{"total":189,"rows":[{"id":"2401.18079","title":"KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization","created":"2024-01-31","cited_by_count":591,"area":"inference"},{"id":"2105.12806","title":"A Universal Law of Robustness via Isoperimetry","created":"2021-05-26","cited_by_count":151,"area":null},{"id":"2202.02643","title":"The Unreasonable Effectiveness of Random Pruning: Return of the Most Naive Baseline for Sparse Training","created":"2022-02-05","cited_by_count":85,"area":null},{"id":"2105.14602","title":"On the geometry of generalization and memorization in deep neural networks","created":"2021-05-30","cited_by_count":73,"area":null},{"id":"2106.14342","title":"Stabilizing Equilibrium Models by Jacobian Regularization","created":"2021-06-28","cited_by_count":72,"area":null},{"id":"2211.12316","title":"Simplicity Bias in Transformers and their Ability to Learn Sparse Boolean Functions","created":"2022-11-22","cited_by_count":70,"area":null},{"id":"2103.05127","title":"Model Complexity of Deep Learning: A Survey","created":"2021-03-08","cited_by_count":65,"area":null},{"id":"2311.17295","title":"Elo Uncovered: Robustness and Best Practices in Language Model Evaluation","created":"2023-11-29","cited_by_count":61,"area":null},{"id":"2106.01606","title":"Exploring Memorization in Adversarial Training","created":"2021-06-03","cited_by_count":55,"area":null},{"id":"2402.15555","title":"Deep Networks Always Grok and Here is Why","created":"2024-02-23","cited_by_count":51,"area":null},{"id":"2102.11492","title":"DeepThermal: Combustion Optimization for Thermal Power Generating Units Using Offline Reinforcement Learning","created":"2021-02-23","cited_by_count":48,"area":"offlinerl"},{"id":"2111.06236","title":"Discovering and Explaining the Representation Bottleneck of DNNs","created":"2021-11-11","cited_by_count":42,"area":null},{"id":"2209.13083","title":"Why neural networks find simple solutions: the many regularizers of geometric complexity","created":"2022-09-27","cited_by_count":39,"area":null},{"id":"2305.00241","title":"When Deep Learning Meets Polyhedral Theory: A Survey","created":"2023-04-29","cited_by_count":39,"area":null},{"id":"2303.10837","title":"FedML-HE: An Efficient Homomorphic-Encryption-Based Privacy-Preserving Federated Learning System","created":"2023-03-20","cited_by_count":38,"area":null},{"id":"2107.11228","title":"Taxonomizing local versus global structure in neural network loss landscapes","created":"2021-07-23","cited_by_count":34,"area":null},{"id":"2211.12312","title":"Interpreting Neural Networks through the Polytope Lens","created":"2022-11-22","cited_by_count":33,"area":"mechinterp"},{"id":"2107.04835","title":"Noise Stability Regularization for Improving BERT Fine-tuning","created":"2021-07-10","cited_by_count":29,"area":null},{"id":"2104.10343","title":"Sensitivity as a Complexity Measure for Sequence Classification Tasks","created":"2021-04-21","cited_by_count":28,"area":null},{"id":"2110.10232","title":"Test time Adaptation through Perturbation Robustness","created":"2021-10-19","cited_by_count":28,"area":null},{"id":"2110.02180","title":"Noisy Feature Mixup","created":"2021-10-05","cited_by_count":27,"area":null},{"id":"2105.03193","title":"Network Pruning That Matters: A Case Study on Retraining Variants","created":"2021-05-07","cited_by_count":25,"area":null},{"id":"2207.06415","title":"The Free Energy Principle for Perception and Action: A Deep Learning Perspective","created":"2022-07-13","cited_by_count":24,"area":null},{"id":"2310.08847","title":"On the Over-Memorization During Natural, Robust and Catastrophic Overfitting","created":"2023-10-13","cited_by_count":20,"area":null},{"id":"2205.07019","title":"Evaluating the Generalization Ability of Super-Resolution Networks","created":"2022-05-14","cited_by_count":18,"area":null},{"id":"2409.11697","title":"Monomial Matrix Group Equivariant