{"total":77,"rows":[{"id":"2106.08320","title":"Self-Supervised Learning with Kernel Dependence Maximization","created":"2021-06-15","cited_by_count":77,"area":null},{"id":"2506.02867","title":"Demystifying Reasoning Dynamics with Mutual Information: Thinking Tokens are Information Peaks in LLM Reasoning","created":"2025-06-03","cited_by_count":51,"area":"lr"},{"id":"2401.05224","title":"Do Vision and Language Encoders Represent the World Similarly?","created":"2024-01-10","cited_by_count":44,"area":null},{"id":"2002.04013","title":"Towards Crowdsourced Training of Large Neural Networks using Decentralized Mixture-of-Experts","created":"2020-02-10","cited_by_count":43,"area":"moe"},{"id":"2106.00305","title":"Independent Prototype Propagation for Zero-Shot Compositionality","created":"2021-06-01","cited_by_count":42,"area":null},{"id":"2106.01939","title":"Causal Effect Inference for Structured Treatments","created":"2021-06-03","cited_by_count":39,"area":null},{"id":"2106.13292","title":"Semi-supervised Meta-learning with Disentanglement for Domain-generalised Medical Image Segmentation","created":"2021-06-24","cited_by_count":36,"area":null},{"id":"2309.05911","title":"Quality-Agnostic Deepfake Detection with Intra-model Collaborative Learning","created":"2023-09-12","cited_by_count":32,"area":null},{"id":"2308.13894","title":"FwdLLM: Efficient FedLLM using Forward Gradient","created":"2023-08-26","cited_by_count":26,"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":"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":"2108.08532","title":"An Information Theory-inspired Strategy for Automatic Network Pruning","created":"2021-08-19","cited_by_count":17,"area":null},{"id":"2303.13090","title":"Orthogonal Annotation Benefits Barely-supervised Medical Image Segmentation","created":"2023-03-23","cited_by_count":15,"area":null},{"id":"2305.00380","title":"DualHSIC: HSIC-Bottleneck and Alignment for Continual Learning","created":"2023-04-30","cited_by_count":15,"area":null},{"id":"2210.04311","title":"Pruning Adversarially Robust Neural Networks without Adversarial Examples","created":"2022-10-09","cited_by_count":12,"area":null},{"id":"2312.04960","title":"MIMIR: Masked Image Modeling for Mutual Information-based Adversarial Robustness","created":"2023-12-08","cited_by_count":12,"area":"mllm"},{"id":"2409.19425","title":"Harnessing Frozen Unimodal Encoders for Flexible Multimodal Alignment","created":"2024-09-28","cited_by_count":12,"area":"mllm"},{"id":"2305.08960","title":"One Forward is Enough for Neural Network Training via Likelihood Ratio Method","created":"2023-05-15","cited_by_count":11,"area":null},{"id":"2401.09067","title":"Towards Continual Learning Desiderata via HSIC-Bottleneck Orthogonalization and Equiangular Embedding","created":"2024-01-17","cited_by_count":10,"area":null},{"id":"2404.17951","title":"Cauchy-Schwarz Divergence Information Bottleneck for Regression","created":"2024-04-27","cited_by_count":9,"area":null},{"id":"2307.16235","title":"Spiking Neural Networks and Bio-Inspired Supervised Deep Learning: A Survey","created":"2023-07-30","cited_by_count":8,"area":null},{"id":"2402.09050","title":"End-to-End Training Induces Information Bottleneck through Layer-Role Differentiation: A Comparative Analysis with Layer-wise Training","created":"2024-02-14","cited_by_count":8,"area":null},{"id":"2403.08215","title":"LIX: Implicitly Infusing Spatial Geometric Prior Knowledge into Visual Semantic Segmentation for Autonomous Driving","created":"2024-03-13","cited_by_count":8,"area":"distill"},{"id":"2605.24011","title":"ActQuant: Sub-4-bit Action-Guided Quantization for Vision-Language-Action Models","created":"2026-05-19","cited_by_count":8,"area":"vla"},{"id":"2106.08848","title":"Data Augmentation for Graph Convolutional Network on Semi-Supervised Classification","created":"2021-06-16","cited_by_count":7,"area":null},{"id":"2405.12443","title":"FFCL: Forward-Forward Net with Cortical Loops, Training and Inference on Edge Without Backpropagation","created":"2024-05-21","cited_by_count":6,"area":null},{"id":"2101.03419","title":"Training Deep Architectures Without End-to-End Backpropagation: A Survey on the