{"list":"other","total":129,"rows":[{"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":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"1602.05629","title":"Communication-Efficient Learning of Deep Networks from Decentralized Data","created":"2016-02-17","cited_by_count":7669},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"2205.11487","title":"Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding","created":"2022-05-23","cited_by_count":6355},{"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":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"id":"2205.11916","title":"Large Language Models are Zero-Shot Reasoners","created":"2022-05-24","cited_by_count":4374},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"2112.10741","title":"GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models","created":"2021-12-20","cited_by_count":3614},{"id":"2305.14314","title":"QLoRA: Efficient Finetuning of Quantized LLMs","created":"2023-05-23","cited_by_count":3418},{"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":"2307.15818","title":"RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control","created":"2023-07-28","cited_by_count":3080},{"id":"1607.00133","title":"Deep Learning with Differential Privacy","created":"2016-07-01","cited_by_count":2728},{"id":"2303.18223","title":"A Survey of Large Language Models","created":"2023-03-31","cited_by_count":2576},{"id":"2212.06817","title":"RT-1: Robotics Transformer for Real-World Control at Scale","created":"2022-12-13","cited_by_count":2061},{"id":"2206.04615","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","created":"2022-06-09","cited_by_count":1998},{"id":"2210.09261","title":"Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them","created":"2022-10-17","cited_by_count":1807},{"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":"2303.11328","title":"Zero-1-to-3: Zero-shot One Image to 3D Object","created":"2023-03-20","cited_by_count":1489},{"id":"2203.07814","title":"Competition-Level Code Generation with AlphaCode","created":"2022-02-08","cited_by_count":1462},{"id":"1804.03999","title":"Attention U-Net: Learning Where to Look for the Pancreas","created":"2018-04-11","cited_by_count":1435},{"id":"2112.03857","title":"Grounded Language-Image Pre-training","created":"2021-12-07","cited_by_count":1156},{"id":"2304.14178","title":"mPLUG-Owl: Modularization Empowers Large Language Models with Multimodality","created":"2023-04-27","cited_by_count":1040},{"id":"2112.08654","title":"Learning to Prompt for Continual Learning","created":"2021-12-16","cited_by_count":944},{"id":"2308.10144","title":"ExpeL: LLM Agents Are Experiential Learners","created":"2023-08-20","cited_by_count":876},{"id":"2211.09085","title":"Galactica: A Large Language Model for Science","created":"2022-11-16","cited_by_count":744},{"id":"1709.10087","title":"Learning Complex Dexterous Manipulation with Deep Reinforcement Learning and Demonstrations","created":"2017-09-28","cited_by_count":715},{"id":"2309.14525","title":"Aligning Large Multimodal Models with Factually Augmented RLHF","created":"2023-09-25","cited_by_count":712},{"id":"2110.07602","title":"P-Tuning v2: Prompt Tuning Can Be Comparable to Fine-tuning Universally Across Scales and Tasks","created":"2021-10-14","cited_by_count":689},{"id":"1604.02808","title":"NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysis","created":"2016-04-11","cited_by_count":686},{"id":"2012.12556","title":"A Survey on Visual Transformer","created":"2020-12-23","cited_by_count":654},{"id":"2012.09838","title":"Transformer Interpretability Beyond Attention Visualization","created":"2020-12-17","cited_by_count":627},{"id":"2212.00774","title":"Score Jacobian Chaining: Lifting Pretrained 2D Diffusion Models for 3D Generation","created":"2022-12-01","cited_by_count":597},{"id":"1801.00553","title":"Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Survey","created":"2018-01-02","cited_by_count":460},{"id":"2304.01933","title":"LLM-Adapters: An Adapter Family for Parameter-Efficient Fine-Tuning of Large Language Models","created":"2023-04-04","cited_by_count":324},{"id":"2304.08177","title":"Efficient and