Neural Functional Networks","created":"2024-09-18","cited_by_count":17,"area":null},{"id":"2410.21853","title":"Learning Infinitesimal Generators of Continuous Symmetries from Data","created":"2024-10-29","cited_by_count":17,"area":null},{"id":"2310.19273","title":"The Memory Perturbation Equation: Understanding Model's Sensitivity to Data","created":"2023-10-30","cited_by_count":16,"area":null},{"id":"2403.06925","title":"Transformers Learn Low Sensitivity Functions: Investigations and Implications","created":"2024-03-11","cited_by_count":14,"area":null},{"id":"2508.12720","title":"Quantifying and Alleviating Co-Adaptation in Sparse-View 3D Gaussian Splatting","created":"2025-08-18","cited_by_count":14,"area":null},{"id":"2601.18089","title":"LatentMoE: Toward Optimal Accuracy per FLOP and Parameter in Mixture of Experts","created":"2026-01-26","cited_by_count":14,"area":"moe"},{"id":"2103.06219","title":"Why flatness does and does not correlate with generalization for deep neural networks","created":"2021-03-10","cited_by_count":13,"area":null},{"id":"2202.11749","title":"Are All Linear Regions Created Equal?","created":"2022-02-23","cited_by_count":13,"area":null},{"id":"2405.10927","title":"Using Degeneracy in the Loss Landscape for Mechanistic Interpretability","created":"2024-05-17","cited_by_count":13,"area":"mechinterp"},{"id":"2502.07998","title":"Adaptive kernel predictors from feature-learning infinite limits of neural networks","created":"2025-02-11","cited_by_count":13,"area":null},{"id":"2104.14672","title":"Analytical bounds on the local Lipschitz constants of ReLU networks","created":"2021-04-29","cited_by_count":12,"area":null},{"id":"2105.02468","title":"Relative stability toward diffeomorphisms indicates performance in deep nets","created":"2021-05-06","cited_by_count":12,"area":null},{"id":"2202.06438","title":"Learning from Randomly Initialized Neural Network Features","created":"2022-02-13","cited_by_count":12,"area":null},{"id":"2301.00008","title":"Effects of Data Geometry in Early Deep Learning","created":"2022-12-29","cited_by_count":12,"area":null},{"id":"2301.12309","title":"On the Lipschitz Constant of Deep Networks and Double Descent","created":"2023-01-28","cited_by_count":11,"area":null},{"id":"2402.13425","title":"Investigating the Histogram Loss in Regression","created":"2024-02-20","cited_by_count":11,"area":null},{"id":"2501.13075","title":"Evolution and The Knightian Blindspot of Machine Learning","created":"2025-01-22","cited_by_count":11,"area":null},{"id":"2508.04117","title":"Unveiling Over-Memorization in Finetuning LLMs for Reasoning Tasks","created":"2025-08-06","cited_by_count":11,"area":"lr"},{"id":"2207.05135","title":"FreeREA: Training-Free Evolution-based Architecture Search","created":"2022-06-17","cited_by_count":10,"area":null},{"id":"2103.09108","title":"Is it enough to optimize CNN architectures on ImageNet?","created":"2021-03-16","cited_by_count":9,"area":null},{"id":"2302.05825","title":"Koopman-based generalization bound: New aspect for full-rank weights","created":"2023-02-12","cited_by_count":9,"area":null},{"id":"2312.11584","title":"ContraNovo: A Contrastive Learning Approach to Enhance De Novo Peptide Sequencing","created":"2023-12-18","cited_by_count":9,"area":null},{"id":"2501.10077","title":"Double descent in quantum kernel methods","created":"2025-01-17","cited_by_count":9,"area":null},{"id":"2111.12143","title":"Critical Initialization of Wide and Deep Neural Networks through Partial Jacobians: General Theory and Applications","created":"2021-11-23","cited_by_count":8,"area":null},{"id":"2207.09340","title":"A coherence parameter characterizing generative compressed sensing with Fourier measurements","created":"2022-07-19","cited_by_count":8,"area":null},{"id":"2209.10080","title":"Deep Double Descent via Smooth Interpolation","created":"2022-09-21","cited_by_count":8,"area":null},{"id":"2210.05742","title":"Curved