{"total":110,"rows":[{"id":"2305.01610","title":"Finding Neurons in a Haystack: Case Studies with Sparse Probing","created":"2023-05-02","cited_by_count":334,"area":null},{"id":"2206.11990","title":"Equiformer: Equivariant Graph Attention Transformer for 3D Atomistic Graphs","created":"2022-06-23","cited_by_count":264,"area":null},{"id":"2306.12059","title":"EquiformerV2: Improved Equivariant Transformer for Scaling to Higher-Degree Representations","created":"2023-06-21","cited_by_count":204,"area":null},{"id":"2310.03003","title":"From Words to Watts: Benchmarking the Energy Costs of Large Language Model Inference","created":"2023-10-04","cited_by_count":170,"area":null},{"id":"2302.06588","title":"Raising the Cost of Malicious AI-Powered Image Editing","created":"2023-02-13","cited_by_count":163,"area":"diffusion"},{"id":"2406.19384","title":"The Remarkable Robustness of LLMs: Stages of Inference?","created":"2024-06-27","cited_by_count":146,"area":null},{"id":"2401.12181","title":"Universal Neurons in GPT2 Language Models","created":"2024-01-22","cited_by_count":102,"area":"mechinterp"},{"id":"2407.16677","title":"From Imitation to Refinement -- Residual RL for Precise Assembly","created":"2024-07-23","cited_by_count":90,"area":null},{"id":"2111.00899","title":"Equivariant Contrastive Learning","created":"2021-10-28","cited_by_count":66,"area":null},{"id":"2110.07059","title":"Subspace Regularizers for Few-Shot Class Incremental Learning","created":"2021-10-13","cited_by_count":56,"area":null},{"id":"2106.01309","title":"Benchmarking the Performance of Bayesian Optimization across Multiple Experimental Materials Science Domains","created":"2021-05-23","cited_by_count":48,"area":null},{"id":"2404.03729","title":"JUICER: Data-Efficient Imitation Learning for Robotic Assembly","created":"2024-04-04","cited_by_count":38,"area":"offlinerl"},{"id":"2211.02127","title":"Scalable Multi-Agent Reinforcement Learning through Intelligent Information Aggregation","created":"2022-11-03","cited_by_count":36,"area":null},{"id":"2207.05739","title":"A Data-Based Perspective on Transfer Learning","created":"2022-07-12","cited_by_count":32,"area":null},{"id":"2211.07541","title":"Aspects of scaling and scalability for flow-based sampling of lattice QCD","created":"2022-11-14","cited_by_count":26,"area":null},{"id":"2207.02842","title":"When does Bias Transfer in Transfer Learning?","created":"2022-07-06","cited_by_count":23,"area":null},{"id":"2205.09646","title":"Great Power, Great Responsibility: Recommendations for Reducing Energy for Training Language Models","created":"2022-05-19","cited_by_count":21,"area":null},{"id":"2101.07243","title":"Gauge Invariant and Anyonic Symmetric Transformer and RNN Quantum States for Quantum Lattice Models","created":"2021-01-18","cited_by_count":18,"area":null},{"id":"2308.09474","title":"Evolving Scientific Discovery by Unifying Data and Background Knowledge with AI Hilbert","created":"2023-08-18","cited_by_count":18,"area":null},{"id":"2403.09549","title":"Generalizing Denoising to Non-Equilibrium Structures Improves Equivariant Force Fields","created":"2024-03-14","cited_by_count":18,"area":null},{"id":"2509.07209","title":"BlendedNet: A Blended Wing Body Aircraft Dataset and Surrogate Model for Aerodynamic Predictions","created":"2025-09-08","cited_by_count":16,"area":null},{"id":"2109.12701","title":"Sparse Plus Low Rank Matrix Decomposition: A Discrete Optimization Approach","created":"2021-09-26","cited_by_count":14,"area":null},{"id":"2208.13771","title":"Fast Bayesian Optimization of Needle-in-a-Haystack Problems using Zooming Memory-Based Initialization (ZoMBI)","created":"2022-08-26","cited_by_count":14,"area":null},{"id":"2307.10163","title":"Rethinking Backdoor Attacks","created":"2023-07-19","cited_by_count":14,"area":"safety"},{"id":"2305.08279","title":"Ship-D: Ship Hull Dataset for Design Optimization using Machine Learning","created":"2023-05-14","cited_by_count":13,"area":null},{"id":"2503.22634","title":"Empirical