{"total":129,"rows":[{"id":"2101.11517","title":"Investigating Bi-Level Optimization for Learning and Vision from a Unified Perspective: A Survey and Beyond","created":"2021-01-27","cited_by_count":153,"area":null},{"id":"2412.20413","title":"EraseAnything: Enabling Concept Erasure in Rectified Flow Transformers","created":"2024-12-29","cited_by_count":95,"area":"diffusion"},{"id":"2405.09783","title":"LLM and Simulation as Bilevel Optimizers: A New Paradigm to Advance Physical Scientific Discovery","created":"2024-05-16","cited_by_count":86,"area":"lr"},{"id":"2205.02215","title":"FedNest: Federated Bilevel, Minimax, and Compositional Optimization","created":"2022-05-04","cited_by_count":60,"area":null},{"id":"2309.01753","title":"On Penalty Methods for Nonconvex Bilevel Optimization and First-Order Stochastic Approximation","created":"2023-09-04","cited_by_count":51,"area":null},{"id":"2205.12679","title":"Self-Guided Noise-Free Data Generation for Efficient Zero-Shot Learning","created":"2022-05-25","cited_by_count":50,"area":null},{"id":"2303.14042","title":"Class-Incremental Exemplar Compression for Class-Incremental Learning","created":"2023-03-24","cited_by_count":50,"area":null},{"id":"2201.01212","title":"AutoBalance: Optimized Loss Functions for Imbalanced Data","created":"2022-01-04","cited_by_count":49,"area":null},{"id":"2301.09819","title":"Model Agnostic Sample Reweighting for Out-of-Distribution Learning","created":"2023-01-24","cited_by_count":44,"area":null},{"id":"2301.01716","title":"First-order penalty methods for bilevel optimization","created":"2023-01-04","cited_by_count":41,"area":null},{"id":"2308.00788","title":"An Introduction to Bi-level Optimization: Foundations and Applications in Signal Processing and Machine Learning","created":"2023-08-01","cited_by_count":41,"area":null},{"id":"2212.14032","title":"On Implicit Bias in Overparameterized Bilevel Optimization","created":"2022-12-28","cited_by_count":30,"area":null},{"id":"2302.14290","title":"Learning to Retain while Acquiring: Combating Distribution-Shift in Adversarial Data-Free Knowledge Distillation","created":"2023-02-28","cited_by_count":29,"area":"distill"},{"id":"2408.02085","title":"Unleashing the Power of Data Tsunami: A Comprehensive Survey on Data Assessment and Selection for Instruction Tuning of Language Models","created":"2024-08-04","cited_by_count":29,"area":"alignment"},{"id":"2301.09880","title":"Probabilistic Bilevel Coreset Selection","created":"2023-01-24","cited_by_count":27,"area":null},{"id":"2105.14937","title":"Safe Pontryagin Differentiable Programming","created":"2021-05-31","cited_by_count":26,"area":null},{"id":"2207.11719","title":"Gradient-based Bi-level Optimization for Deep Learning: A Survey","created":"2022-07-24","cited_by_count":26,"area":null},{"id":"2401.11963","title":"Bridging Evolutionary Algorithms and Reinforcement Learning: A Comprehensive Survey on Hybrid Algorithms","created":"2024-01-22","cited_by_count":26,"area":"deeprl"},{"id":"2305.02279","title":"Learngene: Inheriting Condensed Knowledge from the Ancestry Model to Descendant Models","created":"2023-05-03","cited_by_count":24,"area":null},{"id":"2310.05055","title":"FairTune: Optimizing Parameter Efficient Fine Tuning for Fairness in Medical Image Analysis","created":"2023-10-08","cited_by_count":23,"area":null},{"id":"2404.02817","title":"A Survey of Optimization-based Task and Motion Planning: From Classical To Learning Approaches","created":"2024-04-03","cited_by_count":20,"area":null},{"id":"1906.00429","title":"Learner-aware Teaching: Inverse Reinforcement Learning with Preferences and Constraints","created":"2019-06-02","cited_by_count":18,"area":"offlinerl"},{"id":"2501.14959","title":"Systemizing Multiplicity: The Curious Case of Arbitrariness in Machine Learning","created":"2025-01-24","cited_by_count":17,"area":null},{"id":"2204.13749","title":"Learning to Split for Automatic Bias Detection","created":"2022-04-28","cited_by_count":16,"area":null},{"id":"2406.16087","title":"Imperative Learning: A Self-supervised Neuro-Symbolic