Effective Text Encoding for Chinese LLaMA and Alpaca","created":"2023-04-17","cited_by_count":305},{"id":"2206.05836","title":"GLIPv2: Unifying Localization and Vision-Language Understanding","created":"2022-06-12","cited_by_count":275},{"id":"2010.15875","title":"Retrieve, Program, Repeat: Complex Knowledge Base Question Answering via Alternate Meta-learning","created":"2020-10-29","cited_by_count":216},{"id":"2102.10274","title":"Concealed Object Detection","created":"2021-02-20","cited_by_count":212},{"id":"2309.14348","title":"Defending Against Alignment-Breaking Attacks via Robustly Aligned LLM","created":"2023-09-18","cited_by_count":192},{"id":"2102.10407","title":"VisualGPT: Data-efficient Adaptation of Pretrained Language Models for Image Captioning","created":"2021-02-20","cited_by_count":191},{"id":"2308.15366","title":"AnomalyGPT: Detecting Industrial Anomalies Using Large Vision-Language Models","created":"2023-08-29","cited_by_count":171},{"id":"2307.02499","title":"mPLUG-DocOwl: Modularized Multimodal Large Language Model for Document Understanding","created":"2023-07-04","cited_by_count":168},{"id":"2012.11866","title":"Human Action Recognition from Various Data Modalities: A Review","created":"2020-12-22","cited_by_count":163},{"id":"2310.03589","title":"TimeGPT-1","created":"2023-10-05","cited_by_count":158},{"id":"1503.00593","title":"Learning a Convolutional Neural Network for Non-uniform Motion Blur Removal","created":"2015-03-02","cited_by_count":149},{"id":"2309.00363","title":"FederatedScope-LLM: A Comprehensive Package for Fine-tuning Large Language Models in Federated Learning","created":"2023-09-01","cited_by_count":149},{"id":"1903.08536","title":"Segmentation-Based Deep-Learning Approach for Surface-Defect Detection","created":"2019-03-20","cited_by_count":145},{"id":"2001.07416","title":"Deep Learning for Sensor-based Human Activity Recognition: Overview, Challenges and Opportunities","created":"2020-01-21","cited_by_count":126},{"id":"2002.05646","title":"Adversarial Machine Learning -- Industry Perspectives","created":"2020-02-04","cited_by_count":122},{"id":"2304.05750","title":"Segment Anything Is Not Always Perfect: An Investigation of SAM on Different Real-world Applications","created":"2023-04-12","cited_by_count":121},{"id":"2112.06409","title":"Data Collection and Quality Challenges in Deep Learning: A Data-Centric AI Perspective","created":"2021-12-13","cited_by_count":116},{"id":"2212.10846","title":"From Images to Textual Prompts: Zero-shot VQA with Frozen Large Language Models","created":"2022-12-21","cited_by_count":115},{"id":"2202.06767","title":"Wukong: A 100 Million Large-scale Chinese Cross-modal Pre-training Benchmark","created":"2022-02-14","cited_by_count":114},{"id":"2110.14378","title":"Towards artificial general intelligence via a multimodal foundation model","created":"2021-10-27","cited_by_count":112},{"id":"1703.07475","title":"PKU-MMD: A Large Scale Benchmark for Continuous Multi-Modal Human Action Understanding","created":"2017-03-22","cited_by_count":101},{"id":"2304.04709","title":"Can SAM Segment Anything? When SAM Meets Camouflaged Object Detection","created":"2023-04-10","cited_by_count":100},{"id":"2305.13230","title":"To Repeat or Not To Repeat: Insights from Scaling LLM under Token-Crisis","created":"2023-05-22","cited_by_count":92},{"id":"2308.14840","title":"Identifying and Mitigating the Security Risks of Generative AI","created":"2023-08-28","cited_by_count":91},{"id":"2012.06399","title":"Spatial Temporal Transformer Network for Skeleton-based Action Recognition","created":"2020-12-11","cited_by_count":77},{"id":"2304.06022","title":"SAM Struggles in Concealed Scenes -- Empirical Study on Segment Anything","created":"2023-04-12","cited_by_count":75},{"id":"2207.08184","title":"Zero-Shot Temporal Action Detection via Vision-Language Prompting","created":"2022-07-17","cited_by_count":65},{"id":"2305.08196","title":"A Comprehensive Survey on Segment Anything Model for Vision and Beyond","created":"2023-05-14","cited_by_count":64},{"id":"2305.09863","title":"Explaining black box text modules in natural language with language