{"list":"other","total":96,"rows":[{"id":"1801.01290","title":"Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor","created":"2018-01-04","cited_by_count":4885},{"id":"2212.04356","title":"Robust Speech Recognition via Large-Scale Weak Supervision","created":"2022-12-06","cited_by_count":4057},{"id":"2006.11477","title":"wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations","created":"2020-06-20","cited_by_count":3905},{"id":"2106.07447","title":"HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units","created":"2021-06-14","cited_by_count":2342},{"id":"2303.17564","title":"BloombergGPT: A Large Language Model for Finance","created":"2023-03-30","cited_by_count":939},{"id":"2202.03555","title":"data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Language","created":"2022-02-07","cited_by_count":727},{"id":"1708.05866","title":"A Brief Survey of Deep Reinforcement Learning","created":"2017-08-19","cited_by_count":483},{"id":"1805.00909","title":"Reinforcement Learning and Control as Probabilistic Inference: Tutorial and Review","created":"2018-05-02","cited_by_count":482},{"id":"2312.02003","title":"A Survey on Large Language Model (LLM) Security and Privacy: The Good, the Bad, and the Ugly","created":"2023-12-04","cited_by_count":387},{"id":"1908.10063","title":"FinBERT: Financial Sentiment Analysis with Pre-trained Language Models","created":"2019-08-27","cited_by_count":385},{"id":"1701.07274","title":"Deep Reinforcement Learning: An Overview","created":"2017-01-25","cited_by_count":333},{"id":"1908.08796","title":"Reinforcement Learning in Healthcare: A Survey","created":"2019-08-22","cited_by_count":310},{"id":"2401.05561","title":"TrustLLM: Trustworthiness in Large Language Models","created":"2024-01-10","cited_by_count":285},{"id":"2306.06031","title":"FinGPT: Open-Source Financial Large Language Models","created":"2023-06-09","cited_by_count":253},{"id":"2405.10369","title":"Reinforcement learning","created":"2024-05-16","cited_by_count":247},{"id":"2111.00364","title":"Sustainable AI: Environmental Implications, Challenges and Opportunities","created":"2021-10-30","cited_by_count":242},{"id":"2311.10723","title":"Large Language Models in Finance: A Survey","created":"2023-09-28","cited_by_count":226},{"id":"2306.05443","title":"PIXIU: A Large Language Model, Instruction Data and Evaluation Benchmark for Finance","created":"2023-06-08","cited_by_count":222},{"id":"2312.05187","title":"Seamless: Multilingual Expressive and Streaming Speech Translation","created":"2023-12-08","cited_by_count":192},{"id":"2409.06666","title":"LLaMA-Omni: Seamless Speech Interaction with Large Language Models","created":"2024-09-10","cited_by_count":173},{"id":"1810.07862","title":"Applications of Deep Reinforcement Learning in Communications and Networking: A Survey","created":"2018-10-18","cited_by_count":167},{"id":"1810.08217","title":"Deep Learning Methods for Reynolds-Averaged Navier-Stokes Simulations of Airfoil Flows","created":"2018-10-18","cited_by_count":150},{"id":"1706.10059","title":"A Deep Reinforcement Learning Framework for the Financial Portfolio Management Problem","created":"2017-06-30","cited_by_count":128},{"id":"2211.00083","title":"WHEN FLUE MEETS FLANG: Benchmarks and Large Pre-trained Language Model for Financial Domain","created":"2022-10-31","cited_by_count":117},{"id":"2407.06567","title":"FinCon: A Synthesized LLM Multi-Agent System with Conceptual Verbal Reinforcement for Enhanced Financial Decision Making","created":"2024-07-09","cited_by_count":113},{"id":"2112.04553","title":"Recent Advances in Reinforcement Learning in Finance","created":"2021-12-08","cited_by_count":110},{"id":"2305.11391","title":"A Survey of Safety and Trustworthiness of Large Language Models through the Lens of Verification and Validation","created":"2023-05-19","cited_by_count":93},{"id":"2305.12002","title":"XuanYuan 2.0: A Large Chinese Financial Chat Model with Hundreds of Billions Parameters","created":"2023-05-19","cited_by_count":92},{"id":"2406.11903","title":"A Survey of Large Language Models for Financial Applications: Progress, Prospects and Challenges","created":"2024-06-15","cited_by_count":90},{"id":"2011.09607","title":"FinRL: A Deep Reinforcement Learning Library for Automated Stock Trading in Quantitative Finance","created":"2020-11-19","cited_by_count":87},{"id":"2309.13064","title":"InvestLM: A Large Language Model for Investment using Financial Domain Instruction Tuning","created":"2023-09-15","cited_by_count":82},{"id":"2107.09051","title":"AI in Finance: Challenges, Techniques and Opportunities","created":"2021-07-20","cited_by_count":81},{"id":"2402.02315","title":"A