{"list":"other","total":61,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2011.13456","title":"Score-Based Generative Modeling through Stochastic Differential Equations","created":"2020-11-26","cited_by_count":9122},{"id":"2207.12598","title":"Classifier-Free Diffusion Guidance","created":"2022-07-26","cited_by_count":5847},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"id":"1608.03983","title":"SGDR: Stochastic Gradient Descent with Warm Restarts","created":"2016-08-13","cited_by_count":5045},{"id":"2312.00752","title":"Mamba: Linear-Time Sequence Modeling with Selective State Spaces","created":"2023-12-01","cited_by_count":4718},{"id":"2104.09864","title":"RoFormer: Enhanced Transformer with Rotary Position Embedding","created":"2021-04-20","cited_by_count":4703},{"id":"1907.05600","title":"Generative Modeling by Estimating Gradients of the Data Distribution","created":"2019-07-12","cited_by_count":4101},{"id":"2205.14135","title":"FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness","created":"2022-05-27","cited_by_count":3673},{"id":"1606.08415","title":"Gaussian Error Linear Units (GELUs)","created":"2016-06-27","cited_by_count":3502},{"id":"2303.17651","title":"Self-Refine: Iterative Refinement with Self-Feedback","created":"2023-03-30","cited_by_count":3442},{"id":"2310.06825","title":"Mistral 7B","created":"2023-10-10","cited_by_count":3164},{"id":"2307.08691","title":"FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning","created":"2023-07-17","cited_by_count":2598},{"id":"1602.01783","title":"Asynchronous Methods for Deep Reinforcement Learning","created":"2016-02-04","cited_by_count":2258},{"id":"1703.06868","title":"Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization","created":"2017-03-20","cited_by_count":2010},{"id":"2002.05202","title":"GLU Variants Improve Transformer","created":"2020-02-12","cited_by_count":1804},{"id":"1910.07467","title":"Root Mean Square Layer Normalization","created":"2019-10-16","cited_by_count":1480},{"id":"1703.00564","title":"MoleculeNet: A Benchmark for Molecular Machine Learning","created":"2017-03-02","cited_by_count":1051},{"id":"2305.13048","title":"RWKV: Reinventing RNNs for the Transformer Era","created":"2023-05-22","cited_by_count":827},{"id":"2203.17003","title":"Equivariant Diffusion for Molecule Generation in 3D","created":"2022-03-31","cited_by_count":677},{"id":"2304.05376","title":"ChemCrow: Augmenting large-language models with chemistry tools","created":"2023-04-11","cited_by_count":631},{"id":"1511.06349","title":"Generating Sentences from a Continuous Space","created":"2015-11-19","cited_by_count":612},{"id":"2209.14734","title":"DiGress: Discrete Denoising diffusion for graph generation","created":"2022-09-29","cited_by_count":520},{"id":"2302.10866","title":"Hyena Hierarchy: Towards Larger Convolutional Language Models","created":"2023-02-21","cited_by_count":393},{"id":"2001.09382","title":"GraphAF: a Flow-based Autoregressive Model for Molecular Graph Generation","created":"2020-01-26","cited_by_count":305},{"id":"1811.09621","title":"GuacaMol: Benchmarking Models for De Novo Molecular Design","created":"2018-11-22","cited_by_count":297},{"id":"2111.09266","title":"GFlowNet Foundations","created":"2021-11-17","cited_by_count":290},{"id":"2202.02514","title":"Score-based Generative Modeling of Graphs via the System of Stochastic Differential Equations","created":"2022-02-05","cited_by_count":283},{"id":"1811.12823","title":"Molecular Sets (MOSES): A Benchmarking Platform for Molecular Generation Models","created":"2018-11-29","cited_by_count":275},{"id":"2003.00638","title":"Permutation Invariant Graph Generation via Score-Based Generative Modeling","created":"2020-03-02","cited_by_count":270},{"id":"1812.08466","title":"Fr\\'echet