models","created":"2023-05-17","cited_by_count":62},{"id":"2308.13437","title":"Position-Enhanced Visual Instruction Tuning for Multimodal Large Language Models","created":"2023-08-25","cited_by_count":59},{"id":"2108.04417","title":"Privacy-Preserving Machine Learning: Methods, Challenges and Directions","created":"2021-08-10","cited_by_count":58},{"id":"2111.00418","title":"Deep Learning in Human Activity Recognition with Wearable Sensors: A Review on Advances","created":"2021-10-31","cited_by_count":54},{"id":"2305.14288","title":"LLM-powered Data Augmentation for Enhanced Cross-lingual Performance","created":"2023-05-23","cited_by_count":51},{"id":"2310.00603","title":"Faithful Explanations of Black-box NLP Models Using LLM-generated Counterfactuals","created":"2023-10-01","cited_by_count":44},{"id":"2307.06917","title":"LLM-assisted Knowledge Graph Engineering: Experiments with ChatGPT","created":"2023-07-13","cited_by_count":42},{"id":"2310.19070","title":"Myriad: Large Multimodal Model by Applying Vision Experts for Industrial Anomaly Detection","created":"2023-10-29","cited_by_count":39},{"id":"2008.09514","title":"Neural Logic Reasoning","created":"2020-08-20","cited_by_count":38},{"id":"2209.11799","title":"Augmenting Interpretable Models with LLMs during Training","created":"2022-09-23","cited_by_count":38},{"id":"2307.01187","title":"SAMAug: Point Prompt Augmentation for Segment Anything Model","created":"2023-07-03","cited_by_count":38},{"id":"2310.19248","title":"IMPRESS: Evaluating the Resilience of Imperceptible Perturbations Against Unauthorized Data Usage in Diffusion-Based Generative AI","created":"2023-10-30","cited_by_count":35},{"id":"2304.13973","title":"SkinSAM: Empowering Skin Cancer Segmentation with Segment Anything Model","created":"2023-04-27","cited_by_count":32},{"id":"2101.00798","title":"Fusion of Federated Learning and Industrial Internet of Things: A Survey","created":"2021-01-04","cited_by_count":29},{"id":"2305.01157","title":"Complex Logical Reasoning over Knowledge Graphs using Large Language Models","created":"2023-05-02","cited_by_count":28},{"id":"2212.13504","title":"DAE-Former: Dual Attention-guided Efficient Transformer for Medical Image Segmentation","created":"2022-12-27","cited_by_count":27},{"id":"2306.11732","title":"Retrieving-to-Answer: Zero-Shot Video Question Answering with Frozen Large Language Models","created":"2023-06-15","cited_by_count":27},{"id":"2305.16220","title":"On the Robustness of Segment Anything","created":"2023-05-25","cited_by_count":25},{"id":"2301.04408","title":"GPT as Knowledge Worker: A Zero-Shot Evaluation of (AI)CPA Capabilities","created":"2023-01-11","cited_by_count":22},{"id":"2307.02435","title":"Exploring Continual Learning for Code Generation Models","created":"2023-07-05","cited_by_count":22},{"id":"2205.03860","title":"CCMB: A Large-scale Chinese Cross-modal Benchmark","created":"2022-05-08","cited_by_count":21},{"id":"2304.10550","title":"Deep transfer learning for intrusion detection in industrial control networks: A comprehensive review","created":"2023-04-19","cited_by_count":21},{"id":"2308.14133","title":"Cheap Lunch for Medical Image Segmentation by Fine-tuning SAM on Few Exemplars","created":"2023-08-27","cited_by_count":21},{"id":"2110.07448","title":"Human-robot collaboration and machine learning: a systematic review of recent research","created":"2021-10-14","cited_by_count":20},{"id":"1912.12528","title":"Applications of Unsupervised Deep Transfer Learning to Intelligent Fault Diagnosis: A Survey and Comparative Study","created":"2019-12-28","cited_by_count":19},{"id":"2008.06701","title":"Deep Learning in Industrial Internet of Things: Potentials, Challenges, and Emerging Applications","created":"2020-08-15","cited_by_count":19},{"id":"2211.06885","title":"SCOTCH and SODA: A Transformer Video Shadow Detection Framework","created":"2022-11-13","cited_by_count":19},{"id":"2303.16382","title":"ARMBench: An Object-centric Benchmark Dataset for Robotic Manipulation","created":"2023-03-29","cited_by_count":18},{"id":"1901.08204","title":"A PCB Dataset for Defects Detection and Classification","created":"2019-01-24","cited_by_count":16}],"next_cursor":"100"}