Analysis of Sim-and-Real Cotraining of Diffusion Policies for Planar Pushing from Pixels","created":"2025-03-28","cited_by_count":13,"area":"diffusion"},{"id":"2403.12029","title":"Align and Distill: Unifying and Improving Domain Adaptive Object Detection","created":"2024-03-18","cited_by_count":12,"area":null},{"id":"2502.10600","title":"Weighted quantization using MMD: From mean field to mean shift via gradient flows","created":"2025-02-14","cited_by_count":12,"area":null},{"id":"2311.06315","title":"ShipGen: A Diffusion Model for Parametric Ship Hull Generation with Multiple Objectives and Constraints","created":"2023-11-09","cited_by_count":11,"area":null},{"id":"2303.16028","title":"Synthetically generated text for supervised text analysis","created":"2023-03-28","cited_by_count":10,"area":null},{"id":"2402.18593","title":"Sustainable Supercomputing for AI: GPU Power Capping at HPC Scale","created":"2024-02-25","cited_by_count":9,"area":null},{"id":"2505.12171","title":"Learning to Dissipate Energy in Oscillatory State-Space Models","created":"2025-05-17","cited_by_count":9,"area":null},{"id":"2212.13558","title":"AER: Auto-Encoder with Regression for Time Series Anomaly Detection","created":"2022-12-27","cited_by_count":8,"area":null},{"id":"2304.01996","title":"ANTN: Bridging Autoregressive Neural Networks and Tensor Networks for Quantum Many-Body Simulation","created":"2023-04-04","cited_by_count":8,"area":null},{"id":"2401.17898","title":"Multitask methods for predicting molecular properties from heterogeneous data","created":"2024-01-31","cited_by_count":8,"area":null},{"id":"2108.02037","title":"The MIT Supercloud Dataset","created":"2021-08-04","cited_by_count":7,"area":null},{"id":"2201.12423","title":"Benchmarking Resource Usage for Efficient Distributed Deep Learning","created":"2022-01-28","cited_by_count":7,"area":null},{"id":"2206.12498","title":"Optimal and Robust Category-level Perception: Object Pose and Shape Estimation from 2D and 3D Semantic Keypoints","created":"2022-06-24","cited_by_count":7,"area":null},{"id":"2311.02236","title":"Robust Fine-Tuning of Vision-Language Models for Domain Generalization","created":"2023-11-03","cited_by_count":7,"area":"mllm"},{"id":"2202.11258","title":"Many processors, little time: MCMC for partitions via optimal transport couplings","created":"2022-02-23","cited_by_count":6,"area":null},{"id":"2305.07804","title":"Improving Small Language Models on PubMedQA via Generative Data Augmentation","created":"2023-05-12","cited_by_count":6,"area":null},{"id":"2305.09018","title":"DATED: Guidelines for Creating Synthetic Datasets for Engineering Design Applications","created":"2023-05-15","cited_by_count":6,"area":null},{"id":"2312.09436","title":"Temporal Transfer Learning for Traffic Optimization with Coarse-grained Advisory Autonomy","created":"2023-11-27","cited_by_count":6,"area":null},{"id":"2404.11674","title":"Practical applications of machine-learned flows on gauge fields","created":"2024-04-17","cited_by_count":6,"area":null},{"id":"2511.21622","title":"On the Origin of Algorithmic Progress in AI","created":"2025-11-26","cited_by_count":6,"area":null},{"id":"2301.11581","title":"A Green(er) World for A.I","created":"2023-01-27","cited_by_count":5,"area":null},{"id":"2302.11836","title":"On Statistical Properties of Sharpness-Aware Minimization: Provable Guarantees","created":"2023-02-23","cited_by_count":5,"area":null},{"id":"2307.09366","title":"Sparse Gaussian Graphical Models with Discrete Optimization: Computational and Statistical Perspectives","created":"2023-07-18","cited_by_count":5,"area":null},{"id":"2410.05097","title":"DreamSat: Towards a General 3D Model for Novel View Synthesis of Space Objects","created":"2024-10-07","cited_by_count":5,"area":null},{"id":"2410.14916","title":"Cooperation and Fairness in Multi-Agent Reinforcement Learning","created":"2024-10-19","cited_by_count":5,"area":null},{"id":"2511.21739","title":"Science Is Falling Behind the Frontier: Foundation Model