{"list":"other","total":68,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"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":"1609.02907","title":"Semi-Supervised Classification with Graph Convolutional Networks","created":"2016-09-09","cited_by_count":11361},{"id":"2110.14168","title":"Training Verifiers to Solve Math Word Problems","created":"2021-10-27","cited_by_count":10109},{"id":"1902.00751","title":"Parameter-Efficient Transfer Learning for NLP","created":"2019-02-02","cited_by_count":4236},{"id":"2101.00190","title":"Prefix-Tuning: Optimizing Continuous Prompts for Generation","created":"2021-01-01","cited_by_count":3915},{"id":"2104.08691","title":"The Power of Scale for Parameter-Efficient Prompt Tuning","created":"2021-04-18","cited_by_count":3795},{"id":"2305.14314","title":"QLoRA: Efficient Finetuning of Quantized LLMs","created":"2023-05-23","cited_by_count":3418},{"id":"1508.07909","title":"Neural Machine Translation of Rare Words with Subword Units","created":"2015-08-31","cited_by_count":2918},{"id":"1910.02054","title":"ZeRO: Memory Optimizations Toward Training Trillion Parameter Models","created":"2019-10-04","cited_by_count":1301},{"id":"2303.17580","title":"HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face","created":"2023-03-30","cited_by_count":1190},{"id":"1611.08097","title":"Geometric deep learning: going beyond Euclidean data","created":"2016-11-24","cited_by_count":1048},{"id":"2403.08295","title":"Gemma: Open Models Based on Gemini Research and Technology","created":"2024-03-13","cited_by_count":916},{"id":"2103.07191","title":"Are NLP Models really able to Solve Simple Math Word Problems?","created":"2021-03-12","cited_by_count":878},{"id":"2110.04366","title":"Towards a Unified View of Parameter-Efficient Transfer Learning","created":"2021-10-08","cited_by_count":872},{"id":"2402.09353","title":"DoRA: Weight-Decomposed Low-Rank Adaptation","created":"2024-02-14","cited_by_count":758},{"id":"1705.08039","title":"Poincar\\'e Embeddings for Learning Hierarchical Representations","created":"2017-05-22","cited_by_count":684},{"id":"2012.13255","title":"Intrinsic Dimensionality Explains the Effectiveness of Language Model Fine-Tuning","created":"2020-12-22","cited_by_count":671},{"id":"1705.04146","title":"Program Induction by Rationale Generation : Learning to Solve and Explain Algebraic Word Problems","created":"2017-05-11","cited_by_count":650},{"id":"2302.06476","title":"Is ChatGPT a General-Purpose Natural Language Processing Task Solver?","created":"2023-02-08","cited_by_count":488},{"id":"1805.09112","title":"Hyperbolic Neural Networks","created":"2018-05-23","cited_by_count":402},{"id":"1910.12933","title":"Hyperbolic Graph Convolutional Neural Networks","created":"2019-10-28","cited_by_count":402},{"id":"2402.12354","title":"LoRA+: Efficient Low Rank Adaptation of Large Models","created":"2024-02-19","cited_by_count":377},{"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":"1806.03417","title":"Learning Continuous Hierarchies in the Lorentz Model of Hyperbolic Geometry","created":"2018-06-09","cited_by_count":265},{"id":"1907.12009","title":"Representation Degeneration Problem in Training Natural Language Generation Models","created":"2019-07-28","cited_by_count":255},{"id":"1910.12892","title":"Hyperbolic Graph Neural Networks","created":"2019-10-28","cited_by_count":244},{"id":"1904.02239","title":"Hyperbolic Image Embeddings","created":"2019-04-03","cited_by_count":221},{"id":"1906.02715","title":"Visualizing and Measuring the Geometry of BERT","created":"2019-06-06","cited_by_count":216},{"id":"2310.08659","title":"LoftQ: LoRA-Fine-Tuning-Aware Quantization for Large Language Models","created":"2023-10-12","cited_by_count":196},{"id":"1810.00760","title":"Riemannian Adaptive Optimization Methods","created":"2018-10-01","cited_by_count":194},{"id":"1804.01882","title":"Hyperbolic Entailment Cones for Learning Hierarchical Embeddings","created":"2018-04-03","cited_by_count":162},{"id":"2309.14717","title":"QA-LoRA: Quantization-Aware Low-Rank Adaptation of Large Language Models","created":"2023-09-26","cited_by_count":155},{"id":"2101.04562","title":"Hyperbolic Deep Neural Networks: A