Survey of Large Language Models in Finance (FinLLMs)","created":"2024-02-04","cited_by_count":79},{"id":"2402.01391","title":"StepCoder: Improve Code Generation with Reinforcement Learning from Compiler Feedback","created":"2024-02-02","cited_by_count":77},{"id":"1911.10107","title":"Deep Reinforcement Learning for Trading","created":"2019-11-22","cited_by_count":73},{"id":"2404.07771","title":"An Overview of Diffusion Models: Applications, Guided Generation, Statistical Rates and Optimization","created":"2024-04-11","cited_by_count":73},{"id":"2306.07303","title":"A Comprehensive Survey on Applications of Transformers for Deep Learning Tasks","created":"2023-06-11","cited_by_count":71},{"id":"1905.03030","title":"Meta-learning of Sequential Strategies","created":"2019-05-08","cited_by_count":70},{"id":"2105.00579","title":"BACKDOORL: Backdoor Attack against Competitive Reinforcement Learning","created":"2021-05-02","cited_by_count":68},{"id":"1908.04127","title":"A review on Deep Reinforcement Learning for Fluid Mechanics","created":"2019-08-12","cited_by_count":66},{"id":"2310.15205","title":"DISC-FinLLM: A Chinese Financial Large Language Model based on Multiple Experts Fine-tuning","created":"2023-10-23","cited_by_count":64},{"id":"2311.07989","title":"Unifying the Perspectives of NLP and Software Engineering: A Survey on Language Models for Code","created":"2023-11-14","cited_by_count":62},{"id":"2001.09684","title":"Challenges and Countermeasures for Adversarial Attacks on Deep Reinforcement Learning","created":"2020-01-27","cited_by_count":61},{"id":"2302.09432","title":"BBT-Fin: Comprehensive Construction of Chinese Financial Domain Pre-trained Language Model, Corpus and Benchmark","created":"2023-02-18","cited_by_count":60},{"id":"2305.10435","title":"Generative Pre-trained Transformer: A Comprehensive Review on Enabling Technologies, Potential Applications, Emerging Challenges, and Future Directions","created":"2023-05-11","cited_by_count":55},{"id":"1905.06494","title":"Data Poisoning Attacks on Stochastic Bandits","created":"2019-05-16","cited_by_count":53},{"id":"1811.07522","title":"Practical Deep Reinforcement Learning Approach for Stock Trading","created":"2018-11-19","cited_by_count":49},{"id":"1804.04216","title":"Market Making via Reinforcement Learning","created":"2018-04-11","cited_by_count":47},{"id":"2107.14569","title":"Can You Hear It? Backdoor Attacks via Ultrasonic Triggers","created":"2021-07-30","cited_by_count":44},{"id":"2202.02526","title":"LyaNet: A Lyapunov Framework for Training Neural ODEs","created":"2022-02-05","cited_by_count":44},{"id":"2407.19487","title":"RLCoder: Reinforcement Learning for Repository-Level Code Completion","created":"2024-07-28","cited_by_count":44},{"id":"1911.05892","title":"Reinforcement Learning for Market Making in a Multi-agent Dealer Market","created":"2019-11-14","cited_by_count":39},{"id":"2406.17216","title":"Machine Unlearning Fails to Remove Data Poisoning Attacks","created":"2024-06-25","cited_by_count":37},{"id":"1612.01277","title":"Cryptocurrency Portfolio Management with Deep Reinforcement Learning","created":"2016-12-05","cited_by_count":32},{"id":"2311.09641","title":"RLHFPoison: Reward Poisoning Attack for Reinforcement Learning with Human Feedback in Large Language Models","created":"2023-11-16","cited_by_count":32},{"id":"1903.06638","title":"TrojDRL: Trojan Attacks on Deep Reinforcement Learning Agents","created":"2019-03-01","cited_by_count":30},{"id":"2103.16409","title":"Deep Hedging of Derivatives Using Reinforcement Learning","created":"2021-03-29","cited_by_count":30},{"id":"2312.12585","title":"BadRL: Sparse Targeted Backdoor Attack Against Reinforcement Learning","created":"2023-12-19","cited_by_count":30},{"id":"2408.12171","title":"Recent Advances on Machine Learning for Computational Fluid Dynamics: A Survey","created":"2024-08-22","cited_by_count":28},{"id":"2205.01086","title":"Wav2Seq: Pre-training Speech-to-Text Encoder-Decoder Models Using Pseudo Languages","created":"2022-05-02","cited_by_count":26},{"id":"2109.13851","title":"Reinforcement Learning for Quantitative Trading","created":"2021-09-28","cited_by_count":24},{"id":"1712.04609","title":"QLBS: Q-Learner in the Black-Scholes(-Merton) Worlds","created":"2017-12-13","cited_by_count":23},{"id":"2102.07247","title":"Reinforcement Learning for IoT Security: A Comprehensive Survey","created":"2021-02-14","cited_by_count":23},{"id":"1711.10162","title":"Topological Recurrent Neural Network for Diffusion Prediction","created":"2017-11-28","cited_by_count":21},{"id":"2101.07107","title":"Deep Reinforcement Learning for Active High Frequency