linear separability

Language Directions in Multilingual LLMs: A Layer-wise Diagnostic Study of Token Alignment and Pretraining Imprint ACL 2026 Beyond Accuracy: Revisiting Out-of-Distribution Generalization in NLI Models CoNLL 2025 Grokking at the Edge of Linear Separability ICML 2025 Large Language Models Encode Semantics and Alignment in Linearly Separable Representations IJCNLP 2025 The Oracle Complexity of Simplex-based Matrix Games: Linear Separability and Nash Equilibria COLT 2025 Token-based Decision Criteria Are Suboptimal in In-context Learning NAACL 2025 ViTally Consistent: Scaling Biological Representation Learning for Cell Microscopy ICML 2025 What Makes Freezing Layers in Deep Neural Networks Effective? A Linear Separability Perspective AutoML 2025 Adversarial Noises Are Linearly Separable for (Nearly) Random Neural Networks AISTATS 2023 A Metadata-Driven Approach to Understand Graph Neural Networks NeurIPS 2023 Learning Efficient Coding of Natural Images with Maximum Manifold Capacity Representations NeurIPS 2023 Preserving Linear Separability in Continual Learning by Backward Feature Projection CVPR 2023 Transferable Unlearnable Examples ICLR 2023 Better Hit the Nail on the Head than Beat around the Bush: Removing Protected Attributes with a Single Projection EMNLP 2022 The Separation Capacity of Random Neural Networks JMLR 2022 Graph Convolution for Semi-Supervised Classification: Improved Linear Separability and Out-of-Distribution Generalization ICML 2021 Ranking Neural Checkpoints CVPR 2021 Separation and Concentration in Deep Networks ICLR 2021 Towards Understanding Learning in Neural Networks with Linear Teachers ICML 2021 Emergence of Separable Manifolds in Deep Language Representations ICML 2020 How does BERT capture semantics? A closer look at polysemous words EMNLP 2020 Polynomial Representation for Persistence Diagram CVPR 2019 A Study of the Classification of Low-Dimensional Data with Supervised Manifold Learning JMLR 2018 Increasing In-Class Similarity by Retrofitting Embeddings with Demographic Information EMNLP 2018 How Can Deep Rectifier Networks Achieve Linear Separability and Preserve Distances? ICML 2015