{"total":2515,"rows":[{"id":"2212.04488","title":"Multi-Concept Customization of Text-to-Image Diffusion","created":"2022-12-08","cited_by_count":1106,"area":"diffusion"},{"id":"2310.12036","title":"A General Theoretical Paradigm to Understand Learning from Human Preferences","created":"2023-10-18","cited_by_count":912,"area":"alignment"},{"id":"2111.08005","title":"Solving Inverse Problems in Medical Imaging with Score-Based Generative Models","created":"2021-11-15","cited_by_count":521,"area":"diffusion"},{"id":"2312.11456","title":"Iterative Preference Learning from Human Feedback: Bridging Theory and Practice for RLHF under KL-Constraint","created":"2023-12-18","cited_by_count":350,"area":"alignment"},{"id":"2601.20802","title":"Reinforcement Learning via Self-Distillation","created":"2026-01-28","cited_by_count":332,"area":"lr"},{"id":"2410.19115","title":"MoGe: Unlocking Accurate Monocular Geometry Estimation for Open-Domain Images with Optimal Training Supervision","created":"2024-10-24","cited_by_count":299,"area":null},{"id":"2106.07594","title":"Graph Contrastive Learning Automated","created":"2021-06-10","cited_by_count":287,"area":null},{"id":"2406.07496","title":"TextGrad: Automatic \"Differentiation\" via Text","created":"2024-06-11","cited_by_count":273,"area":null},{"id":"2305.14342","title":"Sophia: A Scalable Stochastic Second-order Optimizer for Language Model Pre-training","created":"2023-05-23","cited_by_count":265,"area":null},{"id":"2310.02743","title":"Reward Model Ensembles Help Mitigate Overoptimization","created":"2023-10-04","cited_by_count":231,"area":"alignment"},{"id":"2202.05607","title":"Online Decision Transformer","created":"2022-02-11","cited_by_count":196,"area":"offlinerl"},{"id":"2205.10330","title":"A Review of Safe Reinforcement Learning: Methods, Theory and Applications","created":"2022-05-20","cited_by_count":181,"area":null},{"id":"2402.10207","title":"Rewards-in-Context: Multi-objective Alignment of Foundation Models with Dynamic Preference Adjustment","created":"2024-02-15","cited_by_count":175,"area":"alignment"},{"id":"2205.11172","title":"How Powerful are Spectral Graph Neural Networks","created":"2022-05-23","cited_by_count":169,"area":null},{"id":"2106.04538","title":"What Makes Multi-modal Learning Better than Single (Provably)","created":"2021-06-08","cited_by_count":153,"area":null},{"id":"2209.08037","title":"DAGMA: Learning DAGs via M-matrices and a Log-Determinant Acyclicity Characterization","created":"2022-09-16","cited_by_count":140,"area":null},{"id":"2212.04612","title":"Training Data Influence Analysis and Estimation: A Survey","created":"2022-12-09","cited_by_count":135,"area":null},{"id":"2303.00566","title":"Structured Pruning for Deep Convolutional Neural Networks: A survey","created":"2023-03-01","cited_by_count":122,"area":null},{"id":"2106.10783","title":"OptiDICE: Offline Policy Optimization via Stationary Distribution Correction Estimation","created":"2021-06-21","cited_by_count":121,"area":"offlinerl"},{"id":"2201.07443","title":"On the Convergence Rates of Policy Gradient Methods","created":"2022-01-19","cited_by_count":119,"area":null},{"id":"2311.01453","title":"PPI++: Efficient Prediction-Powered Inference","created":"2023-11-02","cited_by_count":117,"area":null},{"id":"2303.15810","title":"Offline RL with No OOD Actions: In-Sample Learning via Implicit Value Regularization","created":"2023-03-28","cited_by_count":116,"area":"offlinerl"},{"id":"2106.11342","title":"Dive into Deep Learning","created":"2021-06-21","cited_by_count":111,"area":null},{"id":"2404.18239","title":"SOUL: Unlocking the Power of Second-Order Optimization for LLM Unlearning","created":"2024-04-28","cited_by_count":104,"area":"safety"},{"id":"2201.12091","title":"Linear Adversarial Concept Erasure","created":"2022-01-28","cited_by_count":101,"area":null},{"id":"2310.00429","title":"On the