{"total":142,"rows":[{"id":"2202.08791","title":"cosFormer: Rethinking Softmax in Attention","created":"2022-02-17","cited_by_count":213,"area":"lr"},{"id":"2211.03375","title":"AlphaPose: Whole-Body Regional Multi-Person Pose Estimation and Tracking in Real-Time","created":"2022-11-07","cited_by_count":200,"area":null},{"id":"2202.03036","title":"Structure-Aware Transformer for Graph Representation Learning","created":"2022-02-07","cited_by_count":194,"area":null},{"id":"2210.10340","title":"The Devil in Linear Transformer","created":"2022-10-19","cited_by_count":98,"area":null},{"id":"2106.09296","title":"Voice2Series: Reprogramming Acoustic Models for Time Series Classification","created":"2021-06-17","cited_by_count":91,"area":null},{"id":"2110.11316","title":"CLOOB: Modern Hopfield Networks with InfoLOOB Outperform CLIP","created":"2021-10-21","cited_by_count":89,"area":null},{"id":"2305.11097","title":"Statistical Foundations of Prior-Data Fitted Networks","created":"2023-05-18","cited_by_count":65,"area":null},{"id":"2101.09315","title":"Tighter expected generalization error bounds via Wasserstein distance","created":"2021-01-22","cited_by_count":43,"area":null},{"id":"2309.12673","title":"On Sparse Modern Hopfield Model","created":"2023-09-22","cited_by_count":42,"area":null},{"id":"2403.16843","title":"Do LLM Agents Have Regret? A Case Study in Online Learning and Games","created":"2024-03-25","cited_by_count":35,"area":"agents"},{"id":"2305.17431","title":"Towards Consistent Video Editing with Text-to-Image Diffusion Models","created":"2023-05-27","cited_by_count":34,"area":"diffusion"},{"id":"2309.05911","title":"Quality-Agnostic Deepfake Detection with Intra-model Collaborative Learning","created":"2023-09-12","cited_by_count":32,"area":null},{"id":"2510.14973","title":"Attention Is All You Need for KV Cache in Diffusion LLMs","created":"2025-10-16","cited_by_count":32,"area":"inference"},{"id":"2401.15273","title":"Finite-Time Analysis of On-Policy Heterogeneous Federated Reinforcement Learning","created":"2024-01-27","cited_by_count":31,"area":"deeprl"},{"id":"2110.12351","title":"Integrated Conditional Estimation-Optimization","created":"2021-10-24","cited_by_count":25,"area":null},{"id":"2502.18508","title":"REFINE: Inversion-Free Backdoor Defense via Model Reprogramming","created":"2025-02-22","cited_by_count":22,"area":null},{"id":"2510.23012","title":"Softmax is $1/2$-Lipschitz: A tight bound across all $\\ell_p$ norms","created":"2025-10-27","cited_by_count":22,"area":null},{"id":"2112.13776","title":"Transformer Uncertainty Estimation with Hierarchical Stochastic Attention","created":"2021-12-27","cited_by_count":21,"area":null},{"id":"2305.19562","title":"Replicability in Reinforcement Learning","created":"2023-05-31","cited_by_count":21,"area":null},{"id":"2208.11639","title":"Oracle-free Reinforcement Learning in Mean-Field Games along a Single Sample Path","created":"2022-08-24","cited_by_count":20,"area":null},{"id":"2303.10139","title":"Distill n' Explain: explaining graph neural networks using simple surrogates","created":"2023-03-17","cited_by_count":18,"area":null},{"id":"2308.12383","title":"With a Little Help from your own Past: Prototypical Memory Networks for Image Captioning","created":"2023-08-23","cited_by_count":18,"area":null},{"id":"2207.13955","title":"Neural Architecture Search on Efficient Transformers and Beyond","created":"2022-07-28","cited_by_count":17,"area":null},{"id":"2303.13429","title":"Interacting Particle Langevin Algorithm for Maximum Marginal Likelihood Estimation","created":"2023-03-23","cited_by_count":17,"area":null},{"id":"2206.07801","title":"Beyond Adult and COMPAS: Fairness in Multi-Class Prediction","created":"2022-06-15","cited_by_count":16,"area":null},{"id":"2405.14131","title":"Statistical Advantages of Perturbing Cosine Router in Mixture of Experts","created":"2024-05-23","cited_by_count":16,"area":"moe"},{"id":"2210.07998","title":"$\\Lambda$-DARTS: Mitigating