Learning Framework for Robot Autonomy","created":"2024-06-23","cited_by_count":16,"area":"offlinerl"},{"id":"2207.02829","title":"Online Bilevel Optimization: Regret Analysis of Online Alternating Gradient Methods","created":"2022-07-06","cited_by_count":15,"area":null},{"id":"2202.00048","title":"Single Time-scale Actor-critic Method to Solve the Linear Quadratic Regulator with Convergence Guarantees","created":"2022-01-31","cited_by_count":14,"area":null},{"id":"2305.19442","title":"SimFBO: Towards Simple, Flexible and Communication-efficient Federated Bilevel Learning","created":"2023-05-30","cited_by_count":14,"area":null},{"id":"2212.10048","title":"Asynchronous Distributed Bilevel Optimization","created":"2022-12-20","cited_by_count":13,"area":null},{"id":"2302.04969","title":"Communication-Efficient Federated Hypergradient Computation via Aggregated Iterative Differentiation","created":"2023-02-09","cited_by_count":13,"area":null},{"id":"2303.10891","title":"Non-Exemplar Online Class-incremental Continual Learning via Dual-prototype Self-augment and Refinement","created":"2023-03-20","cited_by_count":13,"area":null},{"id":"2306.00036","title":"Symmetry-Aware Robot Design with Structured Subgroups","created":"2023-05-31","cited_by_count":13,"area":null},{"id":"2311.08675","title":"Refined Coreset Selection: Towards Minimal Coreset Size under Model Performance Constraints","created":"2023-11-15","cited_by_count":13,"area":null},{"id":"2501.13492","title":"Quantized Spike-driven Transformer","created":"2025-01-23","cited_by_count":13,"area":null},{"id":"2101.04852","title":"Knowledge-Enhanced Top-K Recommendation in Poincar\\'e Ball","created":"2021-01-13","cited_by_count":12,"area":null},{"id":"2105.13954","title":"A Gradient Method for Multilevel Optimization","created":"2021-05-28","cited_by_count":12,"area":null},{"id":"2109.13101","title":"Half a Dozen Real-World Applications of Evolutionary Multitasking, and More","created":"2021-09-27","cited_by_count":12,"area":null},{"id":"2301.13501","title":"Auxiliary Learning as an Asymmetric Bargaining Game","created":"2023-01-31","cited_by_count":12,"area":null},{"id":"2101.04849","title":"Probabilistic Metric Learning with Adaptive Margin for Top-K Recommendation","created":"2021-01-13","cited_by_count":11,"area":null},{"id":"2110.00604","title":"Inexact bilevel stochastic gradient methods for constrained and unconstrained lower-level problems","created":"2021-10-01","cited_by_count":11,"area":null},{"id":"2405.17955","title":"Efficient Prior Calibration From Indirect Data","created":"2024-05-28","cited_by_count":11,"area":null},{"id":"2406.14095","title":"Memory-Efficient Gradient Unrolling for Large-Scale Bi-level Optimization","created":"2024-06-20","cited_by_count":11,"area":null},{"id":"2603.15381","title":"Why AI systems don't learn and what to do about it: Lessons on autonomous learning from cognitive science","created":"2026-03-16","cited_by_count":11,"area":null},{"id":"2106.00600","title":"Fair Clustering Using Antidote Data","created":"2021-06-01","cited_by_count":10,"area":null},{"id":"2203.14258","title":"Image quality assessment for machine learning tasks using meta-reinforcement learning","created":"2022-03-27","cited_by_count":10,"area":null},{"id":"2211.07096","title":"Alternating Implicit Projected SGD and Its Efficient Variants for Equality-constrained Bilevel Optimization","created":"2022-11-14","cited_by_count":10,"area":null},{"id":"2305.14851","title":"Sharpness-Aware Data Poisoning Attack","created":"2023-05-24","cited_by_count":10,"area":"safety"},{"id":"2406.12771","title":"First-Order Methods for Linearly Constrained Bilevel Optimization","created":"2024-06-18","cited_by_count":10,"area":null},{"id":"2503.15354","title":"Optimizing Decomposition for Optimal Claim Verification","created":"2025-03-19","cited_by_count":10,"area":null},{"id":"2106.06932","title":"Characterizing the Gap Between Actor-Critic and Policy Gradient","created":"2021-06-13","cited_by_count":9,"area":null},{"id":"2203.13663","title":"FedGradNorm: Personalized