Stability of Iterative Retraining of Generative Models on their own Data","created":"2023-09-30","cited_by_count":100,"area":null},{"id":"2111.13839","title":"Towards Principled Disentanglement for Domain Generalization","created":"2021-11-27","cited_by_count":91,"area":null},{"id":"2301.02280","title":"Filtering, Distillation, and Hard Negatives for Vision-Language Pre-Training","created":"2023-01-05","cited_by_count":91,"area":"mllm"},{"id":"2403.08635","title":"Human Alignment of Large Language Models through Online Preference Optimisation","created":"2024-03-13","cited_by_count":91,"area":"alignment"},{"id":"2202.00817","title":"Do Differentiable Simulators Give Better Policy Gradients?","created":"2022-02-02","cited_by_count":89,"area":null},{"id":"2305.13035","title":"Getting ViT in Shape: Scaling Laws for Compute-Optimal Model Design","created":"2023-05-22","cited_by_count":89,"area":null},{"id":"2206.04920","title":"Fisher SAM: Information Geometry and Sharpness Aware Minimisation","created":"2022-06-10","cited_by_count":84,"area":null},{"id":"2202.00665","title":"Tutorial on amortized optimization","created":"2022-02-01","cited_by_count":83,"area":null},{"id":"2502.11221","title":"PlanGenLLMs: A Modern Survey of LLM Planning Capabilities","created":"2025-02-16","cited_by_count":83,"area":null},{"id":"2208.11195","title":"Robustness to Unbounded Smoothness of Generalized SignSGD","created":"2022-08-23","cited_by_count":81,"area":null},{"id":"2401.14461","title":"Marabou 2.0: A Versatile Formal Analyzer of Neural Networks","created":"2024-01-25","cited_by_count":81,"area":null},{"id":"2402.02030","title":"Panacea: Pareto Alignment via Preference Adaptation for LLMs","created":"2024-02-03","cited_by_count":80,"area":"alignment"},{"id":"2110.13715","title":"ConE: Cone Embeddings for Multi-Hop Reasoning over Knowledge Graphs","created":"2021-10-26","cited_by_count":78,"area":null},{"id":"2403.13117","title":"Optimal Flow Matching: Learning Straight Trajectories in Just One Step","created":"2024-03-19","cited_by_count":78,"area":"diffusion"},{"id":"2306.00148","title":"SafeDiffuser: Safe Planning with Diffusion Probabilistic Models","created":"2023-05-31","cited_by_count":75,"area":"diffusion"},{"id":"2109.05389","title":"Omnipredictors","created":"2021-09-11","cited_by_count":74,"area":null},{"id":"2501.12352","title":"Test-time regression: a unifying framework for designing sequence models with associative memory","created":"2025-01-21","cited_by_count":74,"area":null},{"id":"2502.12892","title":"Archetypal SAE: Adaptive and Stable Dictionary Learning for Concept Extraction in Large Vision Models","created":"2025-02-18","cited_by_count":73,"area":"mechinterp"},{"id":"2301.06197","title":"Who Should Predict? Exact Algorithms For Learning to Defer to Humans","created":"2023-01-15","cited_by_count":70,"area":null},{"id":"2112.11256","title":"Tackling System and Statistical Heterogeneity for Federated Learning with Adaptive Client Sampling","created":"2021-12-21","cited_by_count":66,"area":null},{"id":"2206.03023","title":"How Far I'll Go: Offline Goal-Conditioned Reinforcement Learning via $f$-Advantage Regression","created":"2022-06-07","cited_by_count":66,"area":"offlinerl"},{"id":"2207.09944","title":"Probable Domain Generalization via Quantile Risk Minimization","created":"2022-07-20","cited_by_count":66,"area":null},{"id":"2302.01772","title":"Fixing by Mixing: A Recipe for Optimal Byzantine ML under Heterogeneity","created":"2023-02-03","cited_by_count":65,"area":null},{"id":"2203.07034","title":"Active Learning by Feature Mixing","created":"2022-03-14","cited_by_count":63,"area":null},{"id":"2205.12173","title":"Byzantine Machine Learning Made Easy by Resilient Averaging of Momentums","created":"2022-05-24","cited_by_count":63,"area":null},{"id":"2304.05364","title":"Diffusion Models for Constrained