{"total":802,"rows":[{"id":"2103.03230","title":"Barlow Twins: Self-Supervised Learning via Redundancy Reduction","created":"2021-03-04","cited_by_count":1838,"area":null},{"id":"2304.13705","title":"Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware","created":"2023-04-23","cited_by_count":1568,"area":"offlinerl"},{"id":"2402.13616","title":"YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information","created":"2024-02-21","cited_by_count":425,"area":null},{"id":"2209.02299","title":"A Survey of Machine Unlearning","created":"2022-09-06","cited_by_count":312,"area":"safety"},{"id":"2105.02375","title":"A Geometric Analysis of Neural Collapse with Unconstrained Features","created":"2021-05-06","cited_by_count":227,"area":null},{"id":"2106.05819","title":"Adversarial Graph Augmentation to Improve Graph Contrastive Learning","created":"2021-06-10","cited_by_count":200,"area":null},{"id":"2109.06590","title":"High-Fidelity GAN Inversion for Image Attribute Editing","created":"2021-09-14","cited_by_count":197,"area":null},{"id":"2201.12987","title":"Interpretable and Generalizable Graph Learning via Stochastic Attention Mechanism","created":"2022-01-31","cited_by_count":171,"area":null},{"id":"2111.09794","title":"A Survey of Zero-shot Generalisation in Deep Reinforcement Learning","created":"2021-11-18","cited_by_count":170,"area":null},{"id":"2212.10375","title":"Self-Adaptive In-Context Learning: An Information Compression Perspective for In-Context Example Selection and Ordering","created":"2022-12-20","cited_by_count":161,"area":null},{"id":"2204.12451","title":"Understanding The Robustness in Vision Transformers","created":"2022-04-26","cited_by_count":144,"area":null},{"id":"2106.12484","title":"From Canonical Correlation Analysis to Self-supervised Graph Neural Networks","created":"2021-06-23","cited_by_count":141,"area":null},{"id":"2306.13092","title":"Squeeze, Recover and Relabel: Dataset Condensation at ImageNet Scale From A New Perspective","created":"2023-06-22","cited_by_count":138,"area":null},{"id":"2109.00412","title":"Improving Multimodal Fusion with Hierarchical Mutual Information Maximization for Multimodal Sentiment Analysis","created":"2021-09-01","cited_by_count":131,"area":null},{"id":"2204.09560","title":"Understanding and Preventing Capacity Loss in Reinforcement Learning","created":"2022-04-20","cited_by_count":125,"area":null},{"id":"2103.04505","title":"Split Computing and Early Exiting for Deep Learning Applications: Survey and Research Challenges","created":"2021-03-08","cited_by_count":115,"area":"inference"},{"id":"2109.01116","title":"An Empirical Study of Graph Contrastive Learning","created":"2021-09-02","cited_by_count":113,"area":null},{"id":"2107.03158","title":"A Survey on Data Augmentation for Text Classification","created":"2021-07-07","cited_by_count":111,"area":null},{"id":"1810.00821","title":"Variational Discriminator Bottleneck: Improving Imitation Learning, Inverse RL, and GANs by Constraining Information Flow","created":"2018-10-01","cited_by_count":105,"area":"offlinerl"},{"id":"2406.02917","title":"A comprehensive and FAIR comparison between MLP and KAN representations for differential equations and operator networks","created":"2024-06-05","cited_by_count":104,"area":null},{"id":"2202.07987","title":"Out-Of-Distribution Generalization on Graphs: A Survey","created":"2022-02-16","cited_by_count":97,"area":null},{"id":"2405.14577","title":"Representation Noising: A Defence Mechanism Against Harmful Finetuning","created":"2024-05-23","cited_by_count":96,"area":"safety"},{"id":"2305.18887","title":"How Does Information Bottleneck Help Deep Learning?","created":"2023-05-30","cited_by_count":93,"area":null},{"id":"2106.06333","title":"Invariant Information Bottleneck for Domain Generalization","created":"2021-06-11","cited_by_count":86,"area":null},{"id":"2402.09345","title":"InfoRM: Mitigating Reward Hacking in RLHF via Information-Theoretic Reward