{"list":"other","total":57,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"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":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"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":"2306.05685","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","created":"2023-06-09","cited_by_count":8626},{"id":"1807.03748","title":"Representation Learning with Contrastive Predictive Coding","created":"2018-07-10","cited_by_count":7777},{"id":"1904.09675","title":"BERTScore: Evaluating Text Generation with BERT","created":"2019-04-21","cited_by_count":5512},{"id":"2305.14314","title":"QLoRA: Efficient Finetuning of Quantized LLMs","created":"2023-05-23","cited_by_count":3418},{"id":"2304.10592","title":"MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models","created":"2023-04-20","cited_by_count":2711},{"id":"2306.02858","title":"Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding","created":"2023-06-05","cited_by_count":1471},{"id":"1906.05849","title":"Contrastive Multiview Coding","created":"2019-06-13","cited_by_count":1301},{"id":"2201.08239","title":"LaMDA: Language Models for Dialog Applications","created":"2022-01-20","cited_by_count":1220},{"id":"2303.16199","title":"LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention","created":"2023-03-28","cited_by_count":781},{"id":"2104.01778","title":"AST: Audio Spectrogram Transformer","created":"2021-04-05","cited_by_count":643},{"id":"2304.15010","title":"LLaMA-Adapter V2: Parameter-Efficient Visual Instruction Model","created":"2023-04-28","cited_by_count":602},{"id":"2106.13043","title":"AudioCLIP: Extending CLIP to Image, Text and Audio","created":"2021-06-24","cited_by_count":339},{"id":"1609.08675","title":"YouTube-8M: A Large-Scale Video Classification Benchmark","created":"2016-09-27","cited_by_count":324},{"id":"2305.08845","title":"Large Language Models are Zero-Shot Rankers for Recommender Systems","created":"2023-05-15","cited_by_count":309},{"id":"2303.14524","title":"Chat-REC: Towards Interactive and Explainable LLMs-Augmented Recommender System","created":"2023-03-25","cited_by_count":242},{"id":"2110.11499","title":"Wav2CLIP: Learning Robust Audio Representations From CLIP","created":"2021-10-21","cited_by_count":213},{"id":"2004.00646","title":"A Survey on Conversational Recommender Systems","created":"2020-04-01","cited_by_count":143},{"id":"2101.09459","title":"Advances and Challenges in Conversational Recommender Systems: A Survey","created":"2021-01-23","cited_by_count":118},{"id":"2302.07257","title":"ChatCAD: Interactive Computer-Aided Diagnosis on Medical Image using Large Language Models","created":"2023-02-14","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":"2109.04425","title":"Talk-to-Edit: Fine-Grained Facial Editing via Dialog","created":"2021-09-09","cited_by_count":102},{"id":"2208.12415","title":"MuLan: A Joint Embedding of Music Audio and Natural Language","created":"2022-08-26","cited_by_count":87},{"id":"2212.07983","title":"Vision Transformers are Parameter-Efficient Audio-Visual Learners","created":"2022-12-15","cited_by_count":72},{"id":"2305.07961","title":"Leveraging Large Language Models in Conversational Recommender Systems","created":"2023-05-13","cited_by_count":63},{"id":"1909.06654","title":"musicnn: Pre-trained convolutional neural networks for music audio tagging","created":"2019-09-14","cited_by_count":50},{"id":"2305.13112","title":"Rethinking the Evaluation for Conversational Recommendation in the Era of Large Language Models","created":"2023-05-22","cited_by_count":48},{"id":"2006.00751","title":"Evaluation of CNN-based Automatic Music Tagging Models","created":"2020-06-01","cited_by_count":41},{"id":"1606.00298","title":"Automatic tagging using deep convolutional neural networks","created":"2016-06-01","cited_by_count":40},{"id":"2305.15964","title":"ChatCAD+: Towards a Universal and Reliable Interactive CAD using LLMs","created":"2023-05-25","cited_by_count":35},{"id":"2112.01589","title":"InfoLM: A New Metric to Evaluate Summarization & Data2Text Generation","created":"2021-12-02","cited_by_count":33},{"id":"2208.12208","title":"Contrastive Audio-Language Learning for Music","created":"2022-08-25","cited_by_count":33},{"id":"2204.06923","title":"A Unified Multi-task Learning Framework for Multi-goal Conversational Recommender Systems","created":"2022-04-14","cited_by_count":32},{"id":"1703.01789","title":"Sample-level Deep Convolutional Neural Networks for Music Auto-tagging Using Raw Waveforms","created":"2017-03-06","cited_by_count":27},{"id":"2112.08140","title":"Improving Conversational Recommendation Systems' Quality with Context-Aware Item Meta Information","created":"2021-12-15","cited_by_count":26},{"id":"2111.13457","title":"Semi-Supervised Music Tagging Transformer","created":"2021-11-26","cited_by_count":25},{"id":"2206.07148","title":"It's Time for Artistic Correspondence in Music and Video","created":"2022-06-14","cited_by_count":18},{"id":"2211.14558","title":"Toward Universal Text-to-Music Retrieval","created":"2022-11-26","cited_by_count":18},{"id":"2304.10691","title":"SkinGPT-4: An Interactive Dermatology Diagnostic System with Visual Large Language Model","created":"2023-04-21","cited_by_count":18},{"id":"2306.09327","title":"Language-Guided Music Recommendation for Video via Prompt Analogies","created":"2023-06-15","cited_by_count":18},{"id":"1908.03744","title":"Audio-Visual Embedding for Cross-Modal MusicVideo Retrieval through Supervised Deep CCA","created":"2019-08-10","cited_by_count":16},{"id":"2008.03720","title":"Disentangled Multidimensional Metric Learning for Music Similarity","created":"2020-08-09","cited_by_count":16},{"id":"1907.02670","title":"Zero-shot Learning for Audio-based Music Classification and Tagging","created":"2019-07-05","cited_by_count":13},{"id":"2303.11108","title":"CHATEDIT: Towards Multi-turn Interactive Facial Image Editing via Dialogue","created":"2023-03-20","cited_by_count":12},{"id":"2104.14799","title":"Cross-Modal Music-Video Recommendation: A Study of Design Choices","created":"2021-04-30","cited_by_count":11},{"id":"2107.07268","title":"Cross-modal Variational Auto-encoder for Content-based Micro-video Background Music Recommendation","created":"2021-07-15","cited_by_count":10},{"id":"2202.10139","title":"S3T: Self-Supervised Pre-training with Swin Transformer for Music Classification","created":"2022-02-21","cited_by_count":8},{"id":"1707.04916","title":"Multi-label Music Genre Classification from Audio, Text, and Images Using Deep Features","created":"2017-07-16","cited_by_count":7},{"id":"1606.02627","title":"Brains on Beats","created":"2016-06-08","cited_by_count":4}],"next_cursor":null}