Trading","created":"2021-01-18","cited_by_count":21},{"id":"2202.03609","title":"PolicyCleanse: Backdoor Detection and Mitigation in Reinforcement Learning","created":"2022-02-08","cited_by_count":19},{"id":"2211.02147","title":"A Survey on Reinforcement Learning in Aviation Applications","created":"2022-11-03","cited_by_count":19},{"id":"2407.19845","title":"BackdoorBench: A Comprehensive Benchmark and Analysis of Backdoor Learning","created":"2024-07-29","cited_by_count":19},{"id":"2211.10530","title":"Provable Defense against Backdoor Policies in Reinforcement Learning","created":"2022-11-18","cited_by_count":18},{"id":"2312.08667","title":"Data and Model Poisoning Backdoor Attacks on Wireless Federated Learning, and the Defense Mechanisms: A Comprehensive Survey","created":"2023-12-14","cited_by_count":18},{"id":"2406.05670","title":"Certified Robustness to Data Poisoning in Gradient-Based Training","created":"2024-06-09","cited_by_count":18},{"id":"2106.00123","title":"Deep Reinforcement Learning in Quantitative Algorithmic Trading: A Review","created":"2021-05-31","cited_by_count":17},{"id":"2202.03195","title":"More is Better (Mostly): On the Backdoor Attacks in Federated Graph Neural Networks","created":"2022-02-07","cited_by_count":15},{"id":"1910.03743","title":"Model-based Reinforcement Learning for Predictions and Control for Limit Order Books","created":"2019-10-09","cited_by_count":14},{"id":"2104.09368","title":"Deep Reinforcement Learning in a Monetary Model","created":"2021-04-19","cited_by_count":11},{"id":"2210.13623","title":"Reinforcement Learning and Bandits for Speech and Language Processing: Tutorial, Review and Outlook","created":"2022-10-24","cited_by_count":10},{"id":"2208.10921","title":"AI and 6G into the Metaverse: Fundamentals, Challenges and Future Research Trends","created":"2022-08-23","cited_by_count":8},{"id":"2308.15736","title":"Vulnerability of Machine Learning Approaches Applied in IoT-based Smart Grid: A Review","created":"2023-08-30","cited_by_count":8},{"id":"2201.00762","title":"Execute Order 66: Targeted Data Poisoning for Reinforcement Learning","created":"2022-01-03","cited_by_count":7},{"id":"2301.00188","title":"New Challenges in Reinforcement Learning: A Survey of Security and Privacy","created":"2022-12-31","cited_by_count":7},{"id":"2303.11959","title":"Optimizing Trading Strategies in Quantitative Markets using Multi-Agent Reinforcement Learning","created":"2023-03-15","cited_by_count":7},{"id":"2010.05288","title":"It\\^o's formula for flows of measures on semimartingales","created":"2020-10-11","cited_by_count":6},{"id":"2206.02014","title":"Actuarial Applications of Natural Language Processing Using Transformers: Case Studies for Using Text Features in an Actuarial Context","created":"2022-06-04","cited_by_count":6},{"id":"2409.07775","title":"A Spatiotemporal Stealthy Backdoor Attack against Cooperative Multi-Agent Deep Reinforcement Learning","created":"2024-09-12","cited_by_count":6},{"id":"2407.15855","title":"Data Poisoning Attacks in Intelligent Transportation Systems: A Survey","created":"2024-07-06","cited_by_count":5},{"id":"2212.01554","title":"Distributionally Robust Lyapunov Function Search Under Uncertainty","created":"2022-12-03","cited_by_count":4},{"id":"2304.02277","title":"Rethinking the Trigger-injecting Position in Graph Backdoor Attack","created":"2023-04-05","cited_by_count":4},{"id":"2404.00076","title":"A Backdoor Approach with Inverted Labels Using Dirty Label-Flipping Attacks","created":"2024-03-29","cited_by_count":4},{"id":"2404.04714","title":"Data Poisoning Attacks on Off-Policy Policy Evaluation Methods","created":"2024-04-06","cited_by_count":4},{"id":"1802.06927","title":"On Lyapunov exponents and adversarial perturbation","created":"2018-02-20","cited_by_count":3},{"id":"2102.06800","title":"Reinforcement Learning For Data Poisoning on Graph Neural Networks","created":"2021-02-12","cited_by_count":3},{"id":"2402.05967","title":"The last Dance : Robust backdoor attack via diffusion models and bayesian approach","created":"2024-02-05","cited_by_count":3},{"id":"2406.10719","title":"Trading Devil: Robust backdoor attack via Stochastic investment models and Bayesian approach","created":"2024-06-15","cited_by_count":3},{"id":"2312.15340","title":"Meta-Learning-Based Adaptive Stability Certificates for Dynamical Systems","created":"2023-12-23","cited_by_count":2},{"id":"2410.06213","title":"RL, but don't do anything I wouldn't do","created":"2024-10-08","cited_by_count":2},{"id":"1907.07732","title":"Connecting Lyapunov Control Theory to Adversarial Attacks","created":"2019-07-17","cited_by_count":1}],"next_cursor":null}