{"list":"other","total":52,"rows":[{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"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":"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":"1902.00751","title":"Parameter-Efficient Transfer Learning for NLP","created":"2019-02-02","cited_by_count":4236},{"id":"2305.14314","title":"QLoRA: Efficient Finetuning of Quantized LLMs","created":"2023-05-23","cited_by_count":3418},{"id":"2006.03654","title":"DeBERTa: Decoding-enhanced BERT with Disentangled Attention","created":"2020-06-05","cited_by_count":2181},{"id":"2111.09543","title":"DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing","created":"2021-11-18","cited_by_count":1254},{"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":"1708.05031","title":"Neural Collaborative Filtering","created":"2017-08-16","cited_by_count":1111},{"id":"1904.06690","title":"BERT4Rec: Sequential Recommendation with Bidirectional Encoder Representations from Transformer","created":"2019-04-14","cited_by_count":964},{"id":"1511.06939","title":"Session-based Recommendations with Recurrent Neural Networks","created":"2015-11-21","cited_by_count":695},{"id":"2304.15010","title":"LLaMA-Adapter V2: Parameter-Efficient Visual Instruction Model","created":"2023-04-28","cited_by_count":602},{"id":"2205.08534","title":"Vision Transformer Adapter for Dense Predictions","created":"2022-05-17","cited_by_count":565},{"id":"2106.04647","title":"Compacter: Efficient Low-Rank Hypercomplex Adapter Layers","created":"2021-06-08","cited_by_count":460},{"id":"2007.07779","title":"AdapterHub: A Framework for Adapting Transformers","created":"2020-07-15","cited_by_count":444},{"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":"2205.08084","title":"M6-Rec: Generative Pretrained Language Models are Open-Ended Recommender Systems","created":"2022-05-17","cited_by_count":152},{"id":"2101.06983","title":"Scaling Deep Contrastive Learning Batch Size under Memory Limited Setup","created":"2021-01-18","cited_by_count":127},{"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":"2212.07983","title":"Vision Transformers are Parameter-Efficient Audio-Visual Learners","created":"2022-12-15","cited_by_count":72},{"id":"2104.07413","title":"Empowering News Recommendation with Pre-trained Language Models","created":"2021-04-15","cited_by_count":63},{"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":"2305.14302","title":"VIP5: Towards Multimodal Foundation Models for Recommendation","created":"2023-05-23","cited_by_count":46},{"id":"2302.10632","title":"Multi-Modal Self-Supervised Learning for Recommendation","created":"2023-02-21","cited_by_count":45},{"id":"2309.15379","title":"A Content-Driven Micro-Video Recommendation Dataset at Scale","created":"2023-09-27","cited_by_count":45},{"id":"2308.11175","title":"MISSRec: Pre-training and Transferring Multi-modal Interest-aware Sequence Representation for Recommendation","created":"2023-08-22","cited_by_count":31},{"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":"2108.02417","title":"Structured Multi-modal Feature Embedding and Alignment for Image-Sentence Retrieval","created":"2021-08-05","cited_by_count":23},{"id":"2309.06789","title":"An Image Dataset for Benchmarking Recommender Systems with Raw Pixels","created":"2023-09-13","cited_by_count":18},{"id":"2005.11724","title":"Learning to Transfer Graph Embeddings for Inductive Graph based Recommendation","created":"2020-05-24","cited_by_count":14},{"id":"2210.08908","title":"Cross-modal Semantic Enhanced Interaction for Image-Sentence Retrieval","created":"2022-10-17","cited_by_count":14},{"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":"2308.09970","title":"Tackling Vision Language Tasks Through Learning Inner Monologues","created":"2023-08-19","cited_by_count":7},{"id":"2012.02792","title":"Weight Update Skipping: Reducing Training Time for Artificial Neural Networks","created":"2020-12-05","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":"2310.13540","title":"Thoroughly Modeling Multi-domain Pre-trained Recommendation as Language","created":"2023-10-20","cited_by_count":3},{"id":"2311.05956","title":"ID Embedding as Subtle Features of Content and Structure for Multimodal Recommendation","created":"2023-11-10","cited_by_count":3},{"id":"2401.07257","title":"Lightweight Modality Adaptation to Sequential Recommendation via Correlation Supervision","created":"2024-01-14","cited_by_count":1}],"next_cursor":null}