{"list":"other","total":72,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"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":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"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":"2204.06125","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","created":"2022-04-13","cited_by_count":6585},{"id":"1905.11946","title":"EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks","created":"2019-05-28","cited_by_count":6442},{"id":"1910.13461","title":"BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension","created":"2019-10-29","cited_by_count":5893},{"id":"2310.03744","title":"Improved Baselines with Visual Instruction Tuning","created":"2023-10-05","cited_by_count":4418},{"id":"2102.12092","title":"Zero-Shot Text-to-Image Generation","created":"2021-02-24","cited_by_count":4288},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"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":"2201.03545","title":"A ConvNet for the 2020s","created":"2022-01-10","cited_by_count":3579},{"id":"2010.04159","title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","created":"2020-10-08","cited_by_count":3422},{"id":"2304.10592","title":"MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models","created":"2023-04-20","cited_by_count":2711},{"id":"2106.08254","title":"BEiT: BERT Pre-Training of Image Transformers","created":"2021-06-15","cited_by_count":2375},{"id":"2308.12966","title":"Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond","created":"2023-08-24","cited_by_count":2224},{"id":"2310.02255","title":"MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts","created":"2023-10-03","cited_by_count":1614},{"id":"2306.06070","title":"Mind2Web: Towards a Generalist Agent for the Web","created":"2023-06-09","cited_by_count":1242},{"id":"2111.09883","title":"Swin Transformer V2: Scaling Up Capacity and Resolution","created":"2021-11-18","cited_by_count":1228},{"id":"1912.08777","title":"PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization","created":"2019-12-18","cited_by_count":1102},{"id":"2306.14824","title":"Kosmos-2: Grounding Multimodal Large Language Models to the World","created":"2023-06-26","cited_by_count":1089},{"id":"1608.00272","title":"Modeling Context in Referring Expressions","created":"2016-07-31","cited_by_count":1063},{"id":"2304.14178","title":"mPLUG-Owl: Modularization Empowers Large Language Models with Multimodality","created":"2023-04-27","cited_by_count":1040},{"id":"2306.15195","title":"Shikra: Unleashing Multimodal LLM's Referential Dialogue Magic","created":"2023-06-27","cited_by_count":906},{"id":"1511.02283","title":"Generation and Comprehension of Unambiguous Object Descriptions","created":"2015-11-07","cited_by_count":904},{"id":"2110.06864","title":"ByteTrack: Multi-Object Tracking by Associating Every Detection Box","created":"2021-10-13","cited_by_count":823},{"id":"2111.11432","title":"Florence: A New Foundation Model for Computer Vision","created":"2021-11-22","cited_by_count":804},{"id":"2312.08914","title":"CogAgent: A Visual Language Model for GUI Agents","created":"2023-12-14","cited_by_count":704},{"id":"2107.14795","title":"Perceiver IO: A General Architecture for Structured Inputs & Outputs","created":"2021-07-30","cited_by_count":629},{"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":"2401.10935","title":"SeeClick: Harnessing GUI Grounding for Advanced Visual GUI Agents","created":"2024-01-17","cited_by_count":567},{"id":"2401.01614","title":"GPT-4V(ision) is a Generalist Web Agent, if Grounded","created":"2024-01-03","cited_by_count":563},{"id":"2304.06718","title":"Segment Everything Everywhere All at Once","created":"2023-04-13","cited_by_count":548},{"id":"2208.10442","title":"Image as a Foreign Language: BEiT Pretraining for All Vision and Vision-Language Tasks","created":"2022-08-22","cited_by_count":511},{"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":"2104.01136","title":"LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inference","created":"2021-04-02","cited_by_count":475},{"id":"2108.06152","title":"Conditional