{"list":"other","total":58,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"2309.06180","title":"Efficient Memory Management for Large Language Model Serving with PagedAttention","created":"2023-09-12","cited_by_count":5944},{"id":"2310.06825","title":"Mistral 7B","created":"2023-10-10","cited_by_count":3164},{"id":"1308.3432","title":"Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation","created":"2013-08-15","cited_by_count":2079},{"id":"2403.13372","title":"LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models","created":"2024-03-20","cited_by_count":1464},{"id":"2010.02193","title":"Mastering Atari with Discrete World Models","created":"2020-10-05","cited_by_count":1007},{"id":"2403.08295","title":"Gemma: Open Models Based on Gemini Research and Technology","created":"2024-03-13","cited_by_count":916},{"id":"1906.08253","title":"When to Trust Your Model: Model-Based Policy Optimization","created":"2019-06-19","cited_by_count":773},{"id":"1807.02811","title":"A Tutorial on Bayesian Optimization","created":"2018-07-08","cited_by_count":744},{"id":"1712.05889","title":"Ray: A Distributed Framework for Emerging AI Applications","created":"2017-12-16","cited_by_count":527},{"id":"2106.07998","title":"Revisiting the Calibration of Modern Neural Networks","created":"2021-06-15","cited_by_count":390},{"id":"1906.10652","title":"Monte Carlo Gradient Estimation in Machine Learning","created":"2019-06-25","cited_by_count":283},{"id":"2402.19446","title":"ArCHer: Training Language Model Agents via Hierarchical Multi-Turn RL","created":"2024-02-29","cited_by_count":228},{"id":"2302.02662","title":"Grounding Large Language Models in Interactive Environments with Online Reinforcement Learning","created":"2023-02-06","cited_by_count":195},{"id":"1403.5341","title":"An Information-Theoretic Analysis of Thompson Sampling","created":"2014-03-21","cited_by_count":178},{"id":"2306.08018","title":"Mol-Instructions: A Large-Scale Biomolecular Instruction Dataset for Large Language Models","created":"2023-06-13","cited_by_count":133},{"id":"2002.09309","title":"Efficiently Sampling Functions from Gaussian Process Posteriors","created":"2020-02-21","cited_by_count":127},{"id":"1903.05480","title":"Variational Bayesian Optimal Experimental Design","created":"2019-03-13","cited_by_count":116},{"id":"2103.02438","title":"Deep Adaptive Design: Amortizing Sequential Bayesian Experimental Design","created":"2021-03-03","cited_by_count":106},{"id":"2310.13227","title":"ToolChain*: Efficient Action Space Navigation in Large Language Models with A* Search","created":"2023-10-20","cited_by_count":105},{"id":"1906.08649","title":"Exploring Model-based Planning with Policy Networks","created":"2019-06-20","cited_by_count":90},{"id":"2202.00665","title":"Tutorial on amortized optimization","created":"2022-02-01","cited_by_count":83},{"id":"2107.05719","title":"Calibrating Predictions to Decisions: A Novel Approach to Multi-Class Calibration","created":"2021-07-12","cited_by_count":79},{"id":"2104.06303","title":"Learning and Planning in Complex Action Spaces","created":"2021-04-13","cited_by_count":77},{"id":"1810.08700","title":"Safe Reinforcement Learning with Model Uncertainty Estimates","created":"2018-10-19","cited_by_count":72},{"id":"2111.02329","title":"Implicit Deep Adaptive Design: Policy-Based Experimental Design without Likelihoods","created":"2021-11-03","cited_by_count":61},{"id":"2308.12682","title":"SayCanPay: Heuristic Planning with Large Language Models using Learnable Domain Knowledge","created":"2023-08-24","cited_by_count":49},{"id":"2307.09668","title":"Towards A Unified Agent with Foundation Models","created":"2023-07-18","cited_by_count":47},{"id":"2301.06568","title":"Ankh: Optimized Protein Language Model Unlocks General-Purpose Modelling","created":"2023-01-16","cited_by_count":45},{"id":"2006.15779","title":"Efficient Nonmyopic