Adoption Across Half a Million Papers","created":"2025-11-21","cited_by_count":5,"area":null},{"id":"2206.04513","title":"AAM-Gym: Artificial Intelligence Testbed for Advanced Air Mobility","created":"2022-06-09","cited_by_count":4,"area":null},{"id":"2301.12548","title":"Global Flood Prediction: a Multimodal Machine Learning Approach","created":"2023-01-29","cited_by_count":4,"area":null},{"id":"2303.08272","title":"Automated patent extraction powers generative modeling in focused chemical spaces","created":"2023-03-14","cited_by_count":4,"area":null},{"id":"2308.00864","title":"PeRP: Personalized Residual Policies For Congestion Mitigation Through Co-operative Advisory Systems","created":"2023-08-01","cited_by_count":4,"area":null},{"id":"2308.04958","title":"Improving Autonomous Separation Assurance through Distributed Reinforcement Learning with Attention Networks","created":"2023-08-09","cited_by_count":4,"area":null},{"id":"2405.17209","title":"How Do Transformers \"Do\" Physics? Investigating the Simple Harmonic Oscillator","created":"2024-05-23","cited_by_count":4,"area":null},{"id":"2406.00294","title":"Creative Text-to-Audio Generation via Synthesizer Programming","created":"2024-06-01","cited_by_count":4,"area":null},{"id":"2407.03333","title":"C-ShipGen: A Conditional Guided Diffusion Model for Parametric Ship Hull Design","created":"2024-05-10","cited_by_count":4,"area":"diffusion"},{"id":"2409.16143","title":"Seeing Faces in Things: A Model and Dataset for Pareidolia","created":"2024-09-24","cited_by_count":4,"area":null},{"id":"2112.03364","title":"Scalable Geometric Deep Learning on Molecular Graphs","created":"2021-12-06","cited_by_count":3,"area":null},{"id":"2204.03703","title":"Physics-assisted Generative Adversarial Network for X-Ray Tomography","created":"2022-04-07","cited_by_count":3,"area":null},{"id":"2205.09117","title":"Neighborhood Mixup Experience Replay: Local Convex Interpolation for Improved Sample Efficiency in Continuous Control Tasks","created":"2022-05-18","cited_by_count":3,"area":null},{"id":"2210.03625","title":"C2KD: Cross-Lingual Cross-Modal Knowledge Distillation for Multilingual Text-Video Retrieval","created":"2022-10-07","cited_by_count":3,"area":"distill"},{"id":"2211.07889","title":"Pretraining ECG Data with Adversarial Masking Improves Model Generalizability for Data-Scarce Tasks","created":"2022-11-15","cited_by_count":3,"area":null},{"id":"2306.04647","title":"Compressed Sensing: A Discrete Optimization Approach","created":"2023-06-05","cited_by_count":3,"area":null},{"id":"2502.00899","title":"HASSLE-free: A unified Framework for Sparse plus Low-Rank Matrix Decomposition for LLMs","created":"2025-02-02","cited_by_count":3,"area":null},{"id":"2204.13608","title":"Representative period selection for power system planning using autoencoder-based dimensionality reduction","created":"2022-04-28","cited_by_count":2,"area":null},{"id":"2207.07033","title":"Developing a Series of AI Challenges for the United States Department of the Air Force","created":"2022-07-14","cited_by_count":2,"area":null},{"id":"2212.00855","title":"Reward Function Optimization of a Deep Reinforcement Learning Collision Avoidance System","created":"2022-12-01","cited_by_count":2,"area":null},{"id":"2304.04308","title":"Ensemble Modeling for Time Series Forecasting: an Adaptive Robust Optimization Approach","created":"2023-04-09","cited_by_count":2,"area":null},{"id":"2305.12292","title":"Disjunctive Branch-and-Bound for Certifiably Optimal Low-Rank Matrix Completion","created":"2023-05-20","cited_by_count":2,"area":null},{"id":"2310.00728","title":"Physics-Informed Graph Neural Network for Dynamic Reconfiguration of Power Systems","created":"2023-10-01","cited_by_count":2,"area":null},{"id":"2408.13150","title":"Adaptive Backtracking Line Search","created":"2024-08-23","cited_by_count":2,"area":null},{"id":"2409.03731","title":"A Deep Generative Learning Approach for Two-stage Adaptive Robust