Survey","created":"2021-01-12","cited_by_count":139},{"id":"2304.09172","title":"Hyperbolic Image-Text Representations","created":"2023-04-18","cited_by_count":136},{"id":"2212.10650","title":"KronA: Parameter Efficient Tuning with Kronecker Adapter","created":"2022-12-20","cited_by_count":133},{"id":"1805.09786","title":"Hyperbolic Attention Networks","created":"2018-05-24","cited_by_count":122},{"id":"2005.02819","title":"Geoopt: Riemannian Optimization in PyTorch","created":"2020-05-06","cited_by_count":114},{"id":"1911.05076","title":"Constant Curvature Graph Convolutional Networks","created":"2019-11-12","cited_by_count":108},{"id":"2105.14686","title":"Fully Hyperbolic Neural Networks","created":"2021-05-31","cited_by_count":108},{"id":"1911.08411","title":"Mixed-curvature Variational Autoencoders","created":"2019-11-19","cited_by_count":86},{"id":"2305.06611","title":"Hyperbolic Deep Learning in Computer Vision: A Survey","created":"2023-05-11","cited_by_count":73},{"id":"1912.03046","title":"Hyperbolic Graph Attention Network","created":"2019-12-06","cited_by_count":70},{"id":"2107.03767","title":"Discrete-time Temporal Network Embedding via Implicit Hierarchical Learning in Hyperbolic Space","created":"2021-07-08","cited_by_count":67},{"id":"2310.00035","title":"LoRA ensembles for large language model fine-tuning","created":"2023-09-29","cited_by_count":67},{"id":"2205.11380","title":"Outliers Dimensions that Disrupt Transformers Are Driven by Frequency","created":"2022-05-23","cited_by_count":55},{"id":"2104.06942","title":"A Hyperbolic-to-Hyperbolic Graph Convolutional Network","created":"2021-04-14","cited_by_count":53},{"id":"2108.07344","title":"IsoScore: Measuring the Uniformity of Embedding Space Utilization","created":"2021-08-16","cited_by_count":53},{"id":"2211.00181","title":"The Numerical Stability of Hyperbolic Representation Learning","created":"2022-10-31","cited_by_count":47},{"id":"2407.01290","title":"Hypformer: Exploring Efficient Transformer Fully in Hyperbolic Space","created":"2024-07-01","cited_by_count":43},{"id":"2104.08154","title":"Counter-Interference Adapter for Multilingual Machine Translation","created":"2021-04-16","cited_by_count":40},{"id":"2202.13852","title":"Hyperbolic Graph Neural Networks: A Review of Methods and Applications","created":"2022-02-28","cited_by_count":40},{"id":"2104.01257","title":"Unsupervised Discovery of the Long-Tail in Instance Segmentation Using Hierarchical Self-Supervision","created":"2021-04-02","cited_by_count":39},{"id":"2204.08176","title":"HRCF: Enhancing Collaborative Filtering via Hyperbolic Geometric Regularization","created":"2022-04-18","cited_by_count":34},{"id":"1407.5965","title":"Optimization Techniques on Riemannian Manifolds","created":"2014-07-22","cited_by_count":27},{"id":"2110.07867","title":"Exploring Universal Intrinsic Task Subspace via Prompt Tuning","created":"2021-10-15","cited_by_count":25},{"id":"2210.01542","title":"Hyperbolic Deep Reinforcement Learning","created":"2022-10-04","cited_by_count":25},{"id":"2303.14027","title":"Poincar\\'e ResNet","created":"2023-03-24","cited_by_count":25},{"id":"2207.09051","title":"HICF: Hyperbolic Informative Collaborative Filtering","created":"2022-07-19","cited_by_count":24},{"id":"2405.03188","title":"Hyperbolic Geometric Latent Diffusion Model for Graph Generation","created":"2024-05-06","cited_by_count":20},{"id":"2402.17263","title":"MELoRA: Mini-Ensemble Low-Rank Adapters for Parameter-Efficient Fine-Tuning","created":"2024-02-27","cited_by_count":19},{"id":"2309.04082","title":"Curve Your Attention: Mixed-Curvature Transformers for Graph Representation Learning","created":"2023-09-08","cited_by_count":15},{"id":"2212.01793","title":"kHGCN: Tree-likeness Modeling via Continuous and Discrete Curvature Learning","created":"2022-12-04","cited_by_count":14},{"id":"2105.10475","title":"Generalization Error Bound for Hyperbolic Ordinal Embedding","created":"2021-05-21","cited_by_count":12},{"id":"1503.03061","title":"Hyperbolicity Measures \"Democracy\" in Real-World Networks","created":"2015-03-10","cited_by_count":4},{"id":"1307.0031","title":"On the Hyperbolicity of Large-Scale Networks","created":"2013-06-28","cited_by_count":3}],"next_cursor":null}