{"list":"other","total":174,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"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":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"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":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"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":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"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":"2302.05543","title":"Adding Conditional Control to Text-to-Image Diffusion Models","created":"2023-02-10","cited_by_count":5503},{"id":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"id":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"id":"2205.11916","title":"Large Language Models are Zero-Shot Reasoners","created":"2022-05-24","cited_by_count":4374},{"id":"2201.12086","title":"BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation","created":"2022-01-28","cited_by_count":4322},{"id":"2303.05499","title":"Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection","created":"2023-03-09","cited_by_count":3332},{"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":"2408.00714","title":"SAM 2: Segment Anything in Images and Videos","created":"2024-08-01","cited_by_count":2863},{"id":"2303.18223","title":"A Survey of Large Language Models","created":"2023-03-31","cited_by_count":2576},{"id":"1711.03938","title":"CARLA: An Open Urban Driving Simulator","created":"2017-11-10","cited_by_count":2449},{"id":"2109.01134","title":"Learning to Prompt for Vision-Language Models","created":"2021-09-02","cited_by_count":2281},{"id":"2407.10671","title":"Qwen2 Technical Report","created":"2024-07-15","cited_by_count":2120},{"id":"2303.03378","title":"PaLM-E: An Embodied Multimodal Language Model","created":"2023-03-06","cited_by_count":2071},{"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":"2406.09414","title":"Depth Anything V2","created":"2024-06-13","cited_by_count":1422},{"id":"2401.10891","title":"Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data","created":"2024-01-19","cited_by_count":1360},{"id":"2203.03605","title":"DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection","created":"2022-03-07","cited_by_count":1319},{"id":"2307.03109","title":"A Survey on Evaluation of Large Language Models","created":"2023-07-06","cited_by_count":1242},{"id":"2101.06804","title":"What Makes Good In-Context Examples for GPT-$3$?","created":"2021-01-17","cited_by_count":1195},{"id":"2303.17580","title":"HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face","created":"2023-03-30","cited_by_count":1190},{"id":"2401.14196","title":"DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligence","created":"2024-01-25","cited_by_count":1181},{"id":"2112.03857","title":"Grounded Language-Image Pre-training","created":"2021-12-07","cited_by_count":1156},{"id":"2405.04434","title":"DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model","created":"2024-05-07","cited_by_count":1135},{"id":"2406.12793","title":"ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools","created":"2024-06-18","cited_by_count":1121},{"id":"2306.05424","title":"Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models","created":"2023-06-08","cited_by_count":1062},{"id":"2306.13549","title":"A Survey on Multimodal Large Language Models","created":"2023-06-23","cited_by_count":909},{"id":"2104.13921","title":"Open-vocabulary Object Detection via Vision and Language Knowledge Distillation","created":"2021-04-28","cited_by_count":906},{"id":"2210.02414","title":"GLM-130B: An Open Bilingual Pre-trained Model","created":"2022-10-05","cited_by_count":843},{"id":"2304.00685","title":"Vision-Language Models for Vision Tasks: A Survey","created":"2023-04-03","cited_by_count":839},{"id":"2303.15389","title":"EVA-CLIP: Improved Training Techniques for CLIP at