Representation Space of Vision Transformers","created":"2022-10-11","cited_by_count":8,"area":null},{"id":"2509.11348","title":"On Linear Mode Connectivity of Mixture-of-Experts Architectures","created":"2025-09-14","cited_by_count":8,"area":"moe"},{"id":"2103.13598","title":"Recent Advances in Large Margin Learning","created":"2021-03-25","cited_by_count":7,"area":null},{"id":"2111.03505","title":"Visualizing the Emergence of Intermediate Visual Patterns in DNNs","created":"2021-11-05","cited_by_count":7,"area":null},{"id":"2210.13611","title":"Understanding the Evolution of Linear Regions in Deep Reinforcement Learning","created":"2022-10-24","cited_by_count":7,"area":null},{"id":"2302.01088","title":"Sketched Ridgeless Linear Regression: The Role of Downsampling","created":"2023-02-02","cited_by_count":7,"area":null},{"id":"2305.14683","title":"On progressive sharpening, flat minima and generalisation","created":"2023-05-24","cited_by_count":7,"area":null},{"id":"2408.15127","title":"T-FAKE: Synthesizing Thermal Images for Facial Landmarking","created":"2024-08-27","cited_by_count":7,"area":null},{"id":"2510.10982","title":"Catch-Only-One: Non-Transferable Examples for Model-Specific Authorization","created":"2025-10-13","cited_by_count":7,"area":null},{"id":"2103.06733","title":"Intraclass clustering: an implicit learning ability that regularizes DNNs","created":"2021-03-11","cited_by_count":6,"area":null},{"id":"2105.11397","title":"Autonomous Kinetic Modeling of Biomass Pyrolysis using Chemical Reaction Neural Networks","created":"2021-05-24","cited_by_count":6,"area":null},{"id":"2107.06217","title":"What classifiers know what they don't?","created":"2021-07-13","cited_by_count":6,"area":null},{"id":"2204.10933","title":"A Tale of Two Models: Constructing Evasive Attacks on Edge Models","created":"2022-04-22","cited_by_count":6,"area":null},{"id":"2206.12481","title":"Analyzing Explainer Robustness via Probabilistic Lipschitzness of Prediction Functions","created":"2022-06-24","cited_by_count":6,"area":null},{"id":"2304.09802","title":"Generalization and Estimation Error Bounds for Model-based Neural Networks","created":"2023-04-19","cited_by_count":6,"area":null},{"id":"2508.14087","title":"FM4NPP: A Scaling Foundation Model for Nuclear and Particle Physics","created":"2025-08-13","cited_by_count":6,"area":null},{"id":"2106.04186","title":"What training reveals about neural network complexity","created":"2021-06-08","cited_by_count":5,"area":null},{"id":"2210.05546","title":"What does a deep neural network confidently perceive? The effective dimension of high certainty class manifolds and their low confidence boundaries","created":"2022-10-11","cited_by_count":5,"area":null},{"id":"2104.10459","title":"Jacobian Regularization for Mitigating Universal Adversarial Perturbations","created":"2021-04-21","cited_by_count":4,"area":null},{"id":"2112.00980","title":"Trap of Feature Diversity in the Learning of MLPs","created":"2021-12-02","cited_by_count":4,"area":null},{"id":"2205.07266","title":"Discovering the Representation Bottleneck of Graph Neural Networks","created":"2022-05-15","cited_by_count":4,"area":null},{"id":"2206.01332","title":"Optimal Activation Functions for the Random Features Regression Model","created":"2022-05-31","cited_by_count":4,"area":null},{"id":"2209.07879","title":"Less is Better: Recovering Intended-Feature Subspace to Robustify NLU Models","created":"2022-09-16","cited_by_count":4,"area":null},{"id":"2305.11417","title":"Exploring the Complexity of Deep Neural Networks through Functional Equivalence","created":"2023-05-19","cited_by_count":4,"area":null},{"id":"2305.19424","title":"Quantifying Overfitting: Evaluating Neural Network Performance through Analysis of Null Space","created":"2023-05-30","cited_by_count":4,"area":null},{"id":"2306.10081","title":"Optimizer's