{"list":"other","total":76,"rows":[{"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":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"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":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"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":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"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":"1902.00751","title":"Parameter-Efficient Transfer Learning for NLP","created":"2019-02-02","cited_by_count":4236},{"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":"2109.01652","title":"Finetuned Language Models Are Zero-Shot Learners","created":"2021-09-03","cited_by_count":3780},{"id":"1505.07818","title":"Domain-Adversarial Training of Neural Networks","created":"2015-05-28","cited_by_count":3044},{"id":"2210.11416","title":"Scaling Instruction-Finetuned Language Models","created":"2022-10-20","cited_by_count":3024},{"id":"1409.3215","title":"Sequence to Sequence Learning with Neural Networks","created":"2014-09-10","cited_by_count":2986},{"id":"2212.10560","title":"Self-Instruct: Aligning Language Models with Self-Generated Instructions","created":"2022-12-20","cited_by_count":2724},{"id":"1602.07332","title":"Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations","created":"2016-02-23","cited_by_count":2656},{"id":"1311.3618","title":"Describing Textures in the Wild","created":"2013-11-14","cited_by_count":2125},{"id":"2001.07685","title":"FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence","created":"2020-01-21","cited_by_count":2085},{"id":"2010.01412","title":"Sharpness-Aware Minimization for Efficiently Improving Generalization","created":"2020-10-03","cited_by_count":1417},{"id":"1502.02791","title":"Learning Transferable Features with Deep Adaptation Networks","created":"2015-02-10","cited_by_count":1329},{"id":"1908.03195","title":"LVIS: A Dataset for Large Vocabulary Instance Segmentation","created":"2019-08-08","cited_by_count":1217},{"id":"1805.04833","title":"Hierarchical Neural Story Generation","created":"2018-05-13","cited_by_count":1193},{"id":"1706.07522","title":"Deep Hashing Network for Unsupervised Domain Adaptation","created":"2017-06-22","cited_by_count":1188},{"id":"2007.01434","title":"In Search of Lost Domain Generalization","created":"2020-07-02","cited_by_count":1054},{"id":"1710.03077","title":"Deeper, Broader and Artier Domain Generalization","created":"2017-10-09","cited_by_count":986},{"id":"2003.13678","title":"Designing Network Design Spaces","created":"2020-03-30","cited_by_count":960},{"id":"2302.00093","title":"Large Language Models Can Be Easily Distracted by Irrelevant Context","created":"2023-01-31","cited_by_count":841},{"id":"2109.01903","title":"Robust fine-tuning of zero-shot models","created":"2021-09-04","cited_by_count":797},{"id":"2103.02503","title":"Domain Generalization: A Survey","created":"2021-03-03","cited_by_count":764},{"id":"2302.00923","title":"Multimodal Chain-of-Thought Reasoning in Language Models","created":"2023-02-02","cited_by_count":752},{"id":"2309.12284","title":"MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models","created":"2023-09-21","cited_by_count":735},{"id":"2309.01219","title":"Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Models","created":"2023-09-03","cited_by_count":698},{"id":"2104.02008","title":"Domain Generalization with MixStyle","created":"2021-04-05","cited_by_count":566},{"id":"2110.08263","title":"FlexMatch: Boosting Semi-Supervised Learning with Curriculum Pseudo Labeling","created":"2021-10-15","cited_by_count":540},{"id":"2205.14100","title":"GIT: A Generative Image-to-text Transformer for Vision and Language","created":"2022-05-27","cited_by_count":537},{"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":"1710.06924","title":"VisDA: The Visual Domain Adaptation Challenge","created":"2017-10-18","cited_by_count":435},{"id":"2102.08604","title":"SWAD: Domain Generalization by Seeking Flat Minima","created":"2021-02-17","cited_by_count":434},{"id":"2310.01558","title":"Making Retrieval-Augmented Language Models Robust to Irrelevant