Federated Gradient-Normalized Multi-Task Learning","created":"2022-03-24","cited_by_count":9,"area":null},{"id":"2410.16432","title":"Fair Bilevel Neural Network (FairBiNN): On Balancing fairness and accuracy via Stackelberg Equilibrium","created":"2024-10-21","cited_by_count":9,"area":null},{"id":"2202.09798","title":"Image quality assessment by overlapping task-specific and task-agnostic measures: application to prostate multiparametric MR images for cancer segmentation","created":"2022-02-20","cited_by_count":8,"area":null},{"id":"2402.16338","title":"BLO-SAM: Bi-level Optimization Based Overfitting-Preventing Finetuning of SAM","created":"2024-02-26","cited_by_count":8,"area":null},{"id":"2403.13037","title":"BiLoRA: A Bi-level Optimization Framework for Overfitting-Resilient Low-Rank Adaptation of Large Pre-trained Models","created":"2024-03-19","cited_by_count":8,"area":null},{"id":"2409.18893","title":"HM3: Hierarchical Multi-Objective Model Merging for Pretrained Models","created":"2024-09-27","cited_by_count":8,"area":null},{"id":"2206.02663","title":"TransBO: Hyperparameter Optimization via Two-Phase Transfer Learning","created":"2022-06-06","cited_by_count":7,"area":null},{"id":"2206.11526","title":"A Survey on Learnable Evolutionary Algorithms for Scalable Multiobjective Optimization","created":"2022-06-23","cited_by_count":7,"area":null},{"id":"2401.16777","title":"IN-Flow: Instance Normalization Flow for Non-stationary Time Series Forecasting","created":"2024-01-30","cited_by_count":7,"area":null},{"id":"2405.16837","title":"Enhancing Accuracy in Generative Models via Knowledge Transfer","created":"2024-05-27","cited_by_count":7,"area":null},{"id":"2406.10148","title":"A Primal-Dual-Assisted Penalty Approach to Bilevel Optimization with Coupled Constraints","created":"2024-06-14","cited_by_count":7,"area":null},{"id":"2406.16745","title":"Bandits with Preference Feedback: A Stackelberg Game Perspective","created":"2024-06-24","cited_by_count":7,"area":"alignment"},{"id":"2603.23420","title":"Bilevel Autoresearch: Meta-Autoresearching Itself","created":"2026-03-24","cited_by_count":7,"area":null},{"id":"2204.04817","title":"Effective Mutation Rate Adaptation through Group Elite Selection","created":"2022-04-11","cited_by_count":6,"area":null},{"id":"2305.18394","title":"On Optimal Regularization Parameters via Bilevel Learning","created":"2023-05-28","cited_by_count":6,"area":null},{"id":"2312.11835","title":"Provably Convergent Federated Trilevel Learning","created":"2023-12-19","cited_by_count":6,"area":null},{"id":"2402.14760","title":"Generalizing Reward Modeling for Out-of-Distribution Preference Learning","created":"2024-02-22","cited_by_count":6,"area":"alignment"},{"id":"2204.10231","title":"Handling Imbalanced Classification Problems With Support Vector Machines via Evolutionary Bilevel Optimization","created":"2022-04-21","cited_by_count":5,"area":null},{"id":"2208.06820","title":"Surrogate-assisted Multi-objective Neural Architecture Search for Real-time Semantic Segmentation","created":"2022-08-14","cited_by_count":5,"area":null},{"id":"2210.15371","title":"Meta-Learning Initializations for Interactive Medical Image Registration","created":"2022-10-27","cited_by_count":4,"area":null},{"id":"2404.14649","title":"Bi-CL: A Reinforcement Learning Framework for Robots Coordination Through Bi-level Optimization","created":"2024-04-23","cited_by_count":4,"area":"deeprl"},{"id":"2505.13564","title":"Online Decision-Focused Learning","created":"2025-05-19","cited_by_count":4,"area":null},{"id":"2512.04770","title":"Embodied Co-Design for Rapidly Evolving Agents: Taxonomy, Frontiers, and Challenges","created":"2025-12-04","cited_by_count":4,"area":null},{"id":"2109.13662","title":"DeepPSL: End-to-end perception and reasoning","created":"2021-09-28","cited_by_count":3,"area":null},{"id":"2209.12651","title":"Learning Variational Models with Unrolling and Bilevel Optimization","created":"2022-09-26","cited_by_count":3,"area":null},{"id":"2302.02565","title":"Bi-level Multi-objective Evolutionary