DETR for Fast Training Convergence","created":"2021-08-13","cited_by_count":424},{"id":"2312.13771","title":"AppAgent: Multimodal Agents as Smartphone Users","created":"2023-12-21","cited_by_count":415},{"id":"2303.17491","title":"Language Models can Solve Computer Tasks","created":"2023-03-30","cited_by_count":372},{"id":"2307.12856","title":"A Real-World WebAgent with Planning, Long Context Understanding, and Program Synthesis","created":"2023-07-24","cited_by_count":353},{"id":"2112.02244","title":"LAVT: Language-Aware Vision Transformer for Referring Image Segmentation","created":"2021-12-04","cited_by_count":348},{"id":"1802.08802","title":"Reinforcement Learning on Web Interfaces Using Workflow-Guided Exploration","created":"2018-02-24","cited_by_count":284},{"id":"1904.04745","title":"Cross-Modal Self-Attention Network for Referring Image Segmentation","created":"2019-04-09","cited_by_count":263},{"id":"2402.07456","title":"OS-Copilot: Towards Generalist Computer Agents with Self-Improvement","created":"2024-02-12","cited_by_count":205},{"id":"1908.06354","title":"A Fast and Accurate One-Stage Approach to Visual Grounding","created":"2019-08-18","cited_by_count":195},{"id":"2303.06674","title":"Universal Instance Perception as Object Discovery and Retrieval","created":"2023-03-12","cited_by_count":192},{"id":"2306.07863","title":"Synapse: Trajectory-as-Exemplar Prompting with Memory for Computer Control","created":"2023-06-13","cited_by_count":187},{"id":"2309.11436","title":"You Only Look at Screens: Multimodal Chain-of-Action Agents","created":"2023-09-20","cited_by_count":185},{"id":"2005.03776","title":"Mapping Natural Language Instructions to Mobile UI Action Sequences","created":"2020-05-07","cited_by_count":181},{"id":"2106.00666","title":"You Only Look at One Sequence: Rethinking Transformer in Vision through Object Detection","created":"2021-06-01","cited_by_count":170},{"id":"1603.04042","title":"Deep Interactive Object Selection","created":"2016-03-13","cited_by_count":160},{"id":"2311.07562","title":"GPT-4V in Wonderland: Large Multimodal Models for Zero-Shot Smartphone GUI Navigation","created":"2023-11-13","cited_by_count":137},{"id":"1908.03851","title":"IoU Loss for 2D/3D Object Detection","created":"2019-08-11","cited_by_count":128},{"id":"2110.00061","title":"PubTables-1M: Towards comprehensive table extraction from unstructured documents","created":"2021-09-30","cited_by_count":126},{"id":"2305.09972","title":"Real-Time Flying Object Detection with YOLOv8","created":"2023-05-17","cited_by_count":94},{"id":"2306.03413","title":"DVIS: Decoupled Video Instance Segmentation Framework","created":"2023-06-06","cited_by_count":77},{"id":"2310.00280","title":"Corex: Pushing the Boundaries of Complex Reasoning through Multi-Model Collaboration","created":"2023-09-30","cited_by_count":70},{"id":"2209.14927","title":"Spotlight: Mobile UI Understanding using Vision-Language Models with a Focus","created":"2022-09-29","cited_by_count":62},{"id":"1812.09195","title":"Learning to Navigate the Web","created":"2018-12-21","cited_by_count":60},{"id":"2401.06468","title":"Adapting Large Language Models for Document-Level Machine Translation","created":"2024-01-12","cited_by_count":59},{"id":"2311.09278","title":"Symbol-LLM: Towards Foundational Symbol-centric Interface For Large Language Models","created":"2023-11-15","cited_by_count":39},{"id":"2312.12740","title":"Fine-tuning Large Language Models for Adaptive Machine Translation","created":"2023-12-20","cited_by_count":21},{"id":"2310.04716","title":"Reinforced UI Instruction Grounding: Towards a Generic UI Task Automation API","created":"2023-10-07","cited_by_count":18},{"id":"2205.15051","title":"X-SCITLDR: Cross-Lingual Extreme Summarization of Scholarly Documents","created":"2022-05-30","cited_by_count":12},{"id":"2109.08634","title":"Grounding Natural Language Instructions: Can Large Language Models Capture Spatial Information?","created":"2021-09-17","cited_by_count":10}],"next_cursor":null}