Performance Collapse by Harmonizing Operation Selection among Cells","created":"2022-10-14","cited_by_count":15,"area":null},{"id":"2303.03100","title":"A Finite-Sample Analysis of Payoff-Based Independent Learning in Zero-Sum Stochastic Games","created":"2023-03-03","cited_by_count":15,"area":null},{"id":"2204.14174","title":"Explainable AI via Learning to Optimize","created":"2022-04-29","cited_by_count":14,"area":null},{"id":"2401.08865","title":"The Effect of Intrinsic Dataset Properties on Generalization: Unraveling Learning Differences Between Natural and Medical Images","created":"2024-01-16","cited_by_count":13,"area":null},{"id":"2410.10051","title":"Towards Bridging Generalization and Expressivity of Graph Neural Networks","created":"2024-10-14","cited_by_count":12,"area":null},{"id":"2505.00926","title":"How Transformers Learn Regular Language Recognition: A Theoretical Study on Training Dynamics and Implicit Bias","created":"2025-05-02","cited_by_count":11,"area":null},{"id":"2507.07814","title":"Pay Attention to Attention Distribution: A New Local Lipschitz Bound for Transformers","created":"2025-07-10","cited_by_count":11,"area":null},{"id":"2302.02392","title":"Offline Minimax Soft-Q-learning Under Realizability and Partial Coverage","created":"2023-02-05","cited_by_count":10,"area":"offlinerl"},{"id":"2502.08958","title":"Biologically Plausible Brain Graph Transformer","created":"2025-02-13","cited_by_count":10,"area":null},{"id":"2111.05073","title":"MixACM: Mixup-Based Robustness Transfer via Distillation of Activated Channel Maps","created":"2021-11-09","cited_by_count":9,"area":null},{"id":"2303.04865","title":"Convergence Rates for Localized Actor-Critic in Networked Markov Potential Games","created":"2023-03-08","cited_by_count":9,"area":null},{"id":"2311.01059","title":"Adapt On-the-Go: Behavior Modulation for Single-Life Robot Deployment","created":"2023-11-02","cited_by_count":8,"area":null},{"id":"2406.14292","title":"Proximal Interacting Particle Langevin Algorithms","created":"2024-06-20","cited_by_count":8,"area":null},{"id":"2505.13499","title":"Optimal Control for Transformer Architectures: Enhancing Generalization, Robustness and Efficiency","created":"2025-05-16","cited_by_count":8,"area":null},{"id":"2109.06362","title":"Theoretical Guarantees of Fictitious Discount Algorithms for Episodic Reinforcement Learning and Global Convergence of Policy Gradient Methods","created":"2021-09-13","cited_by_count":7,"area":null},{"id":"2307.16236","title":"Synaptic Plasticity Models and Bio-Inspired Unsupervised Deep Learning: A Survey","created":"2023-07-30","cited_by_count":7,"area":null},{"id":"2602.19799","title":"Path-conditioned training: a principled way to rescale ReLU neural networks","created":"2026-02-23","cited_by_count":6,"area":null},{"id":"2207.05161","title":"What is Flagged in Uncertainty Quantification? Latent Density Models for Uncertainty Categorization","created":"2022-07-11","cited_by_count":5,"area":null},{"id":"2311.00858","title":"SmoothHess: ReLU Network Feature Interactions via Stein's Lemma","created":"2023-11-01","cited_by_count":5,"area":null},{"id":"2405.08005","title":"Graphon Mean Field Games with a Representative Player: Analysis and Learning Algorithm","created":"2024-05-08","cited_by_count":5,"area":null},{"id":"2406.01189","title":"MultiMax: Sparse and Multi-Modal Attention Learning","created":"2024-06-03","cited_by_count":5,"area":null},{"id":"2407.15453","title":"Regression under demographic parity constraints via unlabeled post-processing","created":"2024-07-22","cited_by_count":5,"area":null},{"id":"2408.08192","title":"Stochastic Semi-Gradient Descent for Learning Mean Field Games with Population-Aware Function Approximation","created":"2024-08-15","cited_by_count":5,"area":null},{"id":"2505.19946","title":"Inverse Q-Learning Done Right: Offline Imitation Learning in $Q^\\pi$-Realizable MDPs","created":"2025-05-26","cited_by_count":5,"area":"offlinerl"},{"id":"2510.09904","title":"Stability