Bayesian Optimization via One-Shot Multi-Step Trees","created":"2020-06-29","cited_by_count":41},{"id":"1510.06299","title":"GLASSES: Relieving The Myopia Of Bayesian Optimisation","created":"2015-10-21","cited_by_count":38},{"id":"2311.13884","title":"Controlling Large Language Model-based Agents for Large-Scale Decision-Making: An Actor-Critic Approach","created":"2023-11-23","cited_by_count":38},{"id":"1909.04568","title":"BINOCULARS for Efficient, Nonmyopic Sequential Experimental Design","created":"2019-09-10","cited_by_count":35},{"id":"2305.15930","title":"End-to-End Meta-Bayesian Optimisation with Transformer Neural Processes","created":"2023-05-25","cited_by_count":32},{"id":"2210.16913","title":"Revisiting Simple Regret: Fast Rates for Returning a Good Arm","created":"2022-10-30","cited_by_count":25},{"id":"1911.01004","title":"Why Non-myopic Bayesian Optimization is Promising and How Far Should We Look-ahead? A Study via Rollout","created":"2019-11-04","cited_by_count":23},{"id":"2310.19848","title":"Efficient Exploration in Continuous-time Model-based Reinforcement Learning","created":"2023-10-30","cited_by_count":22},{"id":"2002.10539","title":"Efficient Rollout Strategies for Bayesian Optimization","created":"2020-02-24","cited_by_count":19},{"id":"2106.06079","title":"A Nonmyopic Approach to Cost-Constrained Bayesian Optimization","created":"2021-06-10","cited_by_count":19},{"id":"2111.06537","title":"Multi-Step Budgeted Bayesian Optimization with Unknown Evaluation Costs","created":"2021-11-12","cited_by_count":18},{"id":"2110.13891","title":"Dynamic Causal Bayesian Optimization","created":"2021-10-26","cited_by_count":17},{"id":"2406.20062","title":"Cost-aware Bayesian Optimization via the Pandora's Box Gittins Index","created":"2024-06-28","cited_by_count":16},{"id":"1511.06890","title":"Gaussian Process Planning with Lipschitz Continuous Reward Functions: Towards Unifying Bayesian Optimization, Active Learning, and Beyond","created":"2015-11-21","cited_by_count":15},{"id":"2302.12526","title":"Model-Based Uncertainty in Value Functions","created":"2023-02-24","cited_by_count":15},{"id":"2202.00060","title":"SnAKe: Bayesian Optimization with Pathwise Exploration","created":"2022-01-31","cited_by_count":14},{"id":"2210.01383","title":"Generalizing Bayesian Optimization with Decision-theoretic Entropies","created":"2022-10-04","cited_by_count":11},{"id":"1803.03432","title":"Bayesian Optimization for Dynamic Problems","created":"2018-03-09","cited_by_count":10},{"id":"2002.09670","title":"Nonmyopic Gaussian Process Optimization with Macro-Actions","created":"2020-02-22","cited_by_count":8},{"id":"2206.12708","title":"Bayesian Optimization Over Iterative Learners with Structured Responses: A Budget-aware Planning Approach","created":"2022-06-25","cited_by_count":8},{"id":"2406.02791","title":"Language Models can Infer Action Semantics for Symbolic Planners from Environment Feedback","created":"2024-06-04","cited_by_count":8},{"id":"2402.08406","title":"Transition Constrained Bayesian Optimization via Markov Decision Processes","created":"2024-02-13","cited_by_count":7},{"id":"2402.18866","title":"Dr. Strategy: Model-Based Generalist Agents with Strategic Dreaming","created":"2024-02-29","cited_by_count":6},{"id":"2411.00171","title":"EARL-BO: Reinforcement Learning for Multi-Step Lookahead, High-Dimensional Bayesian Optimization","created":"2024-10-31","cited_by_count":6},{"id":"2501.06339","title":"On The Statistical Complexity of Offline Decision-Making","created":"2025-01-10","cited_by_count":2},{"id":"2310.08331","title":"Dealing with uncertainty: balancing exploration and exploitation in deep recurrent reinforcement learning","created":"2023-10-12","cited_by_count":1},{"id":"2408.07812","title":"Differentiating Policies for Non-Myopic Bayesian Optimization","created":"2024-08-14","cited_by_count":1}],"next_cursor":null}