Domains","created":"2023-04-11","cited_by_count":63,"area":"diffusion"},{"id":"2210.08649","title":"Loss Minimization through the Lens of Outcome Indistinguishability","created":"2022-10-16","cited_by_count":62,"area":null},{"id":"2110.14177","title":"Federated Linear Contextual Bandits","created":"2021-10-27","cited_by_count":61,"area":null},{"id":"2110.03237","title":"Score-based Generative Neural Networks for Large-Scale Optimal Transport","created":"2021-10-07","cited_by_count":60,"area":null},{"id":"2207.13887","title":"Adaptive Second Order Coresets for Data-efficient Machine Learning","created":"2022-07-28","cited_by_count":60,"area":null},{"id":"2209.11379","title":"Do Current Multi-Task Optimization Methods in Deep Learning Even Help?","created":"2022-09-23","cited_by_count":60,"area":null},{"id":"2202.08312","title":"Improved Differential Privacy for SGD via Optimal Private Linear Operators on Adaptive Streams","created":"2022-02-16","cited_by_count":59,"area":null},{"id":"2209.07089","title":"Constrained Update Projection Approach to Safe Policy Optimization","created":"2022-09-15","cited_by_count":58,"area":null},{"id":"2112.11313","title":"On the Adversarial Robustness of Causal Algorithmic Recourse","created":"2021-12-21","cited_by_count":56,"area":null},{"id":"2307.07176","title":"SafeDreamer: Safe Reinforcement Learning with World Models","created":"2023-07-14","cited_by_count":54,"area":"wm"},{"id":"2402.19078","title":"Smooth Tchebycheff Scalarization for Multi-Objective Optimization","created":"2024-02-29","cited_by_count":54,"area":null},{"id":"2407.07880","title":"Towards Robust Alignment of Language Models: Distributionally Robustifying Direct Preference Optimization","created":"2024-07-10","cited_by_count":53,"area":"alignment"},{"id":"2506.04171","title":"Physics-Constrained Flow Matching: Sampling Generative Models with Hard Constraints","created":"2025-06-04","cited_by_count":52,"area":"diffusion"},{"id":"2210.08495","title":"Pareto Set Learning for Expensive Multi-Objective Optimization","created":"2022-10-16","cited_by_count":51,"area":null},{"id":"2110.03677","title":"Large Learning Rate Tames Homogeneity: Convergence and Balancing Effect","created":"2021-10-07","cited_by_count":50,"area":null},{"id":"2205.02640","title":"Model-Based Deep Learning: On the Intersection of Deep Learning and Optimization","created":"2022-05-05","cited_by_count":50,"area":null},{"id":"2302.04040","title":"Sample-efficient Multi-objective Molecular Optimization with GFlowNets","created":"2023-02-08","cited_by_count":50,"area":null},{"id":"2402.09631","title":"Representation Surgery: Theory and Practice of Affine Steering","created":"2024-02-15","cited_by_count":50,"area":null},{"id":"2302.05103","title":"Controllability-Aware Unsupervised Skill Discovery","created":"2023-02-10","cited_by_count":49,"area":null},{"id":"2306.13461","title":"Understanding quantum machine learning also requires rethinking generalization","created":"2023-06-23","cited_by_count":49,"area":null},{"id":"2403.02475","title":"Enhancing LLM Safety via Constrained Direct Preference Optimization","created":"2024-03-04","cited_by_count":49,"area":"alignment"},{"id":"2502.11102","title":"OptMATH: A Scalable Bidirectional Data Synthesis Framework for Optimization Modeling","created":"2025-02-16","cited_by_count":49,"area":"synth"},{"id":"2201.12191","title":"Kernelized Concept Erasure","created":"2022-01-28","cited_by_count":48,"area":null},{"id":"2411.01679","title":"Autoformulation of Mathematical Optimization Models Using LLMs","created":"2024-11-03","cited_by_count":48,"area":null},{"id":"2106.11344","title":"f-Domain-Adversarial Learning: Theory and Algorithms","created":"2021-06-21","cited_by_count":47,"area":null},{"id":"2307.14023","title":"Are Transformers with One Layer Self-Attention Using Low-Rank Weight Matrices Universal