Modeling","created":"2024-02-14","cited_by_count":79,"area":"alignment"},{"id":"2106.08320","title":"Self-Supervised Learning with Kernel Dependence Maximization","created":"2021-06-15","cited_by_count":77,"area":null},{"id":"2110.14811","title":"SE(3) Equivariant Graph Neural Networks with Complete Local Frames","created":"2021-10-26","cited_by_count":76,"area":null},{"id":"2410.13228","title":"From PINNs to PIKANs: Recent Advances in Physics-Informed Machine Learning","created":"2024-10-17","cited_by_count":73,"area":null},{"id":"2110.03051","title":"Prior and Posterior Networks: A Survey on Evidential Deep Learning Methods For Uncertainty Estimation","created":"2021-10-06","cited_by_count":71,"area":null},{"id":"2203.07004","title":"Rethinking Minimal Sufficient Representation in Contrastive Learning","created":"2022-03-14","cited_by_count":69,"area":null},{"id":"2110.06530","title":"Reducing Information Bottleneck for Weakly Supervised Semantic Segmentation","created":"2021-10-13","cited_by_count":65,"area":null},{"id":"2106.04972","title":"Understanding Softmax Confidence and Uncertainty","created":"2021-06-09","cited_by_count":63,"area":null},{"id":"2209.09056","title":"Concept Embedding Models: Beyond the Accuracy-Explainability Trade-Off","created":"2022-09-19","cited_by_count":61,"area":null},{"id":"2306.04542","title":"On the Design Fundamentals of Diffusion Models: A Survey","created":"2023-06-07","cited_by_count":60,"area":"diffusion"},{"id":"2412.15119","title":"Parallelized Autoregressive Visual Generation","created":"2024-12-19","cited_by_count":60,"area":null},{"id":"2310.05077","title":"FedFed: Feature Distillation against Data Heterogeneity in Federated Learning","created":"2023-10-08","cited_by_count":54,"area":"distill"},{"id":"2207.04630","title":"On the Principles of Parsimony and Self-Consistency for the Emergence of Intelligence","created":"2022-07-11","cited_by_count":50,"area":"lr"},{"id":"2310.03789","title":"Grokking as a First Order Phase Transition in Two Layer Networks","created":"2023-10-05","cited_by_count":48,"area":null},{"id":"2102.05113","title":"Negative Data Augmentation","created":"2021-02-09","cited_by_count":46,"area":null},{"id":"2207.01223","title":"A Survey on Label-efficient Deep Image Segmentation: Bridging the Gap between Weak Supervision and Dense Prediction","created":"2022-07-04","cited_by_count":46,"area":null},{"id":"2106.09362","title":"Frustratingly Easy Transferability Estimation","created":"2021-06-17","cited_by_count":45,"area":null},{"id":"2312.03414","title":"Compressed Context Memory For Online Language Model Interaction","created":"2023-12-06","cited_by_count":43,"area":null},{"id":"2109.12909","title":"Compressive Visual Representations","created":"2021-09-27","cited_by_count":41,"area":null},{"id":"2310.16520","title":"Towards Self-Interpretable Graph-Level Anomaly Detection","created":"2023-10-25","cited_by_count":41,"area":null},{"id":"2404.00722","title":"DRCT: Saving Image Super-resolution away from Information Bottleneck","created":"2024-03-31","cited_by_count":40,"area":null},{"id":"2201.02263","title":"ITSA: An Information-Theoretic Approach to Automatic Shortcut Avoidance and Domain Generalization in Stereo Matching Networks","created":"2022-01-06","cited_by_count":39,"area":null},{"id":"2405.09786","title":"IBD-PSC: Input-level Backdoor Detection via Parameter-oriented Scaling Consistency","created":"2024-05-16","cited_by_count":39,"area":null},{"id":"2309.09725","title":"Neural Collapse for Unconstrained Feature Model under Cross-entropy Loss with Imbalanced Data","created":"2023-09-18","cited_by_count":38,"area":null},{"id":"2210.06458","title":"Efficient Knowledge Distillation from Model Checkpoints","created":"2022-10-12","cited_by_count":37,"area":"distill"},{"id":"2006.15061","title":"Intrinsic Reward Driven Imitation Learning via Generative Model","created":"2020-06-26","cited_by_count":35,"area":"offlinerl"},{"id":"2401.17139","title":"Diff-eRank: A Novel Rank-Based