Context","created":"2023-10-02","cited_by_count":369},{"id":"1907.07484","title":"Benchmarking Robustness in Object Detection: Autonomous Driving when Winter is Coming","created":"2019-07-17","cited_by_count":336},{"id":"2205.09712","title":"Selection-Inference: Exploiting Large Language Models for Interpretable Logical Reasoning","created":"2022-05-19","cited_by_count":334},{"id":"2206.08367","title":"SHIFT: A Synthetic Driving Dataset for Continuous Multi-Task Domain Adaptation","created":"2022-06-16","cited_by_count":146},{"id":"1804.07781","title":"Pathologies of Neural Models Make Interpretations Difficult","created":"2018-04-20","cited_by_count":140},{"id":"2203.10789","title":"Domain Generalization by Mutual-Information Regularization with Pre-trained Models","created":"2022-03-21","cited_by_count":133},{"id":"2109.06165","title":"CDTrans: Cross-domain Transformer for Unsupervised Domain Adaptation","created":"2021-09-13","cited_by_count":129},{"id":"2104.04670","title":"Adapting Language Models for Zero-shot Learning by Meta-tuning on Dataset and Prompt Collections","created":"2021-04-10","cited_by_count":128},{"id":"2202.06687","title":"Domain Adaptation via Prompt Learning","created":"2022-02-14","cited_by_count":128},{"id":"1810.02575","title":"Dark Model Adaptation: Semantic Image Segmentation from Daytime to Nighttime","created":"2018-10-05","cited_by_count":122},{"id":"2303.10353","title":"Sharpness-Aware Gradient Matching for Domain Generalization","created":"2023-03-18","cited_by_count":102},{"id":"2302.00864","title":"CLIPood: Generalizing CLIP to Out-of-Distributions","created":"2023-02-02","cited_by_count":96},{"id":"2206.08213","title":"A Closer Look at Smoothness in Domain Adversarial Training","created":"2022-06-16","cited_by_count":85},{"id":"2303.08566","title":"Sensitivity-Aware Visual Parameter-Efficient Fine-Tuning","created":"2023-03-15","cited_by_count":74},{"id":"2103.15796","title":"Adaptive Methods for Real-World Domain Generalization","created":"2021-03-29","cited_by_count":66},{"id":"2307.15199","title":"PromptStyler: Prompt-driven Style Generation for Source-free Domain Generalization","created":"2023-07-27","cited_by_count":59},{"id":"2303.13434","title":"Patch-Mix Transformer for Unsupervised Domain Adaptation: A Game Perspective","created":"2023-03-23","cited_by_count":54},{"id":"2306.16410","title":"Towards Language Models That Can See: Computer Vision Through the LENS of Natural Language","created":"2023-06-28","cited_by_count":53},{"id":"2106.02266","title":"SAND-mask: An Enhanced Gradient Masking Strategy for the Discovery of Invariances in Domain Generalization","created":"2021-06-04","cited_by_count":50},{"id":"2212.10400","title":"Contrastive Learning Reduces Hallucination in Conversations","created":"2022-12-20","cited_by_count":40},{"id":"2308.07758","title":"Forward-Backward Reasoning in Large Language Models for Mathematical Verification","created":"2023-08-15","cited_by_count":40},{"id":"2111.12853","title":"Domain Prompt Learning for Efficiently Adapting CLIP to Unseen Domains","created":"2021-11-25","cited_by_count":39},{"id":"2302.00194","title":"Free Lunch for Domain Adversarial Training: Environment Label Smoothing","created":"2023-02-01","cited_by_count":33},{"id":"2206.06315","title":"JiuZhang: A Chinese Pre-trained Language Model for Mathematical Problem Understanding","created":"2022-06-13","cited_by_count":15},{"id":"2304.05552","title":"DynamicDet: A Unified Dynamic Architecture for Object Detection","created":"2023-04-12","cited_by_count":15},{"id":"2306.00618","title":"Effective Structured Prompting by Meta-Learning and Representative Verbalizer","created":"2023-06-01","cited_by_count":14},{"id":"2310.03328","title":"Reformulating Domain Adaptation of Large Language Models as Adapt-Retrieve-Revise: A Case Study on Chinese Legal Domain","created":"2023-10-05","cited_by_count":12},{"id":"2309.14360","title":"Domain-Guided Conditional Diffusion Model for Unsupervised Domain Adaptation","created":"2023-09-23","cited_by_count":9},{"id":"2304.11597","title":"Learning Partial Correlation based Deep Visual Representation for Image Classification","created":"2023-04-23","cited_by_count":6}],"next_cursor":null}