Key papers

• Contrastive On-Policy Distillation (2026)
  Jiacheng Ruan et al.
  5.49
• Local Synaptic Rules Can Implement a SIGReg Gradient Without Backpropagation (2026)
  Martin Andrews
  5.01
• Alleviating Regional Shortcuts for Few-Shot Class-Incremental Learning (2026)
  Haichen Zhou et al.
  5.01
• CGMatch: A Different Perspective of Semi-supervised Learning (2025)
  Bo Cheng et al.
  4.82
• Interpretable Image Classification via Non-parametric Part Prototype Learning (2025)
  Zhijie Zhu et al.
  4.82
• Robustness Meets Uncertainty: Evidential Adversarial Training for Robust Selective Classification (2026)
  Nicolas Sournac et al.
  4.39
• CuBAS: Information Geometric Curvature-Based Adaptive Sampling for Supervised Classification (2026)
  Alexandre L. M. Levada
  4.39
• A Step Towards Robust Unsupervised Domain Adaptation via Fine-Tuning and Reinforcement Learning (2026)
  Sushant Dagaji Desale et al.
  4.39
• Binary Iterative Method for Non-targeted Adversarial Attack (2026)
  Naman Goyal et al.
  4.39
• SAD-LoRA: Spectral Alignment for Low-Rank Knowledge Distillation (2026)
  Omer Tariq et al.
  4.39
• Hierarchical Scaffolding Enables Human-Like Cognitive Selectivity under Data Scarcity (2026)
  Juhyoung Park et al.
  4.39
• Learning Probabilistic Prompt for Continual Learning (2026)
  Hyekang Park et al.
  4.39
• Virtual Category-Guided Continual Generalized Category Discovery (2026)
  Jiahui Xiong et al.
  4.39
• A Strong Balanced-Softmax Classifier-Retraining Baseline for Long-Tailed Recognition (2026)
  Juan Terven et al.
  4.39
• DiffUE: Enhancing Utility-Unlearnability Trade-off of Unlearnable Examples via Diffusion Autoencoders (2026)
  Syed Irfan Ali Meerza et al.
  4.39
• Single-Teacher View Augmentation: Enhancing Knowledge Distillation with Student-Guided Perturbations (2026)
  Xuyi Yu et al.
  4.39
• Self-Supervised Visual Representation Learning: Pretrain-Finetuning or Joint Training? (2026)
  Nusrat Munia et al.
  4.39
• Barnamala: Parameter-Efficient Handwritten Devanagari Recognition at Benchmark Saturation (2026)
  Ashish Thapa et al.
  4.39
• Detecting Neural Network Failures through Spectral Analysis of Internal Activations (2026)
  Arunan J
  4.39
• Class-Balanced Softmax: A Bayes Theory-Based Method for Long-Tailed Recognition (2026)
  Yi-Hang Zhu et al.
  4.39
• The Weight Norm Sets the Grokking Timescale: A Causal Delay Law (2026)
  Truong Xuan Khanh et al.
  4.33
• Uncertainty Estimation and Generalization Bounds for Modern Deep Learning (2026)
  Luis A. Ortega
  4.33
• FedReLa: Imbalanced Federated Learning via Re-Labeling (2026)
  Guangzheng Hu et al.
  4.33
• CLIMB: Centroid-Based Hierarchical Memory for Online Continual Self-Supervised Learning (2026)
  Julien Lefebvre et al.
  4.33
• MAPE: Defending Against Transferable Adversarial Attacks Using Multi-Source Adversarial Perturbations Elimination (2026)
  Xinlei Liu et al.
  4.33
• Revising RVL-CDIP: Quantifying Errors and Test-Train Overlap (2026)
  Stefan Larson et al.
  4.33
• Evolution of Data-driven Single- and Multi-Hazard Susceptibility Mapping and Emergence of Deep Learning Methods (2025)
  Jaya Sreevalsan-Nair et al.
  4.25
• SuperCM: Improving Semi-Supervised Learning and Domain Adaptation through differentiable clustering (2025)
  Durgesh Singh and Ahc\`ene Boubekki and Robert Jenssen and Michael Kampffmeyer
  3.86
• Unsupervised Waste Classification By Dual-Encoder Contrastive Learning and Multi-Clustering Voting (DECMCV) (2025)
  Kui Huang et al.
  3.64
• Few-Medoids: An Embarrassingly Simple Coreset Selection Method for Few-Shot Knowledge Distillation (2026)
  Cemil-Andrei Dilmac et al.
  3.51
• Label-Decoupled Style Augmentation for Domain Generalization in Multi-Label Remote Sensing Scene Classification (2026)
  Alaa Almouradi et al.