Metric for Evaluating Large Language Models","created":"2024-01-30","cited_by_count":35,"area":null},{"id":"2106.06468","title":"Locally Sparse Neural Networks for Tabular Biomedical Data","created":"2021-06-11","cited_by_count":34,"area":null},{"id":"2312.17174","title":"Visual Explanations of Image-Text Representations via Multi-Modal Information Bottleneck Attribution","created":"2023-12-28","cited_by_count":34,"area":"mllm"},{"id":"2405.09308","title":"TimeX++: Learning Time-Series Explanations with Information Bottleneck","created":"2024-05-15","cited_by_count":33,"area":null},{"id":"2212.11696","title":"Reversible Column Networks","created":"2022-12-22","cited_by_count":32,"area":null},{"id":"2202.00553","title":"Neural Tangent Kernel Beyond the Infinite-Width Limit: Effects of Depth and Initialization","created":"2022-02-01","cited_by_count":30,"area":null},{"id":"2109.03214","title":"Robust Predictable Control","created":"2021-09-07","cited_by_count":29,"area":null},{"id":"2201.11006","title":"An Overview of Compressible and Learnable Image Transformation with Secret Key and Its Applications","created":"2022-01-26","cited_by_count":29,"area":null},{"id":"2210.04206","title":"Attention Diversification for Domain Generalization","created":"2022-10-09","cited_by_count":29,"area":null},{"id":"2306.01103","title":"Joint Learning of Label and Environment Causal Independence for Graph Out-of-Distribution Generalization","created":"2023-06-01","cited_by_count":29,"area":null},{"id":"2306.01958","title":"A Survey on Explainability of Graph Neural Networks","created":"2023-06-02","cited_by_count":29,"area":null},{"id":"2404.13968","title":"Protecting Your LLMs with Information Bottleneck","created":"2024-04-22","cited_by_count":29,"area":"safety"},{"id":"2109.14509","title":"PAC-Bayes Information Bottleneck","created":"2021-09-29","cited_by_count":28,"area":null},{"id":"2403.13349","title":"Hierarchical Gaussian Mixture Normalizing Flow Modeling for Unified Anomaly Detection","created":"2024-03-20","cited_by_count":28,"area":null},{"id":"2501.01346","title":"Large Vision-Language Model Alignment and Misalignment: A Survey Through the Lens of Explainability","created":"2025-01-02","cited_by_count":28,"area":"mllm"},{"id":"2410.14425","title":"Unlearning Backdoor Attacks for LLMs with Weak-to-Strong Knowledge Distillation","created":"2024-10-18","cited_by_count":27,"area":"safety"},{"id":"2203.09250","title":"Symmetry-Based Representations for Artificial and Biological General Intelligence","created":"2022-03-17","cited_by_count":26,"area":null},{"id":"2310.13620","title":"Bridging Information-Theoretic and Geometric Compression in Language Models","created":"2023-10-20","cited_by_count":26,"area":null},{"id":"2106.03783","title":"An Information-theoretic Approach to Distribution Shifts","created":"2021-06-07","cited_by_count":25,"area":null},{"id":"2212.14855","title":"Disentangled Explanations of Neural Network Predictions by Finding Relevant Subspaces","created":"2022-12-30","cited_by_count":25,"area":null},{"id":"2401.08732","title":"Bayes Conditional Distribution Estimation for Knowledge Distillation Based on Conditional Mutual Information","created":"2024-01-16","cited_by_count":25,"area":"distill"},{"id":"2307.14605","title":"Clustering based Point Cloud Representation Learning for 3D Analysis","created":"2023-07-27","cited_by_count":23,"area":null},{"id":"2107.01152","title":"Simpler, Faster, Stronger: Breaking The log-K Curse On Contrastive Learners With FlatNCE","created":"2021-07-02","cited_by_count":22,"area":null},{"id":"2108.12197","title":"Translation Error Detection as Rationale Extraction","created":"2021-08-27","cited_by_count":22,"area":null},{"id":"2202.08333","title":"Self-Supervised Representation Learning via Latent Graph Prediction","created":"2022-02-16","cited_by_count":22,"area":null},{"id":"2312.00761","title":"Deep Unlearning: Fast and Efficient Gradient-free Approach to Class