{"list":"other","total":93,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"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":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"2501.12948","title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","created":"2025-01-22","cited_by_count":6330},{"id":"2203.00667","title":"Generative Adversarial Networks","created":"2022-03-01","cited_by_count":5627},{"id":"2104.08691","title":"The Power of Scale for Parameter-Efficient Prompt Tuning","created":"2021-04-18","cited_by_count":3795},{"id":"1808.06226","title":"SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing","created":"2018-08-19","cited_by_count":1989},{"id":"1812.05905","title":"Soft Actor-Critic Algorithms and Applications","created":"2018-12-13","cited_by_count":1240},{"id":"1711.02257","title":"GradNorm: Gradient Normalization for Adaptive Loss Balancing in Deep Multitask Networks","created":"2017-11-07","cited_by_count":834},{"id":"1807.02811","title":"A Tutorial on Bayesian Optimization","created":"2018-07-08","cited_by_count":744},{"id":"2208.01066","title":"What Can Transformers Learn In-Context? A Case Study of Simple Function Classes","created":"2022-08-01","cited_by_count":715},{"id":"1807.01613","title":"Conditional Neural Processes","created":"2018-07-04","cited_by_count":426},{"id":"1604.00772","title":"The CMA Evolution Strategy: A Tutorial","created":"2016-04-04","cited_by_count":377},{"id":"2112.10510","title":"Transformers Can Do Bayesian Inference","created":"2021-12-20","cited_by_count":360},{"id":"1801.10198","title":"Generating Wikipedia by Summarizing Long Sequences","created":"2018-01-30","cited_by_count":335},{"id":"2401.02051","title":"Evolution of Heuristics: Towards Efficient Automatic Algorithm Design Using Large Language Model","created":"2024-01-04","cited_by_count":268},{"id":"1905.11604","title":"SGD on Neural Networks Learns Functions of Increasing Complexity","created":"2019-05-28","cited_by_count":204},{"id":"2002.04504","title":"pymoo: Multi-objective Optimization in Python","created":"2020-01-22","cited_by_count":200},{"id":"1801.10578","title":"Evaluating the Robustness of Neural Networks: An Extreme Value Theory Approach","created":"2018-01-31","cited_by_count":182},{"id":"2104.10201","title":"Bayesian Optimization is Superior to Random Search for Machine Learning Hyperparameter Tuning: Analysis of the Black-Box Optimization Challenge 2020","created":"2021-04-20","cited_by_count":148},{"id":"2402.03921","title":"Large Language Models to Enhance Bayesian Optimization","created":"2024-02-06","cited_by_count":135},{"id":"2207.04179","title":"Transformer Neural Processes: Uncertainty-Aware Meta Learning Via Sequence Modeling","created":"2022-07-09","cited_by_count":127},{"id":"1706.01445","title":"Batched Large-scale Bayesian Optimization in High-dimensional Spaces","created":"2017-06-05","cited_by_count":117},{"id":"2501.08603","title":"Monte Carlo Tree Search for Comprehensive Exploration in LLM-Based Automatic Heuristic Design","created":"2025-01-15","cited_by_count":109},{"id":"2405.01147","title":"Why Tabular Foundation Models Should Be a Research Priority","created":"2024-05-02","cited_by_count":106},{"id":"2203.12742","title":"Accelerating Bayesian Optimization for Biological Sequence Design with Denoising Autoencoders","created":"2022-03-23","cited_by_count":102},{"id":"2410.13213","title":"LLMOPT: Learning to Define and Solve General Optimization Problems from Scratch","created":"2024-10-17","cited_by_count":102},{"id":"2202.08450","title":"Design-Bench: Benchmarks for Data-Driven Offline Model-Based Optimization","created":"2022-02-17","cited_by_count":97},{"id":"2107.06882","title":"Conservative Objective Models for Effective Offline Model-Based Optimization","created":"2021-07-14","cited_by_count":88},{"id":"1912.13464","title":"Model Inversion Networks for Model-Based Optimization","created":"2019-12-31","cited_by_count":83},{"id":"2305.13673","title":"Physics of Language Models: Part 1, Learning Hierarchical Language Structures","created":"2023-05-23","cited_by_count":83},{"id":"2205.13320","title":"Towards