Learning: A Case Study on Multi-task Graph Neural Topology Search","created":"2023-02-06","cited_by_count":3,"area":null},{"id":"2307.16304","title":"You Shall Pass: Dealing with the Zero-Gradient Problem in Predict and Optimize for Convex Optimization","created":"2023-07-30","cited_by_count":3,"area":null},{"id":"2309.16487","title":"Towards Poisoning Fair Representations","created":"2023-09-28","cited_by_count":3,"area":"safety"},{"id":"2401.03880","title":"Metaheuristics for (Variable-Size) Mixed Optimization Problems: A Unified Taxonomy and Survey","created":"2024-01-08","cited_by_count":3,"area":null},{"id":"2405.17875","title":"BO4IO: A Bayesian optimization approach to inverse optimization with uncertainty quantification","created":"2024-05-28","cited_by_count":3,"area":null},{"id":"2410.18490","title":"Synth4Seg -- Learning Defect Data Synthesis for Defect Segmentation using Bi-level Optimization","created":"2024-10-24","cited_by_count":3,"area":null},{"id":"2511.07398","title":"Solving bilevel optimization via sequential minimax optimization","created":"2025-11-10","cited_by_count":3,"area":null},{"id":"2210.08452","title":"Efficient Cross-Modal Video Retrieval with Meta-Optimized Frames","created":"2022-10-16","cited_by_count":2,"area":null},{"id":"2312.03807","title":"Achieving ${O}(\\epsilon^{-1.5})$ Complexity in Hessian/Jacobian-free Stochastic Bilevel Optimization","created":"2023-12-06","cited_by_count":2,"area":null},{"id":"2403.12918","title":"Generalizable and Stable Finetuning of Pretrained Language Models on Low-Resource Texts","created":"2024-03-19","cited_by_count":2,"area":null},{"id":"2409.19800","title":"Differentially Private Bilevel Optimization","created":"2024-09-29","cited_by_count":2,"area":null},{"id":"2507.17228","title":"P3SL: Personalized Privacy-Preserving Split Learning on Heterogeneous Edge Devices","created":"2025-07-23","cited_by_count":2,"area":null},{"id":"2606.29582","title":"Bilevel Optimization for Neural Architecture Search","created":"2026-06-28","cited_by_count":2,"area":null},{"id":"2109.01255","title":"Provably Safe Model-Based Meta Reinforcement Learning: An Abstraction-Based Approach","created":"2021-09-03","cited_by_count":1,"area":null},{"id":"2201.11926","title":"Simplifying deflation for non-convex optimization with applications in Bayesian inference and topology optimization","created":"2022-01-28","cited_by_count":1,"area":null},{"id":"2205.02329","title":"Second-Order Sensitivity Analysis for Bilevel Optimization","created":"2022-05-04","cited_by_count":1,"area":null},{"id":"2302.10798","title":"Learning a Consensus Sub-Network with Polarization Regularization and One Pass Training","created":"2023-02-17","cited_by_count":1,"area":null},{"id":"2305.00576","title":"Joint Learning of Policy with Unknown Temporal Constraints for Safe Reinforcement Learning","created":"2023-04-30","cited_by_count":1,"area":null},{"id":"2305.07856","title":"Stackelberg Decision Transformer for Asynchronous Action Coordination in Multi-Agent Systems","created":"2023-05-13","cited_by_count":1,"area":"offlinerl"},{"id":"2306.14861","title":"Leveraging Task Structures for Improved Identifiability in Neural Network Representations","created":"2023-06-26","cited_by_count":1,"area":null},{"id":"2402.15893","title":"Concurrent Learning of Policy and Unknown Safety Constraints in Reinforcement Learning","created":"2024-02-24","cited_by_count":1,"area":"deeprl"},{"id":"2403.04763","title":"BloomGML: Graph Machine Learning through the Lens of Bilevel Optimization","created":"2024-03-07","cited_by_count":1,"area":null},{"id":"2410.19319","title":"Fully First-Order Methods for Decentralized Bilevel Optimization","created":"2024-10-25","cited_by_count":1,"area":null},{"id":"2509.09030","title":"Contextual Learning for Anomaly Detection in Tabular Data","created":"2025-09-10","cited_by_count":1,"area":null},{"id":"2510.21436","title":"AutoOpt: A Dataset and a Unified Framework for Automating Optimization Problem Solving","created":"2025-10-24","cited_by_count":1,"area":null}],"next_cursor":"100"}