Information Criterion: Dissecting and Correcting Bias in Data-Driven Optimization","created":"2023-06-16","cited_by_count":4,"area":null},{"id":"2405.15706","title":"The Impact of Geometric Complexity on Neural Collapse in Transfer Learning","created":"2024-05-24","cited_by_count":4,"area":null},{"id":"2502.01628","title":"Harmonic Loss Trains Interpretable AI Models","created":"2025-02-03","cited_by_count":4,"area":null},{"id":"2502.08227","title":"Enhancing Sample Selection Against Label Noise by Cutting Mislabeled Easy Examples","created":"2025-02-12","cited_by_count":4,"area":null},{"id":"2504.03714","title":"Breach in the Shield: Unveiling the Vulnerabilities of Large Language Models","created":"2025-03-28","cited_by_count":4,"area":"mllm"},{"id":"2505.11692","title":"The Geometry of ReLU Networks through the ReLU Transition Graph","created":"2025-05-16","cited_by_count":4,"area":null},{"id":"2506.23174","title":"Data Can Speak for Itself: Quality-guided Utilization of Wireless Synthetic Data","created":"2025-06-29","cited_by_count":4,"area":null},{"id":"2101.05490","title":"Neural networks behave as hash encoders: An empirical study","created":"2021-01-14","cited_by_count":3,"area":null},{"id":"2203.02617","title":"How to Train Unstable Looped Tensor Network","created":"2022-03-05","cited_by_count":3,"area":null},{"id":"2206.00823","title":"Beyond accuracy: generalization properties of bio-plausible temporal credit assignment rules","created":"2022-06-02","cited_by_count":3,"area":null},{"id":"2206.08446","title":"Methods for Estimating and Improving Robustness of Language Models","created":"2022-06-16","cited_by_count":3,"area":null},{"id":"2207.07612","title":"Blessing of Nonconvexity in Deep Linear Models: Depth Flattens the Optimization Landscape Around the True Solution","created":"2022-07-15","cited_by_count":3,"area":null},{"id":"2301.05816","title":"Understanding the Spectral Bias of Coordinate Based MLPs Via Training Dynamics","created":"2023-01-14","cited_by_count":3,"area":null},{"id":"2309.03354","title":"Ensemble linear interpolators: The role of ensembling","created":"2023-09-06","cited_by_count":3,"area":null},{"id":"2310.18725","title":"The Evolution of the Interplay Between Input Distributions and Linear Regions in Networks","created":"2023-10-28","cited_by_count":3,"area":null},{"id":"2311.00897","title":"On The Open Prompt Challenge In Conditional Audio Generation","created":"2023-11-01","cited_by_count":3,"area":null},{"id":"2311.09858","title":"Polynomially Over-Parameterized Convolutional Neural Networks Contain Structured Strong Winning Lottery Tickets","created":"2023-11-16","cited_by_count":3,"area":null},{"id":"2311.12764","title":"Investigating Weight-Perturbed Deep Neural Networks With Application in Iris Presentation Attack Detection","created":"2023-11-21","cited_by_count":3,"area":null},{"id":"2312.09988","title":"Towards Architecture-Agnostic Untrained Network Priors for Image Reconstruction with Frequency Regularization","created":"2023-12-15","cited_by_count":3,"area":null},{"id":"2408.06101","title":"Generalization capabilities of MeshGraphNets to unseen geometries for fluid dynamics","created":"2024-08-12","cited_by_count":3,"area":null},{"id":"2501.10229","title":"Amortized Bayesian Mixture Models","created":"2025-01-17","cited_by_count":3,"area":null},{"id":"2503.00374","title":"MIRROR: Multi-Modal Pathological Self-Supervised Representation Learning via Modality Alignment and Retention","created":"2025-03-01","cited_by_count":3,"area":null},{"id":"2507.04448","title":"Transfer Learning in Infinite Width Feature Learning Networks","created":"2025-07-06","cited_by_count":3,"area":null},{"id":"2103.03328","title":"Evaluation of Complexity Measures for Deep Learning Generalization in Medical Image Analysis","created":"2021-03-04","cited_by_count":2,"area":null}],"next_cursor":"100"}