Optimization","created":"2024-09-05","cited_by_count":2,"area":null},{"id":"2410.06333","title":"Batched Bayesian optimization by maximizing the probability of including the optimum","created":"2024-10-08","cited_by_count":2,"area":null},{"id":"2502.05383","title":"Is attention all you need to solve the correlated electron problem?","created":"2025-02-07","cited_by_count":2,"area":null},{"id":"2503.12822","title":"An Optimization Framework for Differentially Private Sparse Fine-Tuning","created":"2025-03-17","cited_by_count":2,"area":null},{"id":"2606.16447","title":"Training and Evaluating Diffusion Policies with Long Context Lengths","created":"2026-06-15","cited_by_count":2,"area":"diffusion"},{"id":"2109.12171","title":"NICE: Robust Scheduling through Reinforcement Learning-Guided Integer Programming","created":"2021-09-24","cited_by_count":1,"area":null},{"id":"2111.08011","title":"Advantage of Machine Learning over Maximum Likelihood in Limited-Angle Low-Photon X-Ray Tomography","created":"2021-11-15","cited_by_count":1,"area":null},{"id":"2209.12035","title":"Graph Representation Learning for Energy Demand Data: Application to Joint Energy System Planning under Emissions Constraints","created":"2022-09-24","cited_by_count":1,"area":null},{"id":"2303.08996","title":"Learning Spatio-Temporal Aggregations for Large-Scale Capacity Expansion Problems","created":"2023-03-16","cited_by_count":1,"area":null},{"id":"2305.16424","title":"SketchOGD: Memory-Efficient Continual Learning","created":"2023-05-25","cited_by_count":1,"area":null},{"id":"2306.03218","title":"Optimal transport for automatic alignment of untargeted metabolomic data","created":"2023-06-05","cited_by_count":1,"area":null},{"id":"2309.04510","title":"Decreasing the Computing Time of Bayesian Optimization using Generalizable Memory Pruning","created":"2023-09-08","cited_by_count":1,"area":null},{"id":"2310.17748","title":"OrionBench: Benchmarking Time Series Generative Models in the Service of the End-User","created":"2023-10-26","cited_by_count":1,"area":null},{"id":"2403.00026","title":"Learning to Deliver: a Foundation Model for the Montreal Capacitated Vehicle Routing Problem","created":"2024-02-28","cited_by_count":1,"area":null},{"id":"2405.12229","title":"Multi-task learning for molecular electronic structure approaching coupled-cluster accuracy","created":"2024-05-09","cited_by_count":1,"area":null},{"id":"2406.13971","title":"Complex fractal trainability boundary can arise from trivial non-convexity","created":"2024-06-20","cited_by_count":1,"area":null},{"id":"2407.00553","title":"Cooperative Advisory Residual Policies for Congestion Mitigation","created":"2024-06-30","cited_by_count":1,"area":null},{"id":"2511.00267","title":"Advancing AI Challenges for the United States Department of the Air Force","created":"2025-10-31","cited_by_count":1,"area":null},{"id":"2512.04452","title":"NORi: An ML-Augmented Ocean Boundary Layer Parameterization","created":"2025-12-04","cited_by_count":1,"area":null},{"id":"2604.22816","title":"Applied AI-Enhanced RF Interference Rejection","created":"2026-04-14","cited_by_count":1,"area":null},{"id":"2108.11503","title":"Maneuver Identification Challenge","created":"2021-08-25","cited_by_count":0,"area":null},{"id":"2111.07140","title":"The Pseudo Projection Operator: Applications of Deep Learning to Projection Based Filtering in Non-Trivial Frequency Regimes","created":"2021-11-13","cited_by_count":0,"area":null},{"id":"2112.04977","title":"Bringing Atomistic Deep Learning to Prime Time","created":"2021-12-09","cited_by_count":0,"area":null},{"id":"2112.11929","title":"Meta-Learning and Self-Supervised Pretraining for Real World Image Translation","created":"2021-12-22","cited_by_count":0,"area":null},{"id":"2206.01749","title":"Uncertainty Estimation in Machine Learning","created":"2022-06-03","cited_by_count":0,"area":null},{"id":"2310.18542","title":"End-to-end Feature Selection Approach for Learning Skinny Trees","created":"2023-10-28","cited_by_count":0,"area":null}],"next_cursor":"100"}