Approximators?","created":"2023-07-26","cited_by_count":47,"area":null},{"id":"2404.01730","title":"Asymptotics of Language Model Alignment","created":"2024-04-02","cited_by_count":47,"area":"alignment"},{"id":"2202.00089","title":"Understanding AdamW through Proximal Methods and Scale-Freeness","created":"2022-01-31","cited_by_count":46,"area":null},{"id":"2406.09405","title":"Why Warmup the Learning Rate? Underlying Mechanisms and Improvements","created":"2024-06-13","cited_by_count":46,"area":null},{"id":"2206.05282","title":"Learning to Estimate Shapley Values with Vision Transformers","created":"2022-06-10","cited_by_count":45,"area":null},{"id":"2403.01131","title":"LLaMoCo: Instruction Tuning of Large Language Models for Optimization Code Generation","created":"2024-03-02","cited_by_count":45,"area":null},{"id":"2505.24873","title":"MiniMax-Remover: Taming Bad Noise Helps Video Object Removal","created":"2025-05-30","cited_by_count":45,"area":"diffusion"},{"id":"2211.14666","title":"Synergies between Disentanglement and Sparsity: Generalization and Identifiability in Multi-Task Learning","created":"2022-11-26","cited_by_count":44,"area":null},{"id":"2306.01264","title":"Convex and Non-convex Optimization Under Generalized Smoothness","created":"2023-06-02","cited_by_count":44,"area":null},{"id":"2403.07362","title":"Challenging Forgets: Unveiling the Worst-Case Forget Sets in Machine Unlearning","created":"2024-03-12","cited_by_count":44,"area":"safety"},{"id":"2107.00940","title":"Inverse-Dirichlet Weighting Enables Reliable Training of Physics Informed Neural Networks","created":"2021-07-02","cited_by_count":43,"area":null},{"id":"2202.02433","title":"Versatile Offline Imitation from Observations and Examples via Regularized State-Occupancy Matching","created":"2022-02-04","cited_by_count":43,"area":"offlinerl"},{"id":"2106.15093","title":"Certifiable Machine Unlearning for Linear Models","created":"2021-06-29","cited_by_count":42,"area":"safety"},{"id":"2403.06279","title":"Fine-tuning of diffusion models via stochastic control: entropy regularization and beyond","created":"2024-03-10","cited_by_count":42,"area":"diffusion"},{"id":"2407.20109","title":"Diffusion-DICE: In-Sample Diffusion Guidance for Offline Reinforcement Learning","created":"2024-07-29","cited_by_count":42,"area":"diffusion"},{"id":"2201.01985","title":"Jointly Efficient and Optimal Algorithms for Logistic Bandits","created":"2022-01-06","cited_by_count":41,"area":null},{"id":"2312.10299","title":"Image Restoration Through Generalized Ornstein-Uhlenbeck Bridge","created":"2023-12-16","cited_by_count":41,"area":"diffusion"},{"id":"2407.10834","title":"MetaLLM: A High-performant and Cost-efficient Dynamic Framework for Wrapping LLMs","created":"2024-07-15","cited_by_count":41,"area":null},{"id":"2502.04664","title":"Implicit Bias of Spectral Descent and Muon on Multiclass Separable Data","created":"2025-02-07","cited_by_count":41,"area":null},{"id":"2308.02585","title":"PARL: A Unified Framework for Policy Alignment in Reinforcement Learning from Human Feedback","created":"2023-08-03","cited_by_count":40,"area":"alignment"},{"id":"2203.05816","title":"No Free Lunch Theorem for Security and Utility in Federated Learning","created":"2022-03-11","cited_by_count":39,"area":null},{"id":"2310.05351","title":"Generalized Neural Collapse for a Large Number of Classes","created":"2023-10-09","cited_by_count":39,"area":null},{"id":"2310.06116","title":"OptiMUS: Optimization Modeling Using MIP Solvers and large language models","created":"2023-10-09","cited_by_count":39,"area":null},{"id":"2405.16587","title":"Cost-Effective Online Multi-LLM Selection with Versatile Reward Models","created":"2024-05-26","cited_by_count":39,"area":"alignment"},{"id":"2502.12668","title":"Evaluation of Best-of-N Sampling Strategies for Language Model Alignment","created":"2025-02-18","cited_by_count":39,"area":"alignment"}],"next_cursor":"100"}