{"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":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2010.02502","title":"Denoising Diffusion Implicit Models","created":"2020-10-06","cited_by_count":9781},{"id":"2501.12948","title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","created":"2025-01-22","cited_by_count":6330},{"id":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"id":"2207.12598","title":"Classifier-Free Diffusion Guidance","created":"2022-07-26","cited_by_count":5847},{"id":"2203.00667","title":"Generative Adversarial Networks","created":"2022-03-01","cited_by_count":5627},{"id":"2309.16609","title":"Qwen Technical Report","created":"2023-09-28","cited_by_count":3344},{"id":"2006.04779","title":"Conservative Q-Learning for Offline Reinforcement Learning","created":"2020-06-08","cited_by_count":1809},{"id":"2106.01345","title":"Decision Transformer: Reinforcement Learning via Sequence Modeling","created":"2021-06-02","cited_by_count":1546},{"id":"2004.07219","title":"D4RL: Datasets for Deep Data-Driven Reinforcement Learning","created":"2020-04-15","cited_by_count":1427},{"id":"2110.06169","title":"Offline Reinforcement Learning with Implicit Q-Learning","created":"2021-10-12","cited_by_count":1293},{"id":"1812.02900","title":"Off-Policy Deep Reinforcement Learning without Exploration","created":"2018-12-07","cited_by_count":1241},{"id":"2205.09991","title":"Planning with Diffusion for Flexible Behavior Synthesis","created":"2022-05-20","cited_by_count":1061},{"id":"2407.01392","title":"Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion","created":"2024-07-01","cited_by_count":681},{"id":"2106.02039","title":"Offline Reinforcement Learning as One Big Sequence Modeling Problem","created":"2021-06-03","cited_by_count":644},{"id":"2005.05951","title":"MOReL : Model-Based Offline Reinforcement Learning","created":"2020-05-12","cited_by_count":590},{"id":"2211.15657","title":"Is Conditional Generative Modeling all you need for Decision-Making?","created":"2022-11-28","cited_by_count":516},{"id":"1606.05908","title":"Tutorial on Variational Autoencoders","created":"2016-06-19","cited_by_count":409},{"id":"2404.04057","title":"Score identity Distillation: Exponentially Fast Distillation of Pretrained Diffusion Models for One-Step Generation","created":"2024-04-05","cited_by_count":214},{"id":"2310.13268","title":"DPM-Solver-v3: Improved Diffusion ODE Solver with Empirical Model Statistics","created":"2023-10-20","cited_by_count":161},{"id":"2302.01877","title":"AdaptDiffuser: Diffusion Models as Adaptive Self-evolving Planners","created":"2023-02-03","cited_by_count":149},{"id":"2103.03493","title":"Causal Attention for Vision-Language Tasks","created":"2021-03-05","cited_by_count":111},{"id":"2402.02416","title":"Aligner: Efficient Alignment by Learning to Correct","created":"2024-02-04","cited_by_count":98},{"id":"1701.02490","title":"Real-Time Bidding by Reinforcement Learning in Display Advertising","created":"2017-01-10","cited_by_count":91},{"id":"2302.01687","title":"Better Training of GFlowNets with Local Credit and Incomplete Trajectories","created":"2023-02-03","cited_by_count":85},{"id":"2302.07351","title":"Constrained Decision Transformer for Offline Safe Reinforcement Learning","created":"2023-02-14","cited_by_count":69},{"id":"2305.19923","title":"MetaDiffuser: Diffusion Model as Conditional Planner for Offline Meta-RL","created":"2023-05-31","cited_by_count":68},{"id":"1802.09756","title":"Real-Time Bidding with Multi-Agent Reinforcement Learning in Display Advertising","created":"2018-02-27","cited_by_count":65},{"id":"1802.08365","title":"Budget Constrained Bidding by Model-free Reinforcement Learning in Display Advertising","created":"2018-02-23","cited_by_count":61},{"id":"1703.02091","title":"Optimized Cost per Click in Taobao Display