{"total":264,"rows":[{"id":"2206.09426","title":"ADBench: Anomaly Detection Benchmark","created":"2022-06-19","cited_by_count":232,"area":null},{"id":"2201.00382","title":"ECOD: Unsupervised Outlier Detection Using Empirical Cumulative Distribution Functions","created":"2022-01-02","cited_by_count":153,"area":null},{"id":"2202.05441","title":"Learning Causally Invariant Representations for Out-of-Distribution Generalization on Graphs","created":"2022-02-11","cited_by_count":144,"area":null},{"id":"2203.12742","title":"Accelerating Bayesian Optimization for Biological Sequence Design with Denoising Autoencoders","created":"2022-03-23","cited_by_count":102,"area":null},{"id":"2407.01603","title":"A Review of Large Language Models and Autonomous Agents in Chemistry","created":"2024-06-26","cited_by_count":99,"area":"agents"},{"id":"2503.02819","title":"Feynman-Kac Correctors in Diffusion: Annealing, Guidance, and Product of Experts","created":"2025-03-04","cited_by_count":96,"area":"diffusion"},{"id":"2211.14238","title":"Wild-Time: A Benchmark of in-the-Wild Distribution Shift over Time","created":"2022-11-25","cited_by_count":90,"area":null},{"id":"2503.00096","title":"BixBench: a Comprehensive Benchmark for LLM-based Agents in Computational Biology","created":"2025-02-28","cited_by_count":89,"area":"agents"},{"id":"2208.09339","title":"Evaluating Explainability for Graph Neural Networks","created":"2022-08-19","cited_by_count":87,"area":null},{"id":"2206.10071","title":"BOND: Benchmarking Unsupervised Outlier Node Detection on Static Attributed Graphs","created":"2022-06-21","cited_by_count":80,"area":null},{"id":"2201.11872","title":"Local Latent Space Bayesian Optimization over Structured Inputs","created":"2022-01-28","cited_by_count":79,"area":null},{"id":"2206.02096","title":"PEER: A Comprehensive and Multi-Task Benchmark for Protein Sequence Understanding","created":"2022-06-05","cited_by_count":77,"area":null},{"id":"2406.16976","title":"Efficient Evolutionary Search Over Chemical Space with Large Language Models","created":"2024-06-23","cited_by_count":61,"area":null},{"id":"2207.12600","title":"Learning Hierarchical Protein Representations via Complete 3D Graph Networks","created":"2022-07-26","cited_by_count":55,"area":null},{"id":"2109.10469","title":"Differentiable Scaffolding Tree for Molecular Optimization","created":"2021-09-22","cited_by_count":53,"area":null},{"id":"2501.06158","title":"GenMol: A Drug Discovery Generalist with Discrete Diffusion","created":"2025-01-10","cited_by_count":50,"area":"diffusion"},{"id":"2310.10773","title":"Gotta be SAFE: A New Framework for Molecular Design","created":"2023-10-16","cited_by_count":48,"area":null},{"id":"2303.03363","title":"Enhancing Activity Prediction Models in Drug Discovery with the Ability to Understand Human Language","created":"2023-03-06","cited_by_count":44,"area":null},{"id":"2411.15692","title":"DrugAgent: Automating AI-aided Drug Discovery Programming through LLM Multi-Agent Collaboration","created":"2024-11-24","cited_by_count":44,"area":"agents"},{"id":"2302.13406","title":"GNNDelete: A General Strategy for Unlearning in Graph Neural Networks","created":"2023-02-26","cited_by_count":43,"area":null},{"id":"2310.19035","title":"Does Invariant Graph Learning via Environment Augmentation Learn Invariance?","created":"2023-10-29","cited_by_count":42,"area":null},{"id":"2406.08506","title":"RGFN: Synthesizable Molecular Generation Using GFlowNets","created":"2024-06-01","cited_by_count":41,"area":null},{"id":"2504.06196","title":"TxGemma: Efficient and Agentic LLMs for Therapeutics","created":"2025-04-08","cited_by_count":41,"area":"agents"},{"id":"2310.04292","title":"Towards Foundational Models for Molecular Learning on Large-Scale Multi-Task Datasets","created":"2023-10-06","cited_by_count":39,"area":null},{"id":"2402.05961","title":"Genetic-guided GFlowNets for Sample Efficient Molecular Optimization","created":"2024-02-05","cited_by_count":39,"area":null},{"id":"2404.11568","title":"On