Provably Optimal Methods","created":"2021-01-09","cited_by_count":5,"area":null},{"id":"2103.04314","title":"Expert System Gradient Descent Style Training: Development of a Defensible Artificial Intelligence Technique","created":"2021-03-07","cited_by_count":5,"area":null},{"id":"2410.16672","title":"The Tug of War Within: Mitigating the Fairness-Privacy Conflicts in Large Language Models","created":"2024-10-22","cited_by_count":5,"area":null},{"id":"2511.17579","title":"Multi-Value Alignment for LLMs via Value Decorrelation and Extrapolation","created":"2025-11-15","cited_by_count":5,"area":"alignment"},{"id":"2307.05948","title":"Diversity-enhancing Generative Network for Few-shot Hypothesis Adaptation","created":"2023-07-12","cited_by_count":4,"area":null},{"id":"2309.17357","title":"Module-wise Training of Neural Networks via the Minimizing Movement Scheme","created":"2023-09-29","cited_by_count":4,"area":null},{"id":"2410.05966","title":"FLOPS: Forward Learning with OPtimal Sampling","created":"2024-10-08","cited_by_count":4,"area":null},{"id":"2509.20829","title":"Explaining Grokking and Information Bottleneck through Neural Collapse Emergence","created":"2025-09-25","cited_by_count":4,"area":null},{"id":"2311.05472","title":"Text Representation Distillation via Information Bottleneck Principle","created":"2023-11-09","cited_by_count":3,"area":null},{"id":"2202.01210","title":"Deep Layer-wise Networks Have Closed-Form Weights","created":"2022-02-01","cited_by_count":2,"area":null},{"id":"2206.01820","title":"A Robust Backpropagation-Free Framework for Images","created":"2022-06-03","cited_by_count":2,"area":null},{"id":"2302.10896","title":"IB-RAR: Information Bottleneck as Regularizer for Adversarial Robustness","created":"2023-02-09","cited_by_count":2,"area":null},{"id":"2309.16687","title":"Duality Principle and Biologically Plausible Learning: Connecting the Representer Theorem and Hebbian Learning","created":"2023-08-02","cited_by_count":2,"area":null},{"id":"2403.05559","title":"Exploring Heterogeneity and Uncertainty for Graph-based Cognitive Diagnosis Models in Intelligent Education","created":"2024-02-15","cited_by_count":2,"area":null},{"id":"2510.20627","title":"H-SPLID: HSIC-based Saliency Preserving Latent Information Decomposition","created":"2025-10-23","cited_by_count":2,"area":null},{"id":"2603.13878","title":"Step-CoT: Stepwise Visual Chain-of-Thought for Medical Visual Question Answering","created":"2026-03-14","cited_by_count":2,"area":"lr"},{"id":"2105.09590","title":"Intra-Model Collaborative Learning of Neural Networks","created":"2021-05-20","cited_by_count":1,"area":null},{"id":"2111.13187","title":"Information Bottleneck-Based Hebbian Learning Rule Naturally Ties Working Memory and Synaptic Updates","created":"2021-11-24","cited_by_count":1,"area":null},{"id":"2203.05417","title":"Deep Regression Ensembles","created":"2022-03-10","cited_by_count":1,"area":null},{"id":"2208.03563","title":"HSIC-InfoGAN: Learning Unsupervised Disentangled Representations by Maximising Approximated Mutual Information","created":"2022-08-06","cited_by_count":1,"area":null},{"id":"2208.07934","title":"Measuring Statistical Dependencies via Maximum Norm and Characteristic Functions","created":"2022-08-16","cited_by_count":1,"area":null},{"id":"2210.00949","title":"Block-wise Training of Residual Networks via the Minimizing Movement Scheme","created":"2022-10-03","cited_by_count":1,"area":null},{"id":"2303.09497","title":"Gate Recurrent Unit Network based on Hilbert-Schmidt Independence Criterion for State-of-Health Estimation","created":"2023-03-16","cited_by_count":1,"area":null},{"id":"2304.03202","title":"SLM: End-to-end Feature Selection via Sparse Learnable Masks","created":"2023-04-06","cited_by_count":1,"area":null},{"id":"2403.02011","title":"Bipartite Graph Variational Auto-Encoder with Fair Latent Representation to Account for Sampling Bias in Ecological Networks","created":"2024-03-04","cited_by_count":1,"area":null},{"id":"2403.08124","title":"Towards Independence Criterion in Machine Unlearning of Features and Labels","created":"2024-03-12","cited_by_count":1,"area":"safety"},{"id":"2405.05097","title":"Biology-inspired