  3.51
• FedLAS: Feature-Modulated Bidirectional Label Smoothing for Neural Network Calibration (2026)
  Thiru Thillai Nadarasar Bahavan et al.
  3.45
• The Platonic Defense: Backdoor Defense for Self-Supervised Encoders in the Era of Large Scale Pre-training (2026)
  Tuo Chen et al.
  3.45
• Robust Trajectory Distillation: Hybrid Reweighting Meets Teacher-Inspired Targets (2026)
  Kaifeng Chen et al.
  3.45
• CouCE: A Unified Causal Framework for Debiased Deep Metric Learning (2026)
  Xin Yuan et al.
  3.45
• Finite Difference Flow Optimization for RL Post-Training of Text-to-Image Models (2026)
  David McAllister et al.
  3.28
• Label Smoothing++: Enhanced Label Regularization for Training Neural Networks (2025)
  Sachin Chhabra et al.
  3.04
• Cluster Contrast for Unsupervised Visual Representation Learning (2025)
  Nikolaos Giakoumoglou et al.
  2.93
• Improving the Transferability of Adversarial Attacks by an Input Transpose (2025)
  Qing Wan et al.
  2.71
• From Limited Labels to Open Domains:An Efficient Learning Method for Drone-view Geo-Localization (2025)
  Zhongwei Chen et al.
  2.71
• Selecting Samples on Graphs: A Unified Dataset Pruning Framework for Lossless Training Acceleration (2026)
  Dongyue Wu et al.
  1.94
• Learning a Sampling-Free Variational DNN Plugin from Tiny Training Sets to Refine OOD Segmentation With Uncertainty Estimation (2026)
  Jimut B. Pal et al.
  1.94
• Distill Once, Adapt Life-Long: Exploring Dataset Distillation for Continual Test-Time Adaptation (2026)
  Hyun-Kurl Jang et al.
  1.94
• LatentDiff: Scaling Semantic Dataset Comparison to Millions of Images (2026)
  James Flora et al.
  1.89
• CPCANet: Deep Unfolding Common Principal Component Analysis for Domain Generalization (2026)
  Yu-Hsi Chen et al.
  1.89
• Inducing Spatial Locality in Vision Transformers through the Training Protocol (2026)
  Eduardo Santiago Toledo and Asael Fabian Mart\'inez
  1.89
• GIBLy: Improving 3D Semantic Segmentation through an Architecture-Agnostic Lightweight Geometric Inductive Bias Layer (2026)
  Diogo Lavado et al.
  1.89
• Student Capacity Moderates Knowledge Distillation Effectiveness: A Systematic Study Across ResNet Teacher-Student Pairs on CIFAR-10 (2026)
  Umut Onur Yasar
  1.89
• VDLF-Net: Variational Feature Fusion for Adaptive and Few-Shot Visual Learning (2026)
  Jiawei Yan
  1.83
• Elite-driven Support Vector Machines For Classification (2026)
  Mohammad Jafari Jozani, Bahram Moeinianfar
  1.83
• Decoupling Stability and Plasticity for Multi-Modal Test-Time Adaptation (2026)
  Yongbo He et al.
  1.78
• Towards Principled Dataset Distillation: A Spectral Distribution Perspective (2026)
  Ruixi Wu and Shaobo Wang and Jiahuan Chen and Zhiyuan Liu and Yicun Yang and Zhaorun Chen and Zekai Li and Kaixin Li and Xinming Wang and Hongzhu Yi and Kai Wang and Linfeng Zhang
  1.78
• An Analysis of Multi-Task Architectures for the Hierarchic Multi-Label Problem of Vehicle Model and Make Classification (2026)
  Alexandru Manole et al.
  1.78
• From Fewer Samples to Fewer Bits: Reframing Dataset Distillation as Joint Optimization of Precision and Compactness (2026)
  My H. Dinh et al.
  1.78
• Scale-invariant Gaussian derivative residual networks (2026)
  Andrzej Perzanowski and Tony Lindeberg
  1.78
• Vector-Quantized Soft Label Compression for Dataset Distillation (2026)
  Ali Abbasi et al.
  1.78
• Degradation-based augmented training for robust individual animal re-identification (2026)
  Thanos Polychronou et al.
  1.78
• Hold-One-Shot-Out (HOSO) for Validation-Free Few-Shot CLIP Adapters (2026)
  Chris Vorster et al.
  1.78
• Training for Trustworthy Saliency Maps: Adversarial Training Meets Feature-Map Smoothing (2026)
  Dipkamal Bhusal et al.
  1.78
• Removing the Trigger, Not the Backdoor: Alternative Triggers and Latent Backdoors (2026)
  Gorka Abad et al.
  1.78