the Scalability of GNNs for Molecular Graphs","created":"2024-04-17","cited_by_count":36,"area":null},{"id":"2402.18012","title":"Diffusion Models as Constrained Samplers for Optimization with Unknown Constraints","created":"2024-02-28","cited_by_count":35,"area":"diffusion"},{"id":"2210.16484","title":"A Systematic Survey of Chemical Pre-trained Models","created":"2022-10-29","cited_by_count":34,"area":null},{"id":"2404.01475","title":"Are large language models superhuman chemists?","created":"2024-04-01","cited_by_count":34,"area":null},{"id":"2204.12095","title":"PyGOD: A Python Library for Graph Outlier Detection","created":"2022-04-26","cited_by_count":32,"area":null},{"id":"2402.05140","title":"Tag-LLM: Repurposing General-Purpose LLMs for Specialized Domains","created":"2024-02-06","cited_by_count":30,"area":null},{"id":"2110.04383","title":"Learning 3D Representations of Molecular Chirality with Invariance to Bond Rotations","created":"2021-10-08","cited_by_count":29,"area":null},{"id":"2210.12496","title":"Bayesian Optimization with Conformal Prediction Sets","created":"2022-10-22","cited_by_count":28,"area":null},{"id":"2405.01155","title":"SynFlowNet: Design of Diverse and Novel Molecules with Synthesis Constraints","created":"2024-05-02","cited_by_count":26,"area":null},{"id":"2406.06316","title":"Tx-LLM: A Large Language Model for Therapeutics","created":"2024-06-10","cited_by_count":25,"area":null},{"id":"2502.11420","title":"Training-Free Guidance Beyond Differentiability: Scalable Path Steering with Tree Search in Diffusion and Flow Models","created":"2025-02-17","cited_by_count":24,"area":null},{"id":"2406.04739","title":"A survey and benchmark of high-dimensional Bayesian optimization of discrete sequences","created":"2024-06-07","cited_by_count":23,"area":null},{"id":"2411.12078","title":"Molecule Generation with Fragment Retrieval Augmentation","created":"2024-11-18","cited_by_count":23,"area":null},{"id":"2207.09542","title":"Controllable Data Generation by Deep Learning: A Review","created":"2022-07-19","cited_by_count":20,"area":null},{"id":"2404.14986","title":"$\\texttt{MiniMol}$: A Parameter-Efficient Foundation Model for Molecular Learning","created":"2024-04-23","cited_by_count":20,"area":null},{"id":"2210.04893","title":"Equivariant Shape-Conditioned Generation of 3D Molecules for Ligand-Based Drug Design","created":"2022-10-06","cited_by_count":19,"area":null},{"id":"2303.10108","title":"Data-Centric Learning from Unlabeled Graphs with Diffusion Model","created":"2023-03-17","cited_by_count":19,"area":"diffusion"},{"id":"2310.02902","title":"Searching for High-Value Molecules Using Reinforcement Learning and Transformers","created":"2023-10-04","cited_by_count":18,"area":null},{"id":"2310.20258","title":"Advancing Bayesian Optimization via Learning Correlated Latent Space","created":"2023-10-31","cited_by_count":18,"area":null},{"id":"2410.03494","title":"Generative Artificial Intelligence for Navigating Synthesizable Chemical Space","created":"2024-10-04","cited_by_count":18,"area":null},{"id":"2306.04620","title":"Goal-conditioned GFlowNets for Controllable Multi-Objective Molecular Design","created":"2023-06-07","cited_by_count":17,"area":null},{"id":"2403.01528","title":"Leveraging Biomolecule and Natural Language through Multi-Modal Learning: A Survey","created":"2024-03-03","cited_by_count":17,"area":null},{"id":"2505.16326","title":"ChemMLLM: Chemical Multimodal Large Language Model","created":"2025-05-22","cited_by_count":17,"area":"mllm"},{"id":"2202.05145","title":"Deep learning for drug repurposing: methods, databases, and applications","created":"2022-02-08","cited_by_count":16,"area":null},{"id":"2207.03928","title":"Accelerating Material Design with the Generative Toolkit for Scientific Discovery","created":"2022-07-08","cited_by_count":16,"area":null},{"id":"2406.12120","title":"Adding Conditional Control to Diffusion Models with Reinforcement