Learning Universal Hyperparameter Optimizers with Transformers","created":"2022-05-26","cited_by_count":81},{"id":"2306.07180","title":"Diffusion Models for Black-Box Optimization","created":"2023-06-12","cited_by_count":76},{"id":"2305.17535","title":"PFNs4BO: In-Context Learning for Bayesian Optimization","created":"2023-05-27","cited_by_count":73},{"id":"1909.11639","title":"ROBEL: Robotics Benchmarks for Learning with Low-Cost Robots","created":"2019-09-25","cited_by_count":72},{"id":"2009.12867","title":"An Easy-to-use Real-world Multi-objective Optimization Problem Suite","created":"2020-09-27","cited_by_count":71},{"id":"2101.07667","title":"Few-Shot Bayesian Optimization with Deep Kernel Surrogates","created":"2021-01-19","cited_by_count":71},{"id":"2204.11051","title":"$\\pi$BO: Augmenting Acquisition Functions with User Beliefs for Bayesian Optimization","created":"2022-04-23","cited_by_count":70},{"id":"2410.14716","title":"A Systematic Survey on Large Language Models for Algorithm Design","created":"2024-10-11","cited_by_count":69},{"id":"2109.08215","title":"Pre-trained Gaussian Processes for Bayesian Optimization","created":"2021-09-16","cited_by_count":63},{"id":"2112.01898","title":"Linear algebra with transformers","created":"2021-12-03","cited_by_count":63},{"id":"2409.16867","title":"Multi-objective Evolution of Heuristic Using Large Language Model","created":"2024-09-25","cited_by_count":54},{"id":"2006.08052","title":"Autofocused oracles for model-based design","created":"2020-06-14","cited_by_count":50},{"id":"2403.01131","title":"LLaMoCo: Instruction Tuning of Large Language Models for Optimization Code Generation","created":"2024-03-02","cited_by_count":45},{"id":"2212.04180","title":"evosax: JAX-based Evolution Strategies","created":"2022-12-08","cited_by_count":41},{"id":"2110.14188","title":"RoMA: Robust Model Adaptation for Offline Model-based Optimization","created":"2021-10-27","cited_by_count":39},{"id":"2102.07970","title":"Offline Model-Based Optimization via Normalized Maximum Likelihood Estimation","created":"2021-02-16","cited_by_count":38},{"id":"2206.10786","title":"Generative Pretraining for Black-Box Optimization","created":"2022-06-22","cited_by_count":36},{"id":"2209.07507","title":"Bidirectional Learning for Offline Infinite-width Model-based Optimization","created":"2022-09-15","cited_by_count":35},{"id":"2402.18012","title":"Diffusion Models as Constrained Samplers for Optimization with Unknown Constraints","created":"2024-02-28","cited_by_count":35},{"id":"1310.6740","title":"Active Learning of Linear Embeddings for Gaussian Processes","created":"2013-10-24","cited_by_count":34},{"id":"2203.06801","title":"MetaBalance: Improving Multi-Task Recommendations via Adapting Gradient Magnitudes of Auxiliary Tasks","created":"2022-03-14","cited_by_count":34},{"id":"2402.14547","title":"OmniPred: Language Models as Universal Regressors","created":"2024-02-22","cited_by_count":34},{"id":"2412.17287","title":"LLM4AD: A Platform for Algorithm Design with Large Language Model","created":"2024-12-23","cited_by_count":33},{"id":"2305.15930","title":"End-to-End Meta-Bayesian Optimisation with Transformer Neural Processes","created":"2023-05-25","cited_by_count":32},{"id":"2211.11349","title":"Data-Driven Offline Decision-Making via Invariant Representation Learning","created":"2022-11-21","cited_by_count":31},{"id":"2110.11346","title":"Data-Driven Offline Optimization For Architecting Hardware Accelerators","created":"2021-10-20","cited_by_count":29},{"id":"2309.11600","title":"Importance-aware Co-teaching for Offline Model-based Optimization","created":"2023-09-20","cited_by_count":28},{"id":"2302.05927","title":"Transfer Learning for Bayesian Optimization: A Survey","created":"2023-02-12","cited_by_count":27},{"id":"2309.11592","title":"Parallel-mentoring for Offline Model-based Optimization","created":"2023-09-20","cited_by_count":26},{"id":"2406.18851","title":"LICO: Large Language Models for In-Context Molecular