Advertising","created":"2017-02-27","cited_by_count":57},{"id":"2305.03935","title":"Improved Techniques for Maximum Likelihood Estimation for Diffusion ODEs","created":"2023-05-06","cited_by_count":54},{"id":"1610.03013","title":"Display Advertising with Real-Time Bidding (RTB) and Behavioural Targeting","created":"2016-10-07","cited_by_count":42},{"id":"2401.15443","title":"DiffuserLite: Towards Real-time Diffusion Planning","created":"2024-01-27","cited_by_count":42},{"id":"2406.09509","title":"CleanDiffuser: An Easy-to-use Modularized Library for Diffusion Models in Decision Making","created":"2024-06-13","cited_by_count":39},{"id":"1905.10928","title":"Bid Optimization by Multivariable Control in Display Advertising","created":"2019-05-24","cited_by_count":37},{"id":"2310.02054","title":"AlignDiff: Aligning Diverse Human Preferences via Behavior-Customisable Diffusion Model","created":"2023-10-03","cited_by_count":37},{"id":"1803.00259","title":"Deep Reinforcement Learning for Sponsored Search Real-time Bidding","created":"2018-03-01","cited_by_count":34},{"id":"2310.09629","title":"Adaptive Online Replanning with Diffusion Models","created":"2023-10-14","cited_by_count":34},{"id":"2210.07006","title":"Sustainable Online Reinforcement Learning for Auto-bidding","created":"2022-10-13","cited_by_count":29},{"id":"2412.10798","title":"AuctionNet: A Novel Benchmark for Decision-Making in Large-Scale Games","created":"2024-12-14","cited_by_count":28},{"id":"2504.14587","title":"Generative Auto-Bidding with Value-Guided Explorations","created":"2025-04-20","cited_by_count":23},{"id":"2106.06224","title":"A Cooperative-Competitive Multi-Agent Framework for Auto-bidding in Online Advertising","created":"2021-06-11","cited_by_count":22},{"id":"1803.02194","title":"Bidding Machine: Learning to Bid for Directly Optimizing Profits in Display Advertising","created":"2018-03-01","cited_by_count":21},{"id":"1707.06409","title":"Attribution Modeling Increases Efficiency of Bidding in Display Advertising","created":"2017-07-20","cited_by_count":19},{"id":"2107.06650","title":"An Efficient Deep Distribution Network for Bid Shading in First-Price Auctions","created":"2021-07-12","cited_by_count":14},{"id":"1809.02230","title":"Deep Neural Net with Attention for Multi-channel Multi-touch Attribution","created":"2018-09-06","cited_by_count":12},{"id":"2206.05240","title":"ROI-Constrained Bidding via Curriculum-Guided Bayesian Reinforcement Learning","created":"2022-06-10","cited_by_count":12},{"id":"2009.01360","title":"Bid Shading in The Brave New World of First-Price Auctions","created":"2020-09-02","cited_by_count":11},{"id":"1907.12118","title":"AiAds: Automated and Intelligent Advertising System for Sponsored Search","created":"2019-07-28","cited_by_count":10},{"id":"2404.03637","title":"Sequential Recommendation for Optimizing Both Immediate Feedback and Long-term Retention","created":"2024-04-04","cited_by_count":10},{"id":"1808.03737","title":"Learning Multi-touch Conversion Attribution with Dual-attention Mechanisms for Online Advertising","created":"2018-08-11","cited_by_count":9},{"id":"1507.04811","title":"Lift-Based Bidding in Ad Selection","created":"2015-07-17","cited_by_count":8},{"id":"2006.07042","title":"Recurrent Neural Networks for Stochastic Control in Real-Time Bidding","created":"2020-06-12","cited_by_count":6},{"id":"2412.17018","title":"GAS: Generative Auto-bidding with Post-training Search","created":"2024-12-22","cited_by_count":6},{"id":"2501.07212","title":"Future-Conditioned Recommendations with Multi-Objective Controllable Decision Transformer","created":"2025-01-13","cited_by_count":4},{"id":"1708.05565","title":"LADDER: A Human-Level Bidding Agent for Large-Scale Real-Time Online Auctions","created":"2017-08-18","cited_by_count":3},{"id":"2007.04002","title":"Unbiased Lift-based Bidding System","created":"2020-07-08","cited_by_count":3}],"next_cursor":null}