Scale","created":"2023-03-27","cited_by_count":798},{"id":"1703.00121","title":"Remote Sensing Image Scene Classification: Benchmark and State of the Art","created":"2017-03-01","cited_by_count":797},{"id":"2307.15217","title":"Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback","created":"2023-07-27","cited_by_count":759},{"id":"2401.12168","title":"SpatialVLM: Endowing Vision-Language Models with Spatial Reasoning Capabilities","created":"2024-01-22","cited_by_count":706},{"id":"2210.03493","title":"Automatic Chain of Thought Prompting in Large Language Models","created":"2022-10-07","cited_by_count":688},{"id":"2309.17421","title":"The Dawn of LMMs: Preliminary Explorations with GPT-4V(ision)","created":"2023-09-29","cited_by_count":681},{"id":"2302.12288","title":"ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depth","created":"2023-02-23","cited_by_count":657},{"id":"1803.08475","title":"Attention, Learn to Solve Routing Problems!","created":"2018-03-22","cited_by_count":656},{"id":"2307.06435","title":"A Comprehensive Overview of Large Language Models","created":"2023-07-12","cited_by_count":648},{"id":"2111.07783","title":"FILIP: Fine-grained Interactive Language-Image Pre-Training","created":"2021-11-09","cited_by_count":627},{"id":"1711.10398","title":"DOTA: A Large-scale Dataset for Object Detection in Aerial Images","created":"2017-11-28","cited_by_count":623},{"id":"2112.09106","title":"RegionCLIP: Region-based Language-Image Pretraining","created":"2021-12-16","cited_by_count":616},{"id":"2210.04150","title":"Open-Vocabulary Semantic Segmentation with Mask-adapted CLIP","created":"2022-10-09","cited_by_count":565},{"id":"2210.02406","title":"Decomposed Prompting: A Modular Approach for Solving Complex Tasks","created":"2022-10-05","cited_by_count":558},{"id":"2304.06718","title":"Segment Everything Everywhere All at Once","created":"2023-04-13","cited_by_count":548},{"id":"2311.17043","title":"LLaMA-VID: An Image is Worth 2 Tokens in Large Language Models","created":"2023-11-28","cited_by_count":546},{"id":"2402.06196","title":"Large Language Models: A Survey","created":"2024-02-09","cited_by_count":525},{"id":"1705.05065","title":"AirSim: High-Fidelity Visual and Physical Simulation for Autonomous Vehicles","created":"2017-05-15","cited_by_count":523},{"id":"2211.11559","title":"Visual Programming: Compositional visual reasoning without training","created":"2022-11-18","cited_by_count":516},{"id":"2112.10003","title":"Image Segmentation Using Text and Image Prompts","created":"2021-12-18","cited_by_count":512},{"id":"2401.17270","title":"YOLO-World: Real-Time Open-Vocabulary Object Detection","created":"2024-01-30","cited_by_count":503},{"id":"1909.11059","title":"Unified Vision-Language Pre-Training for Image Captioning and VQA","created":"2019-09-24","cited_by_count":494},{"id":"1810.11981","title":"GOT-10k: A Large High-Diversity Benchmark for Generic Object Tracking in the Wild","created":"2018-10-29","cited_by_count":475},{"id":"2411.10440","title":"LLaVA-CoT: Let Vision Language Models Reason Step-by-Step","created":"2024-11-15","cited_by_count":454},{"id":"2402.02716","title":"Understanding the planning of LLM agents: A survey","created":"2024-02-05","cited_by_count":421},{"id":"2410.02073","title":"Depth Pro: Sharp Monocular Metric Depth in Less Than a Second","created":"2024-10-02","cited_by_count":404},{"id":"2403.17297","title":"InternLM2 Technical Report","created":"2024-03-26","cited_by_count":397},{"id":"2009.09796","title":"Multi-Task Learning with Deep Neural Networks: A Survey","created":"2020-09-10","cited_by_count":375},{"id":"2306.11029","title":"RemoteCLIP: A Vision Language Foundation Model for Remote Sensing","created":"2023-06-19","cited_by_count":363},{"id":"2402.00253","title":"A Survey on Hallucination in Large Vision-Language Models","created":"2024-02-01","cited_by_count":357},{"id":"2304.09842","title":"Chameleon: Plug-and-Play Compositional Reasoning with Large Language Models","created":"2023-04-19","cited_by_count":356},{"id":"2306.14289","title":"Faster Segment Anything: Towards Lightweight SAM for Mobile Applications","created":"2023-06-25","cited_by_count":352},{"id":"1909.00133","title":"Object Detection in Optical Remote Sensing Images: A Survey and A New Benchmark","created":"2019-08-31","cited_by_count":340},{"id":"2401.15947","title":"MoE-LLaVA: Mixture of Experts for Large Vision-Language Models","created":"2024-01-29","cited_by_count":300},{"id":"2306.17582","title":"ChatGPT for Robotics: Design Principles and Model Abilities","created":"2023-02-20","cited_by_count":299},{"id":"2305.15408","title":"Towards Revealing the Mystery behind Chain of Thought: A Theoretical Perspective","created":"2023-05-24","cited_by_count":294},{"id":"1810.05642","title":"The highD Dataset: A Drone Dataset of Naturalistic Vehicle Trajectories on German Highways for Validation of Highly Automated Driving Systems","created":"2018-10-11","cited_by_count":277},{"id":"2001.06303","title":"Detection and Tracking Meet Drones Challenge","created":"2020-01-16","cited_by_count":263},{"id":"2111.08276","title":"Multi-Grained Vision Language Pre-Training: Aligning Texts with Visual Concepts","created":"2021-11-16","cited_by_count":256},{"id":"2405.19209","title":"VideoTree: Adaptive Tree-based Video Representation for LLM Reasoning on Long Videos","created":"2024-05-29","cited_by_count":251},{"id":"1804.00518","title":"The Unmanned Aerial Vehicle Benchmark: Object Detection and Tracking","created":"2018-03-26","cited_by_count":208},{"id":"2403.14003","title":"Multi-Modal Hallucination Control by Visual Information Grounding","created":"2024-03-20","cited_by_count":208},{"id":"1712.07835","title":"Exploring Models and Data for Remote Sensing Image Caption Generation","created":"2017-12-21","cited_by_count":197},{"id":"1905.12886","title":"iSAID: A Large-scale Dataset for Instance Segmentation in Aerial Images","created":"2019-05-30","cited_by_count":197},{"id":"2111.12233","title":"Scaling Up Vision-Language Pre-training for Image Captioning","created":"2021-11-24","cited_by_count":196},{"id":"2011.12172","title":"VIGOR: Cross-View Image Geo-localization beyond One-to-one Retrieval","created":"2020-11-24","cited_by_count":189},{"id":"2012.02951","title":"FloodNet: A High Resolution Aerial Imagery Dataset for Post Flood Scene Understanding","created":"2020-12-05","cited_by_count":181},{"id":"2202.10936","title":"A Survey of Vision-Language Pre-Trained Models","created":"2022-02-18","cited_by_count":177},{"id":"2312.06709","title":"AM-RADIO: Agglomerative Vision Foundation Model -- Reduce All Domains Into One","created":"2023-12-10","cited_by_count":169},{"id":"2012.11866","title":"Human Action Recognition from Various Data Modalities: A Review","created":"2020-12-22","cited_by_count":163},{"id":"2312.10032","title":"Osprey: Pixel Understanding with Visual Instruction Tuning","created":"2023-12-15","cited_by_count":159},{"id":"2002.12186","title":"University-1652: A Multi-view Multi-source Benchmark for Drone-based Geo-localization","created":"2020-02-27","cited_by_count":157},{"id":"1707.05972","title":"Drone-based Object Counting by Spatially Regularized Regional Proposal Network","created":"2017-07-19","cited_by_count":156},{"id":"2306.11300","title":"RS5M and GeoRSCLIP: A Large Scale Vision-Language Dataset and A Large Vision-Language Model for Remote Sensing","created":"2023-06-20","cited_by_count":151},{"id":"1802.07856","title":"xView: Objects in Context in Overhead Imagery","created":"2018-02-22","cited_by_count":146},{"id":"2103.16746","title":"Towards More Flexible and Accurate Object Tracking with Natural Language: Algorithms and Benchmark","created":"2021-03-31","cited_by_count":126}],"next_cursor":"100"}