Optimization","created":"2024-06-27","cited_by_count":26},{"id":"2306.03111","title":"Bootstrapped Training of Score-Conditioned Generator for Offline Design of Biological Sequences","created":"2023-06-05","cited_by_count":23},{"id":"2310.19961","title":"ExPT: Synthetic Pretraining for Few-Shot Experimental Design","created":"2023-10-30","cited_by_count":22},{"id":"2311.14645","title":"A General Framework for User-Guided Bayesian Optimization","created":"2023-11-24","cited_by_count":22},{"id":"2501.01956","title":"Metadata Conditioning Accelerates Language Model Pre-training","created":"2025-01-03","cited_by_count":22},{"id":"2405.03547","title":"Position: Leverage Foundational Models for Black-Box Optimization","created":"2024-05-06","cited_by_count":21},{"id":"2301.02931","title":"Bidirectional Learning for Offline Model-based Biological Sequence Design","created":"2023-01-07","cited_by_count":20},{"id":"2405.05349","title":"Offline Model-Based Optimization via Policy-Guided Gradient Search","created":"2024-05-08","cited_by_count":19},{"id":"2411.14708","title":"Understanding LLM Embeddings for Regression","created":"2024-11-22","cited_by_count":19},{"id":"2310.20258","title":"Advancing Bayesian Optimization via Learning Correlated Latent Space","created":"2023-10-31","cited_by_count":18},{"id":"2407.01624","title":"Guided Trajectory Generation with Diffusion Models for Offline Model-based Optimization","created":"2024-06-29","cited_by_count":15},{"id":"2503.17286","title":"Offline Model-Based Optimization: Comprehensive Review","created":"2025-03-21","cited_by_count":15},{"id":"2402.17423","title":"Reinforced In-Context Black-Box Optimization","created":"2024-02-27","cited_by_count":14},{"id":"2406.03348","title":"Position: A Call to Action for a Human-Centered AutoML Paradigm","created":"2024-06-05","cited_by_count":14},{"id":"2406.03722","title":"Offline Multi-Objective Optimization","created":"2024-06-06","cited_by_count":14},{"id":"2408.11527","title":"The Vizier Gaussian Process Bandit Algorithm","created":"2024-08-21","cited_by_count":14},{"id":"2410.11502","title":"Offline Model-Based Optimization by Learning to Rank","created":"2024-10-15","cited_by_count":13},{"id":"2501.19383","title":"Decoding-based Regression","created":"2025-01-31","cited_by_count":12},{"id":"2401.05442","title":"Functional Graphical Models: Structure Enables Offline Data-Driven Optimization","created":"2024-01-08","cited_by_count":11},{"id":"2402.06532","title":"Generative Adversarial Model-Based Optimization via Source Critic Regularization","created":"2024-02-09","cited_by_count":10},{"id":"2405.13964","title":"Design Editing for Offline Model-based Optimization","created":"2024-05-22","cited_by_count":10},{"id":"2309.16597","title":"Transfer Learning for Bayesian Optimization on Heterogeneous Search Spaces","created":"2023-09-28","cited_by_count":9},{"id":"2405.16730","title":"\"Noisier\" Noise Contrastive Eestimation is (Almost) Maximum Likelihood","created":"2024-05-27","cited_by_count":8},{"id":"2410.10190","title":"Language Model Embeddings Can Be Sufficient for Bayesian Optimization","created":"2024-10-14","cited_by_count":8},{"id":"2412.20375","title":"Scalable Bayesian Optimization via Focalized Sparse Gaussian Processes","created":"2024-12-29","cited_by_count":8},{"id":"2412.07186","title":"Monte Carlo Tree Search based Space Transfer for Black-box Optimization","created":"2024-12-10","cited_by_count":7},{"id":"2503.04181","title":"Boosting Offline Optimizers with Surrogate Sensitivity","created":"2025-03-06","cited_by_count":6},{"id":"2503.04242","title":"Incorporating Surrogate Gradient Norm to Improve Offline Optimization Techniques","created":"2025-03-06","cited_by_count":5},{"id":"2410.13106","title":"Cliqueformer: Model-Based Optimization with Structured Transformers","created":"2024-10-17","cited_by_count":3},{"id":"2210.04971","title":"Multi-step Planning for Automated Hyperparameter Optimization with OptFormer","created":"2022-10-10","cited_by_count":2},{"id":"2010.07517","title":"GTOPX Space Mission Benchmarks","created":"2020-10-15","cited_by_count":1}],"next_cursor":null}