":"LayoutDM: Discrete Diffusion Model for Controllable Layout Generation","created":"2023-03-14","cited_by_count":143},{"id":"1901.06767","title":"LayoutGAN: Generating Graphic Layouts with Wireframe Discriminators","created":"2019-01-21","cited_by_count":131},{"id":"1705.07962","title":"pix2code: Generating Code from a Graphical User Interface Screenshot","created":"2017-05-22","cited_by_count":114},{"id":"2108.01249","title":"CanvasVAE: Learning to Generate Vector Graphic Documents","created":"2021-08-03","cited_by_count":95},{"id":"2104.02416","title":"Variational Transformer Networks for Layout Generation","created":"2021-04-06","cited_by_count":88},{"id":"1912.09421","title":"Neural Design Network: Graphic Layout Generation with Constraints","created":"2019-12-19","cited_by_count":83},{"id":"2108.00871","title":"Constrained Graphic Layout Generation via Latent Optimization","created":"2021-08-02","cited_by_count":83},{"id":"2105.02769","title":"Computer-Aided Design as Language","created":"2021-05-06","cited_by_count":82},{"id":"2401.00988","title":"Holistic Autonomous Driving Understanding by Bird's-Eye-View Injected Multi-Modal Large Models","created":"2024-01-02","cited_by_count":76},{"id":"2304.14400","title":"IconShop: Text-Guided Vector Icon Synthesis with Autoregressive Transformers","created":"2023-04-27","cited_by_count":75},{"id":"2401.10229","title":"OMG-Seg: Is One Model Good Enough For All Segmentation?","created":"2024-01-18","cited_by_count":75},{"id":"2101.11796","title":"DOC2PPT: Automatic Presentation Slides Generation from Scientific Documents","created":"2021-01-28","cited_by_count":70},{"id":"2112.05112","title":"BLT: Bidirectional Layout Transformer for Controllable Layout Generation","created":"2021-12-09","cited_by_count":69},{"id":"2009.05284","title":"Attribute-conditioned Layout GAN for Automatic Graphic Design","created":"2020-09-11","cited_by_count":68},{"id":"2106.02711","title":"SketchGen: Generating Constrained CAD Sketches","created":"2021-06-04","cited_by_count":68},{"id":"2303.15937","title":"PosterLayout: A New Benchmark and Approach for Content-aware Visual-Textual Presentation Layout","created":"2023-03-28","cited_by_count":61},{"id":"2205.00303","title":"Composition-aware Graphic Layout GAN for Visual-textual Presentation Designs","created":"2022-04-30","cited_by_count":59},{"id":"2311.06612","title":"PerceptionGPT: Effectively Fusing Visual Perception into LLM","created":"2023-11-11","cited_by_count":59},{"id":"2208.08037","title":"LayoutFormer++: Conditional Graphic Layout Generation via Constraint Serialization and Decoding Space Restriction","created":"2022-08-17","cited_by_count":43},{"id":"2303.11589","title":"LayoutDiffusion: Improving Graphic Layout Generation by Discrete Diffusion Probabilistic Models","created":"2023-03-21","cited_by_count":41},{"id":"2308.01095","title":"AutoPoster: A Highly Automatic and Content-aware Design System for Advertising Poster Generation","created":"2023-08-02","cited_by_count":41},{"id":"2306.09086","title":"Relation-Aware Diffusion Model for Controllable Poster Layout Generation","created":"2023-06-15","cited_by_count":37},{"id":"2303.18248","title":"Towards Flexible Multi-modal Document Models","created":"2023-03-31","cited_by_count":31},{"id":"2301.11529","title":"PLay: Parametrically Conditioned Layout Generation using Latent Diffusion","created":"2023-01-27","cited_by_count":24},{"id":"2308.07891","title":"Link-Context Learning for Multimodal LLMs","created":"2023-08-15","cited_by_count":24},{"id":"2309.09506","title":"LayoutNUWA: Revealing the Hidden Layout Expertise of Large Language Models","created":"2023-09-18","cited_by_count":19},{"id":"2308.04733","title":"TextPainter: Multimodal Text Image Generation with Visual-harmony and Text-comprehension for Poster Design","created":"2023-08-09","cited_by_count":18},{"id":"2212.09877","title":"LayoutDETR: Detection Transformer Is a Good Multimodal Layout Designer","created":"2022-12-19","cited_by_count":15},{"id":"2308.12700","title":"A Parse-Then-Place Approach for Generating Graphic Layouts from Textual Descriptions","created":"2023-08-24","cited_by_count":15},{"id":"2310.15455","title":"UI Layout Generation with LLMs Guided by UI Grammar","created":"2023-10-24","cited_by_count":15},{"id":"2311.06791","title":"InfMLLM: A Unified Framework for Visual-Language Tasks","created":"2023-11-12","cited_by_count":11},{"id":"2306.06233","title":"Boosting GUI Prototyping with Diffusion Models","created":"2023-06-09","cited_by_count":10},{"id":"2204.08676","title":"Auto-Icon+: An Automated End-to-End Code Generation Tool for Icon Designs in UI Development","created":"2022-04-19","cited_by_count":3}],"next_cursor":null}