{"list":"other","total":51,"rows":[{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2402.03300","title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","created":"2024-02-05","cited_by_count":9379},{"id":"2501.12948","title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","created":"2025-01-22","cited_by_count":6330},{"id":"2309.06180","title":"Efficient Memory Management for Large Language Model Serving with PagedAttention","created":"2023-09-12","cited_by_count":5944},{"id":"2203.11171","title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models","created":"2022-03-21","cited_by_count":5708},{"id":"2412.15115","title":"Qwen2.5 Technical Report","created":"2024-12-19","cited_by_count":4942},{"id":"2205.11916","title":"Large Language Models are Zero-Shot Reasoners","created":"2022-05-24","cited_by_count":4374},{"id":"2305.10601","title":"Tree of Thoughts: Deliberate Problem Solving with Large Language Models","created":"2023-05-17","cited_by_count":3211},{"id":"2403.13372","title":"LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models","created":"2024-03-20","cited_by_count":1464},{"id":"2501.19393","title":"s1: Simple test-time scaling","created":"2025-01-31","cited_by_count":1341},{"id":"2307.03109","title":"A Survey on Evaluation of Large Language Models","created":"2023-07-06","cited_by_count":1242},{"id":"2504.13837","title":"Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?","created":"2025-04-18","cited_by_count":982},{"id":"2203.14465","title":"STaR: Bootstrapping Reasoning With Reasoning","created":"2022-03-28","cited_by_count":940},{"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":"2106.04399","title":"Flow Network based Generative Models for Non-Iterative Diverse Candidate Generation","created":"2021-06-08","cited_by_count":392},{"id":"2503.01307","title":"Cognitive Behaviors that Enable Self-Improving Reasoners, or, Four Habits of Highly Effective STaRs","created":"2025-03-03","cited_by_count":377},{"id":"1904.01561","title":"Analyzing Learned Molecular Representations for Property Prediction","created":"2019-04-02","cited_by_count":375},{"id":"2311.03191","title":"DeepInception: Hypnotize Large Language Model to Be Jailbreaker","created":"2023-11-06","cited_by_count":367},{"id":"1704.07555","title":"Molecular De Novo Design through Deep Reinforcement Learning","created":"2017-04-25","cited_by_count":267},{"id":"2102.09548","title":"Therapeutics Data Commons: Machine Learning Datasets and Tasks for Drug Discovery and Development","created":"2021-02-18","cited_by_count":264},{"id":"2307.10635","title":"SciBench: Evaluating College-Level Scientific Problem-Solving Abilities of Large Language Models","created":"2023-07-20","cited_by_count":256},{"id":"2305.18365","title":"What can Large Language Models do in chemistry? A comprehensive benchmark on eight tasks","created":"2023-05-27","cited_by_count":185},{"id":"2204.11817","title":"Translation between Molecules and Natural Language","created":"2022-04-25","cited_by_count":177},{"id":"2309.11489","title":"Text2Reward: Reward Shaping with Language Models for Reinforcement Learning","created":"2023-09-20","cited_by_count":160},{"id":"2310.07276","title":"BioT5: Enriching Cross-modal Integration in Biology with Chemical Knowledge and Natural Language Associations","created":"2023-10-11","cited_by_count":100},{"id":"2402.00782","title":"Dense Reward for Free in Reinforcement Learning from Human Feedback","created":"2024-02-01","cited_by_count":78},{"id":"2406.16976","title":"Efficient Evolutionary Search Over Chemical Space with Large Language Models","created":"2024-06-23","cited_by_count":61},{"id":"2302.04040","title":"Sample-efficient Multi-objective Molecular Optimization with GFlowNets","created":"2023-02-08","cited_by_count":50},{"id":"2211.16508","title":"Reinforced Genetic Algorithm for Structure-based Drug Design","created":"2022-11-28","cited_by_count":46},{"id":"2410.23856","title":"Can Language Models Perform Robust Reasoning in Chain-of-thought Prompting with Noisy Rationales?","created":"2024-10-31","cited_by_count":41},{"id":"2404.01475","title":"Are large language models superhuman chemists?","created":"2024-04-01","cited_by_count":34},{"id":"2106.04011","title":"JANUS: Parallel Tempered Genetic Algorithm Guided by Deep Neural Networks for Inverse Molecular Design","created":"2021-06-07","cited_by_count":32},{"id":"2406.00806","title":"Envisioning Outlier Exposure by Large Language Models for Out-of-Distribution Detection","created":"2024-06-02","cited_by_count":32},{"id":"2411.15382","title":"On the Impact of Fine-Tuning on Chain-of-Thought Reasoning","created":"2024-11-22","cited_by_count":32},{"id":"2503.18929","title":"Trajectory Balance with Asynchrony: Decoupling Exploration and Learning for Fast, Scalable LLM Post-Training","created":"2025-03-24","cited_by_count":29},{"id":"2406.18851","title":"LICO: Large Language Models for In-Context Molecular Optimization","created":"2024-06-27","cited_by_count":26},{"id":"2503.22165","title":"Landscape of Thoughts: Visualizing the Reasoning Process of Large Language Models","created":"2025-03-28","cited_by_count":25},{"id":"2506.08295","title":"From Passive to Active Reasoning: Can Large Language Models Ask the Right Questions under Incomplete Information?","created":"2025-06-09","cited_by_count":23},{"id":"2508.00410","title":"Co-rewarding: Stable Self-supervised RL for Eliciting Reasoning in Large Language Models","created":"2025-08-01","cited_by_count":23},{"id":"2502.09511","title":"Diffusion Models for Molecules: A Survey of Methods and Tasks","created":"2025-02-13","cited_by_count":19},{"id":"2502.13398","title":"GeLLMO: Generalizing Large Language Models for Multi-property Molecule Optimization","created":"2025-02-19","cited_by_count":17},{"id":"2505.19433","title":"Can Compressed LLMs Truly Act? An Empirical Evaluation of Agentic Capabilities in LLM Compression","created":"2025-05-26","cited_by_count":16},{"id":"2402.01439","title":"From Words to Molecules: A Survey of Large Language Models in Chemistry","created":"2024-02-02","cited_by_count":14},{"id":"2510.05837","title":"EEPO: Exploration-Enhanced Policy Optimization via Sample-Then-Forget","created":"2025-10-07","cited_by_count":14},{"id":"2411.14721","title":"MolReFlect: Towards In-Context Fine-grained Alignments between Molecules and Texts","created":"2024-11-22","cited_by_count":11},{"id":"2311.01276","title":"Neural Atoms: Propagating Long-range Interaction in Molecular Graphs through Efficient Communication Channel","created":"2023-11-02","cited_by_count":10},{"id":"2502.14604","title":"Noisy Test-Time Adaptation in Vision-Language Models","created":"2025-02-20","cited_by_count":10},{"id":"2602.06423","title":"On the Wings of Imagination: Conflicting Script-based Multi-role Framework for Humor Caption Generation","created":"2026-02-06","cited_by_count":3},{"id":"2502.14934","title":"Fast and Accurate Blind Flexible Docking","created":"2025-02-20","cited_by_count":2}],"next_cursor":null}