Forgetting","created":"2023-12-01","cited_by_count":22,"area":"safety"},{"id":"2403.02187","title":"Mutual Information Estimation via Normalizing Flows","created":"2024-03-04","cited_by_count":22,"area":null},{"id":"2405.15318","title":"Are Long-LLMs A Necessity For Long-Context Tasks?","created":"2024-05-24","cited_by_count":22,"area":null},{"id":"2410.08063","title":"Reversible Decoupling Network for Single Image Reflection Removal","created":"2024-10-10","cited_by_count":22,"area":null},{"id":"2110.10735","title":"Dynamic Bottleneck for Robust Self-Supervised Exploration","created":"2021-10-20","cited_by_count":21,"area":null},{"id":"2210.11472","title":"VIBUS: Data-efficient 3D Scene Parsing with VIewpoint Bottleneck and Uncertainty-Spectrum Modeling","created":"2022-10-20","cited_by_count":21,"area":null},{"id":"2510.06826","title":"Mid-Training of Large Language Models: A Survey","created":"2025-10-08","cited_by_count":21,"area":null},{"id":"2106.02734","title":"Revisiting Hilbert-Schmidt Information Bottleneck for Adversarial Robustness","created":"2021-06-04","cited_by_count":20,"area":null},{"id":"2404.07900","title":"High-Dimension Human Value Representation in Large Language Models","created":"2024-04-11","cited_by_count":20,"area":null},{"id":"2406.12618","title":"From Insights to Actions: The Impact of Interpretability and Analysis Research on NLP","created":"2024-06-18","cited_by_count":20,"area":null},{"id":"2509.23883","title":"DocPruner: A Storage-Efficient Framework for Multi-Vector Visual Document Retrieval via Adaptive Patch-Level Embedding Pruning","created":"2025-09-28","cited_by_count":20,"area":null},{"id":"2112.00459","title":"Information Theoretic Representation Distillation","created":"2021-12-01","cited_by_count":19,"area":"distill"},{"id":"2305.08013","title":"Information Bottleneck Analysis of Deep Neural Networks via Lossy Compression","created":"2023-05-13","cited_by_count":19,"area":null},{"id":"2306.15612","title":"Adaptive Multi-Modal Cross-Entropy Loss for Stereo Matching","created":"2023-06-27","cited_by_count":19,"area":null},{"id":"2105.12049","title":"Honest-but-Curious Nets: Sensitive Attributes of Private Inputs Can Be Secretly Coded into the Classifiers' Outputs","created":"2021-05-25","cited_by_count":18,"area":null},{"id":"2107.01131","title":"Tight Mutual Information Estimation With Contrastive Fenchel-Legendre Optimization","created":"2021-07-02","cited_by_count":18,"area":null},{"id":"2206.04101","title":"What-is and How-to for Fairness in Machine Learning: A Survey, Reflection, and Perspective","created":"2022-06-08","cited_by_count":18,"area":null},{"id":"2302.03271","title":"IB-UQ: Information bottleneck based uncertainty quantification for neural function regression and neural operator learning","created":"2023-02-07","cited_by_count":18,"area":null},{"id":"2307.07832","title":"MixupExplainer: Generalizing Explanations for Graph Neural Networks with Data Augmentation","created":"2023-07-15","cited_by_count":18,"area":null},{"id":"2402.19465","title":"Towards Tracing Trustworthiness Dynamics: Revisiting Pre-training Period of Large Language Models","created":"2024-02-29","cited_by_count":18,"area":null},{"id":"2404.09403","title":"Neuro-Inspired Information-Theoretic Hierarchical Perception for Multimodal Learning","created":"2024-04-15","cited_by_count":18,"area":null},{"id":"2104.06008","title":"Disentangled Motif-aware Graph Learning for Phrase Grounding","created":"2021-04-13","cited_by_count":17,"area":null},{"id":"2106.10414","title":"Deep Learning for Functional Data Analysis with Adaptive Basis Layers","created":"2021-06-19","cited_by_count":17,"area":null},{"id":"2110.08532","title":"Pro-KD: Progressive Distillation by Following the Footsteps of the Teacher","created":"2021-10-16","cited_by_count":17,"area":null},{"id":"2205.15809","title":"Feature Learning in $L_{2}$-regularized DNNs: Attraction/Repulsion and Sparsity","created":"2022-05-31","cited_by_count":17,"area":null}],"next_cursor":"100"}