Audio Distance: A Metric for Evaluating Music Enhancement Algorithms","created":"2018-12-20","cited_by_count":225},{"id":"1803.09518","title":"Fr\\'echet ChemNet Distance: A metric for generative models for molecules in drug discovery","created":"2018-03-26","cited_by_count":194},{"id":"2305.01140","title":"Geometric Latent Diffusion Models for 3D Molecule Generation","created":"2023-05-02","cited_by_count":186},{"id":"1805.09076","title":"Constrained Graph Variational Autoencoders for Molecule Design","created":"2018-05-23","cited_by_count":185},{"id":"2006.10137","title":"MoFlow: An Invertible Flow Model for Generating Molecular Graphs","created":"2020-06-17","cited_by_count":185},{"id":"2102.01189","title":"GraphDF: A Discrete Flow Model for Molecular Graph Generation","created":"2021-02-01","cited_by_count":180},{"id":"1908.08342","title":"A Generalized Algorithm for Multi-Objective Reinforcement Learning and Policy Adaptation","created":"2019-08-21","cited_by_count":177},{"id":"2206.12411","title":"Sample Efficiency Matters: A Benchmark for Practical Molecular Optimization","created":"2022-06-22","cited_by_count":155},{"id":"2103.10432","title":"MARS: Markov Molecular Sampling for Multi-objective Drug Discovery","created":"2021-03-18","cited_by_count":125},{"id":"2210.12765","title":"Multi-Objective GFlowNets","created":"2022-10-23","cited_by_count":101},{"id":"2206.07632","title":"Exploring Chemical Space with Score-based Out-of-distribution Generation","created":"2022-06-06","cited_by_count":95},{"id":"2306.17806","title":"Stay on topic with Classifier-Free Guidance","created":"2023-06-30","cited_by_count":91},{"id":"2307.08849","title":"Autoregressive Diffusion Model for Graph Generation","created":"2023-07-17","cited_by_count":83},{"id":"2204.00056","title":"SELFIES and the future of molecular string representations","created":"2022-03-31","cited_by_count":76},{"id":"2209.15408","title":"Equivariant Energy-Guided SDE for Inverse Molecular Design","created":"2022-09-30","cited_by_count":73},{"id":"2203.15386","title":"Pareto Set Learning for Neural Multi-objective Combinatorial Optimization","created":"2022-03-29","cited_by_count":56},{"id":"2302.03596","title":"Graph Generation with Diffusion Mixture","created":"2023-02-07","cited_by_count":55},{"id":"2201.09871","title":"On Evaluation Metrics for Graph Generative Models","created":"2022-01-24","cited_by_count":46},{"id":"2011.07457","title":"Molecular Mechanics-Driven Graph Neural Network with Multiplex Graph for Molecular Structures","created":"2020-11-15","cited_by_count":45},{"id":"2401.13858","title":"Graph Diffusion Transformers for Multi-Conditional Molecular Generation","created":"2024-01-24","cited_by_count":45},{"id":"2304.04662","title":"SELFormer: Molecular Representation Learning via SELFIES Language Models","created":"2023-04-10","cited_by_count":40},{"id":"2310.02902","title":"Searching for High-Value Molecules Using Reinforcement Learning and Transformers","created":"2023-10-04","cited_by_count":18},{"id":"2403.15441","title":"Unified Generative Modeling of 3D Molecules via Bayesian Flow Networks","created":"2024-03-17","cited_by_count":18},{"id":"2312.02230","title":"A Simple and Scalable Representation for Graph Generation","created":"2023-12-04","cited_by_count":16},{"id":"2301.01829","title":"t-SMILES: A Scalable Fragment-based Molecular Representation Framework for De Novo Molecule Generation","created":"2023-01-04","cited_by_count":14},{"id":"2210.06032","title":"Modular Flows: Differential Molecular Generation","created":"2022-10-12","cited_by_count":11},{"id":"2208.10718","title":"String-based Molecule Generation via Multi-decoder VAE","created":"2022-08-23","cited_by_count":2}],"next_cursor":null}