{"list":"other","total":60,"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":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"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":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"2204.06125","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","created":"2022-04-13","cited_by_count":6585},{"id":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"id":"2102.12092","title":"Zero-Shot Text-to-Image Generation","created":"2021-02-24","cited_by_count":4288},{"id":"1902.00751","title":"Parameter-Efficient Transfer Learning for NLP","created":"2019-02-02","cited_by_count":4236},{"id":"2106.10199","title":"BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-models","created":"2021-06-18","cited_by_count":1245},{"id":"1808.09781","title":"Self-Attentive Sequential Recommendation","created":"2018-08-20","cited_by_count":1184},{"id":"2002.02126","title":"LightGCN: Simplifying and Powering Graph Convolution Network for Recommendation","created":"2020-02-06","cited_by_count":1139},{"id":"1708.05031","title":"Neural Collaborative Filtering","created":"2017-08-16","cited_by_count":1111},{"id":"2106.04560","title":"Scaling Vision Transformers","created":"2021-06-08","cited_by_count":999},{"id":"1904.06690","title":"BERT4Rec: Sequential Recommendation with Bidirectional Encoder Representations from Transformer","created":"2019-04-14","cited_by_count":964},{"id":"2209.06794","title":"PaLI: A Jointly-Scaled Multilingual Language-Image Model","created":"2022-09-14","cited_by_count":766},{"id":"1511.06939","title":"Session-based Recommendations with Recurrent Neural Networks","created":"2015-11-21","cited_by_count":695},{"id":"2302.05442","title":"Scaling Vision Transformers to 22 Billion Parameters","created":"2023-02-10","cited_by_count":694},{"id":"1703.04247","title":"DeepFM: A Factorization-Machine based Neural Network for CTR Prediction","created":"2017-03-13","cited_by_count":676},{"id":"2106.04647","title":"Compacter: Efficient Low-Rank Hypercomplex Adapter Layers","created":"2021-06-08","cited_by_count":460},{"id":"1909.11556","title":"Reducing Transformer Depth on Demand with Structured Dropout","created":"2019-09-25","cited_by_count":439},{"id":"2111.03930","title":"Tip-Adapter: Training-free CLIP-Adapter for Better Vision-Language Modeling","created":"2021-11-06","cited_by_count":431},{"id":"2305.00447","title":"TALLRec: An Effective and Efficient Tuning Framework to Align Large Language Model with Recommendation","created":"2023-04-30","cited_by_count":337},{"id":"2002.01808","title":"K-Adapter: Infusing Knowledge into Pre-Trained Models with Adapters","created":"2020-02-05","cited_by_count":319},{"id":"2302.12242","title":"Side Adapter Network for Open-Vocabulary Semantic Segmentation","created":"2023-02-23","cited_by_count":300},{"id":"2206.06522","title":"LST: Ladder Side-Tuning for Parameter and Memory Efficient Transfer Learning","created":"2022-06-13","cited_by_count":230},{"id":"2307.05222","title":"Emu: Generative Pretraining in Multimodality","created":"2023-07-11","cited_by_count":157},{"id":"2205.08084","title":"M6-Rec: Generative Pretrained Language Models are Open-Ended Recommender Systems","created":"2022-05-17","cited_by_count":152},{"id":"2303.13835","title":"Where to Go Next for Recommender Systems? ID- vs. Modality-based Recommender Models Revisited","created":"2023-03-24","cited_by_count":124},{"id":"2206.05941","title":"Towards Universal Sequence Representation Learning for Recommender Systems","created":"2022-06-13","cited_by_count":121},{"id":"2110.14378","title":"Towards artificial general intelligence via a multimodal foundation model","created":"2021-10-27","cited_by_count":112},{"id":"2210.12316","title":"Learning Vector-Quantized Item Representation for Transferable Sequential Recommenders","created":"2022-10-22","cited_by_count":112},{"id":"2212.07983","title":"Vision Transformers are Parameter-Efficient Audio-Visual Learners","created":"2022-12-15","cited_by_count":72},{"id":"2111.02036","title":"GRCN: Graph-Refined Convolutional Network for Multimedia Recommendation with Implicit Feedback","created":"2021-11-03","cited_by_count":58},{"id":"2305.06566","title":"ONCE: Boosting Content-based Recommendation with Both Open- and Closed-source Large Language Models","created":"2023-05-11","cited_by_count":54},{"id":"2402.05391","title":"Knowledge Graphs Meet Multi-Modal Learning: A Comprehensive Survey","created":"2024-02-08","cited_by_count":53},{"id":"2305.14302","title":"VIP5: Towards Multimodal Foundation Models for Recommendation","created":"2023-05-23","cited_by_count":46},{"id":"2309.15379","title":"A Content-Driven Micro-Video Recommendation Dataset at Scale","created":"2023-09-27","cited_by_count":45},{"id":"2305.11700","title":"Exploring the Upper Limits of Text-Based Collaborative Filtering Using Large Language Models: Discoveries and Insights","created":"2023-05-19","cited_by_count":38},{"id":"2305.15036","title":"Exploring Adapter-based Transfer Learning for Recommender Systems: Empirical Studies and Practical Insights","created":"2023-05-24","cited_by_count":29},{"id":"2206.06190","title":"TransRec: Learning Transferable Recommendation from Mixture-of-Modality Feedback","created":"2022-06-13","cited_by_count":27},{"id":"2402.18490","title":"TAMM: TriAdapter Multi-Modal Learning for 3D Shape Understanding","created":"2024-02-28","cited_by_count":27},{"id":"2108.07686","title":"Scaling Laws for Deep Learning","created":"2021-08-17","cited_by_count":26},{"id":"2404.02059","title":"IISAN: Efficiently Adapting Multimodal Representation for Sequential Recommendation with Decoupled PEFT","created":"2024-04-02","cited_by_count":26},{"id":"2404.00621","title":"Multimodal Pretraining, Adaptation, and Generation for Recommendation: A Survey","created":"2024-03-31","cited_by_count":25},{"id":"2309.07705","title":"NineRec: A Benchmark Dataset Suite for Evaluating Transferable Recommendation","created":"2023-09-14","cited_by_count":21},{"id":"2309.06789","title":"An Image Dataset for Benchmarking Recommender Systems with Raw Pixels","created":"2023-09-13","cited_by_count":18},{"id":"2308.04067","title":"Online Distillation-enhanced Multi-modal Transformer for Sequential Recommendation","created":"2023-08-08","cited_by_count":10},{"id":"2312.09602","title":"Multi-Modality is All You Need for Transferable Recommender Systems","created":"2023-12-15","cited_by_count":9},{"id":"2402.15276","title":"CFIR: Fast and Effective Long-Text To Image Retrieval for Large Corpora","created":"2024-02-23","cited_by_count":8},{"id":"2404.17273","title":"3SHNet: Boosting Image-Sentence Retrieval via Visual Semantic-Spatial Self-Highlighting","created":"2024-04-26","cited_by_count":6},{"id":"2205.02923","title":"End-to-End Image-Based Fashion Recommendation","created":"2022-05-05","cited_by_count":5},{"id":"2206.02323","title":"ID-Agnostic User Behavior Pre-training for Sequential Recommendation","created":"2022-06-06","cited_by_count":5},{"id":"2310.01612","title":"Towards Efficient and Effective Adaptation of Large Language Models for Sequential Recommendation","created":"2023-10-02","cited_by_count":4},{"id":"2403.17372","title":"An Empirical Study of Training ID-Agnostic Multi-modal Sequential Recommenders","created":"2024-03-26","cited_by_count":1}],"next_cursor":null}