joint distribution neurons based on Hierarchical Correlation Reconstruction allowing for multidirectional propagation of values and densities","created":"2024-05-08","cited_by_count":1,"area":null},{"id":"2410.23595","title":"Disentangling Interpretable Factors with Supervised Independent Subspace Principal Component Analysis","created":"2024-10-31","cited_by_count":1,"area":null},{"id":"2502.09125","title":"Enhanced Structured Lasso Pruning with Class-wise Information","created":"2025-02-13","cited_by_count":1,"area":null},{"id":"2509.01533","title":"Forward-Only Continual Learning","created":"2025-09-01","cited_by_count":1,"area":null},{"id":"2510.03273","title":"Learning without Global Backpropagation via Synergistic Information Distillation","created":"2025-09-27","cited_by_count":1,"area":null},{"id":"2510.05191","title":"Provable Speech Attributes Conversion via Latent Independence","created":"2025-10-06","cited_by_count":1,"area":null},{"id":"2512.17531","title":"NetworkFF: Unified Layer Optimization in Forward-Only Neural Networks","created":"2025-12-19","cited_by_count":1,"area":null},{"id":"2603.16760","title":"Dual Stream Independence Decoupling for True Emotion Recognition under Masked Expressions","created":"2026-03-17","cited_by_count":1,"area":null},{"id":"2606.19679","title":"LOKI: Memory-Free Null-Space Constrained Lifelong Knowledge Editing","created":"2026-06-18","cited_by_count":1,"area":null},{"id":"2106.05569","title":"Front Contribution instead of Back Propagation","created":"2021-06-10","cited_by_count":0,"area":null},{"id":"2108.03815","title":"P-WAE: Generalized Patch-Wasserstein Autoencoder for Anomaly Screening","created":"2021-08-09","cited_by_count":0,"area":null},{"id":"2207.02845","title":"Automating the Design and Development of Gradient Descent Trained Expert System Networks","created":"2022-07-04","cited_by_count":0,"area":null},{"id":"2308.02427","title":"Unlocking the Potential of Similarity Matching: Scalability, Supervision and Pre-training","created":"2023-08-02","cited_by_count":0,"area":null},{"id":"2308.07772","title":"MOLE: MOdular Learning FramEwork via Mutual Information Maximization","created":"2023-08-15","cited_by_count":0,"area":null},{"id":"2312.07636","title":"Go beyond End-to-End Training: Boosting Greedy Local Learning with Context Supply","created":"2023-12-12","cited_by_count":0,"area":null},{"id":"2403.12320","title":"Approximated Likelihood Ratio: A Forward-Only and Parallel Framework for Boosting Neural Network Training","created":"2024-03-18","cited_by_count":0,"area":null},{"id":"2412.05667","title":"Training neural networks without backpropagation using particles","created":"2024-12-07","cited_by_count":0,"area":null},{"id":"2508.18338","title":"Linear cost mutual information estimation and independence test of similar performance as HSIC","created":"2025-08-25","cited_by_count":0,"area":null},{"id":"2510.27651","title":"Information-Theoretic Greedy Layer-wise Training for Traffic Sign Recognition","created":"2025-10-31","cited_by_count":0,"area":null},{"id":"2512.02437","title":"LightHCG: a Lightweight yet powerful HSIC Disentanglement based Causal Glaucoma Detection Model framework","created":"2025-12-02","cited_by_count":0,"area":null},{"id":"2601.22501","title":"MIRRORTALK: Forging Personalized Avatars Via Disentangled Style and Hierarchical Motion Control","created":"2026-01-30","cited_by_count":0,"area":null},{"id":"2604.13409","title":"CausalDisenSeg: A Causality-Guided Disentanglement Framework with Counterfactual Reasoning for Robust Brain Tumor Segmentation Under Missing Modalities","created":"2026-04-15","cited_by_count":0,"area":null},{"id":"2604.18146","title":"Modular Representation Compression: Adapting LLMs for Efficient and Effective Recommendations","created":"2026-04-20","cited_by_count":0,"area":null},{"id":"2608.10470","title":"A Joint-Distribution Route to Fair Representations with Continuous Sensitive Attributes","created":"2026-08-11","cited_by_count":0,"area":null},{"id":"2609.33240","title":"The Price of Locality: Why Forward-Forward Underperforms Backpropagation?","created":"2026-09-27","cited_by_count":0,"area":null}],"next_cursor":null}