Learning","created":"2024-06-17","cited_by_count":16,"area":"diffusion"},{"id":"2406.13864","title":"Evaluating representation learning on the protein structure universe","created":"2024-06-19","cited_by_count":16,"area":null},{"id":"2306.00344","title":"BOtied: Multi-objective Bayesian optimization with tied multivariate ranks","created":"2023-06-01","cited_by_count":15,"area":null},{"id":"2503.17286","title":"Offline Model-Based Optimization: Comprehensive Review","created":"2025-03-21","cited_by_count":15,"area":null},{"id":"2505.20820","title":"MT-Mol:Multi Agent System with Tool-based Reasoning for Molecular Optimization","created":"2025-05-27","cited_by_count":15,"area":"lr"},{"id":"2508.06199","title":"Benchmarking Pretrained Molecular Embedding Models For Molecular Representation Learning","created":"2025-08-08","cited_by_count":15,"area":null},{"id":"2309.05934","title":"MatSciML: A Broad, Multi-Task Benchmark for Solid-State Materials Modeling","created":"2023-09-12","cited_by_count":14,"area":null},{"id":"2409.02231","title":"SmileyLlama: Modifying Large Language Models for Directed Chemical Space Exploration","created":"2024-09-03","cited_by_count":14,"area":"alignment"},{"id":"2411.17983","title":"Optimized Conformal Selection: Powerful Selective Inference After Conformity Score Optimization","created":"2024-11-27","cited_by_count":14,"area":null},{"id":"2506.15792","title":"Deep Learning Foundation Models from Classical Molecular Descriptors","created":"2025-06-18","cited_by_count":14,"area":null},{"id":"2202.09212","title":"Molecule Generation for Drug Design: a Graph Learning Perspective","created":"2022-02-18","cited_by_count":13,"area":null},{"id":"2307.11694","title":"SynerGPT: In-Context Learning for Personalized Drug Synergy Prediction and Drug Design","created":"2023-06-19","cited_by_count":13,"area":null},{"id":"2310.06083","title":"Transformers and Large Language Models for Chemistry and Drug Discovery","created":"2023-10-09","cited_by_count":13,"area":null},{"id":"2310.12033","title":"Conformal Drug Property Prediction with Density Estimation under Covariate Shift","created":"2023-10-18","cited_by_count":13,"area":null},{"id":"2402.04286","title":"Progress and Opportunities of Foundation Models in Bioinformatics","created":"2024-02-06","cited_by_count":13,"area":null},{"id":"2505.16094","title":"A Survey of Large Language Models for Text-Guided Molecular Discovery: from Molecule Generation to Optimization","created":"2025-05-22","cited_by_count":13,"area":null},{"id":"2211.02657","title":"MolE: a molecular foundation model for drug discovery","created":"2022-11-03","cited_by_count":12,"area":null},{"id":"2603.24704","title":"Conformal Selective Prediction with General Risk Control","created":"2026-03-25","cited_by_count":12,"area":null},{"id":"2606.12736","title":"Benchmarking AI Agents for Addressing Scientific Challenges Across Scales","created":"2026-06-10","cited_by_count":12,"area":null},{"id":"2202.05240","title":"ChemicalX: A Deep Learning Library for Drug Pair Scoring","created":"2022-02-10","cited_by_count":11,"area":null},{"id":"2208.09016","title":"Improving Small Molecule Generation using Mutual Information Machine","created":"2022-08-18","cited_by_count":10,"area":null},{"id":"2306.12802","title":"Otter-Knowledge: benchmarks of multimodal knowledge graph representation learning from different sources for drug discovery","created":"2023-06-22","cited_by_count":10,"area":null},{"id":"2307.15073","title":"Drug Discovery under Covariate Shift with Domain-Informed Prior Distributions over Functions","created":"2023-07-14","cited_by_count":10,"area":null},{"id":"2310.06399","title":"Lo-Hi: Practical ML Drug Discovery Benchmark","created":"2023-10-10","cited_by_count":10,"area":null},{"id":"2410.22296","title":"Generalists vs. Specialists: Evaluating LLMs on Highly-Constrained Biophysical Sequence Optimization Tasks","created":"2024-10-29","cited_by_count":10,"area":null},{"id":"2502.11059","title":"ClimateLLM: Efficient Weather Forecasting via