of Transformers under Layer Normalization","created":"2025-10-10","cited_by_count":5,"area":null},{"id":"2602.05230","title":"ZeroS: Zero-Sum Linear Attention for Efficient Transformers","created":"2026-02-05","cited_by_count":5,"area":null},{"id":"2605.08689","title":"Structure-Centric Graph Foundation Model via Geometric Bases","created":"2026-05-09","cited_by_count":5,"area":null},{"id":"2112.11928","title":"A Stochastic Bregman Primal-Dual Splitting Algorithm for Composite Optimization","created":"2021-12-22","cited_by_count":4,"area":null},{"id":"2302.09703","title":"Reinforcement Learning with Function Approximation: From Linear to Nonlinear","created":"2023-02-20","cited_by_count":4,"area":null},{"id":"2303.17655","title":"Q-Learning based system for path planning with unmanned aerial vehicles swarms in obstacle environments","created":"2023-03-30","cited_by_count":4,"area":null},{"id":"2306.07926","title":"A Theory of Unsupervised Speech Recognition","created":"2023-06-09","cited_by_count":4,"area":null},{"id":"2405.19222","title":"Lower Bounds on the Expressivity of Recurrent Neural Language Models","created":"2024-05-29","cited_by_count":4,"area":null},{"id":"2206.05997","title":"Analysis of function approximation and stability of general DNNs in directed acyclic graphs using un-rectifying analysis","created":"2022-06-13","cited_by_count":3,"area":null},{"id":"2207.09090","title":"Actor-Critic based Improper Reinforcement Learning","created":"2022-07-19","cited_by_count":3,"area":null},{"id":"2208.01148","title":"Boosted Off-Policy Learning","created":"2022-08-01","cited_by_count":3,"area":null},{"id":"2304.14831","title":"Earning Extra Performance from Restrictive Feedbacks","created":"2023-04-28","cited_by_count":3,"area":null},{"id":"2401.03540","title":"SeTformer is What You Need for Vision and Language","created":"2024-01-07","cited_by_count":3,"area":null},{"id":"2404.08566","title":"Mitigating Receiver Impact on Radio Frequency Fingerprint Identification via Domain Adaptation","created":"2024-04-12","cited_by_count":3,"area":null},{"id":"2406.02329","title":"On Affine Homotopy between Language Encoders","created":"2024-06-04","cited_by_count":3,"area":null},{"id":"2503.07691","title":"Fair Text Classification via Transferable Representations","created":"2025-03-10","cited_by_count":3,"area":null},{"id":"2505.19525","title":"Rethinking Gating Mechanism in Sparse MoE: Handling Arbitrary Modality Inputs with Confidence-Guided Gate","created":"2025-05-26","cited_by_count":3,"area":"moe"},{"id":"2602.18849","title":"Exact Attention Sensitivity and the Geometry of Transformer Stability","created":"2026-02-21","cited_by_count":3,"area":null},{"id":"2602.23353","title":"SOTAlign: Semi-Supervised Alignment of Unimodal Vision and Language Models via Optimal Transport","created":"2026-02-26","cited_by_count":3,"area":null},{"id":"2101.00153","title":"Graphmax for Text Generation","created":"2021-01-01","cited_by_count":2,"area":null},{"id":"2107.01081","title":"Neural Network Layer Algebra: A Framework to Measure Capacity and Compression in Deep Learning","created":"2021-07-02","cited_by_count":2,"area":null},{"id":"2303.07203","title":"On the Robustness of Text Vectorizers","created":"2023-03-09","cited_by_count":2,"area":null},{"id":"2312.08008","title":"Learning in Zero-Sum Markov Games: Relaxing Strong Reachability and Mixing Time Assumptions","created":"2023-12-13","cited_by_count":2,"area":null},{"id":"2401.07646","title":"Multifractal-spectral features enhance classification of anomalous diffusion","created":"2024-01-15","cited_by_count":2,"area":null},{"id":"2403.08906","title":"Strategizing against Q-learners: A Control-theoretical Approach","created":"2024-03-13","cited_by_count":2,"area":"deeprl"},{"id":"2405.03718","title":"A Single Online Agent Can Efficiently Learn Mean Field Games","created":"2024-05-05","cited_by_count":2,"area":null},{"id":"2505.15661","title":"Deep greedy unfolding: Sorting out argsorting in greedy sparse recovery algorithms","created":"2025-05-21","cited_by_count":2,"area":null},{"id":"2510.26566","title":"Multiclass Local Calibration with the Jensen-Shannon Distance","created":"2025-10-30","cited_by_count":2,"area":null},{"id":"2511.04217","title":"The Strong Lottery Ticket Hypothesis for Multi-Head Attention Mechanisms","created":"2025-11-06","cited_by_count":2,"area":null},{"id":"2511.21056","title":"Bilevel Data Curation for LLM Fine-tuning: Offline Selection and Online Self-Refining Generation","created":"2025-11-26","cited_by_count":2,"area":null},{"id":"2512.04745","title":"An Energy-Based Mechanism for Compositional Behavior","created":"2025-12-04","cited_by_count":2,"area":null},{"id":"2601.09588","title":"Energy-Entropy Regularization: The True Power of Minimal Looped Transformers","created":"2026-01-14","cited_by_count":2,"area":"lr"},{"id":"2605.29327","title":"Reasoning-preserved Efficient Distillation of Large Language Models via Activation-aware Initialization","created":"2026-05-28","cited_by_count":2,"area":"lr"},{"id":"2608.04074","title":"Spend Bits Where Queries Look: KV Cache Vector Quantization with Attention-Preserving Transforms","created":"2026-08-04","cited_by_count":2,"area":"inference"},{"id":"2103.15367","title":"Joint User Association and Power Allocation in Heterogeneous Ultra Dense Network via Semi-Supervised Representation Learning","created":"2021-03-29","cited_by_count":1,"area":null},{"id":"2202.08876","title":"An alternative approach to train neural networks using monotone variational inequality","created":"2022-02-17","cited_by_count":1,"area":null},{"id":"2208.05152","title":"TagRec++: Hierarchical Label Aware Attention Network for Question Categorization","created":"2022-08-10","cited_by_count":1,"area":null},{"id":"2211.05580","title":"Hyperbolic Cosine Transformer for LiDAR 3D Object Detection","created":"2022-11-10","cited_by_count":1,"area":null},{"id":"2211.10629","title":"Unifying Label-inputted Graph Neural Networks with Deep Equilibrium Models","created":"2022-11-19","cited_by_count":1,"area":null},{"id":"2302.09806","title":"Logit-Q Dynamics for Efficient Learning in Stochastic Teams","created":"2023-02-20","cited_by_count":1,"area":null},{"id":"2401.11365","title":"Confidence Preservation Property in Knowledge Distillation Abstractions","created":"2024-01-21","cited_by_count":1,"area":"safety"},{"id":"2404.15829","title":"Accelerating Cavity Fault Prediction Using Deep Learning at Jefferson Laboratory","created":"2024-04-24","cited_by_count":1,"area":null},{"id":"2405.18828","title":"CHANI: Correlation-based Hawkes Aggregation of Neurons with bio-Inspiration","created":"2024-05-29","cited_by_count":1,"area":null},{"id":"2406.01149","title":"Agnostic Learning of Mixed Linear Regressions with EM and AM Algorithms","created":"2024-06-03","cited_by_count":1,"area":null},{"id":"2409.02663","title":"Generalized Individual Q-learning for Polymatrix Games with Partial Observations","created":"2024-09-04","cited_by_count":1,"area":"deeprl"},{"id":"2410.09701","title":"Transformers as Game Players: Provable In-context Game-playing Capabilities of Pre-trained Models","created":"2024-10-13","cited_by_count":1,"area":null},{"id":"2501.13428","title":"Softplus Attention with Re-weighting Boosts Length Extrapolation in Large Language Models","created":"2025-01-23","cited_by_count":1,"area":null},{"id":"2506.17242","title":"Differentiable neural network representation of multi-well, locally-convex potentials","created":"2025-06-06","cited_by_count":1,"area":null},{"id":"2509.23135","title":"Trust Region Reward Optimization and Proximal Inverse Reward Optimization Algorithm","created":"2025-09-27","cited_by_count":1,"area":"offlinerl"},{"id":"2510.02049","title":"Mathematical Modeling and Convergence Analysis of Deep Neural Networks with Dense Layer Connectivities in Deep Learning","created":"2025-10-02","cited_by_count":1,"area":null}],"next_cursor":"100"}