Frequency-Aware Large Language Models","created":"2025-02-16","cited_by_count":9,"area":"moe"},{"id":"2503.12602","title":"SynLlama: Generating Synthesizable Molecules and Their Analogs with Large Language Models","created":"2025-03-16","cited_by_count":9,"area":null},{"id":"2505.12534","title":"ChemPile: A 250GB Diverse and Curated Dataset for Chemical Foundation Models","created":"2025-05-18","cited_by_count":9,"area":null},{"id":"2505.15054","title":"MolLangBench: A Comprehensive Benchmark for Language-Prompted Molecular Structure Recognition, Editing, and Generation","created":"2025-05-21","cited_by_count":9,"area":null},{"id":"2605.28655","title":"AutoScientists: Self-Organizing Agent Teams for Long-Running Scientific Experimentation","created":"2026-05-27","cited_by_count":9,"area":null},{"id":"2210.03745","title":"ProGReST: Prototypical Graph Regression Soft Trees for Molecular Property Prediction","created":"2022-10-07","cited_by_count":8,"area":null},{"id":"2305.19901","title":"Adaptive Conformal Regression with Jackknife+ Rescaled Scores","created":"2023-05-31","cited_by_count":8,"area":null},{"id":"2306.14902","title":"Molecule Design by Latent Space Energy-Based Modeling and Gradual Distribution Shifting","created":"2023-06-09","cited_by_count":8,"area":null},{"id":"2307.05378","title":"M$^2$Hub: Unlocking the Potential of Machine Learning for Materials Discovery","created":"2023-06-14","cited_by_count":8,"area":null},{"id":"2407.00236","title":"Closed-Form Test Functions for Biophysical Sequence Optimization Algorithms","created":"2024-06-28","cited_by_count":8,"area":null},{"id":"2505.12565","title":"mCLM: A Modular Chemical Language Model that Generates Functional and Makeable Molecules","created":"2025-05-18","cited_by_count":8,"area":null},{"id":"2111.02916","title":"A Unified View of Relational Deep Learning for Drug Pair Scoring","created":"2021-11-04","cited_by_count":7,"area":null},{"id":"2306.14852","title":"CoarsenConf: Equivariant Coarsening with Aggregated Attention for Molecular Conformer Generation","created":"2023-06-26","cited_by_count":7,"area":null},{"id":"2405.12961","title":"Aligning Transformers with Continuous Feedback via Energy Rank Alignment","created":"2024-05-21","cited_by_count":7,"area":"alignment"},{"id":"2406.03403","title":"Structure-based Drug Design Benchmark: Do 3D Methods Really Dominate?","created":"2024-06-04","cited_by_count":7,"area":null},{"id":"2406.07640","title":"When is an Embedding Model More Promising than Another?","created":"2024-06-11","cited_by_count":7,"area":null},{"id":"2407.12136","title":"Molecular Topological Profile (MOLTOP) -- Simple and Strong Baseline for Molecular Graph Classification","created":"2024-07-16","cited_by_count":7,"area":null},{"id":"2509.16084","title":"Exploring Synthesizable Chemical Space with Iterative Pathway Refinements","created":"2025-09-19","cited_by_count":7,"area":null},{"id":"2510.09201","title":"Multimodal Prompt Optimization: Why Not Leverage Multiple Modalities for MLLMs","created":"2025-10-10","cited_by_count":7,"area":null},{"id":"2306.01631","title":"Bi-level Contrastive Learning for Knowledge-Enhanced Molecule Representations","created":"2023-06-02","cited_by_count":6,"area":null},{"id":"2309.16235","title":"Language models in molecular discovery","created":"2023-09-28","cited_by_count":6,"area":null},{"id":"2311.06965","title":"Anchor Data Augmentation","created":"2023-11-12","cited_by_count":6,"area":null},{"id":"2404.16196","title":"ApisTox: a new benchmark dataset for the classification of small molecules toxicity on honey bees","created":"2024-04-24","cited_by_count":6,"area":null},{"id":"2411.03641","title":"Constrained Multi-objective Bayesian Optimization through Optimistic Constraints Estimation","created":"2024-11-06","cited_by_count":6,"area":null},{"id":"2603.05900","title":"Reference-guided Policy Optimization for Molecular Optimization via LLM Reasoning","created":"2026-03-06","cited_by_count":6,"area":"lr"}],"next_cursor":"100"}