linear representation

TensorLens: End-to-End Transformer Analysis via High-Order Attention Tensors ACL 2026 All or None: Identifiable Linear Properties of Next-Token Predictors in Language Modeling AISTATS 2025 Learning from Similar Linear Representations: Adaptivity, Minimaxity, and Robustness JMLR 2025 On Linear Representations and Pretraining Data Frequency in Language Models ICLR 2025 Superpose Task-specific Features for Model Merging EMNLP 2025 When Bad Data Leads to Good Models ICML 2025 A representation-learning game for classes of prediction tasks ICLR 2024 Exploring the LLM Journey from Cognition to Expression with Linear Representations ICML 2024 From Causal to Concept-Based Representation Learning NeurIPS 2024 Language Models Linearly Represent Sentiment EMNLP 2024 Language Models Represent Space and Time ICLR 2024 On the Origins of Linear Representations in Large Language Models ICML 2024 Transformers Represent Belief State Geometry in their Residual Stream NeurIPS 2024 Emergent Linear Representations in World Models of Self-Supervised Sequence Models EMNLP 2023 Provably Efficient Lifelong Reinforcement Learning with Linear Representation ICLR 2023 Structure Aggregation for Cross-Spectral Stereo Image Guided Denoising CVPR 2023 The Power of Contrast for Feature Learning: A Theoretical Analysis JMLR 2023 Unsupervised Manifold Linearizing and Clustering ICCV 2023 Conditional Meta-Learning of Linear Representations NeurIPS 2022 Near-optimal Offline Reinforcement Learning with Linear Representation: Leveraging Variance Information with Pessimism ICLR 2022 Leveraging Good Representations in Linear Contextual Bandits ICML 2021 Near-Optimal Representation Learning for Linear Bandits and Linear RL ICML 2021 Spatially Variant Linear Representation Models for Joint Filtering CVPR 2019 Visual Tracking via Probability Continuous Outlier Model CVPR 2014 Non-negative Matrix Factorization with Sparseness Constraints JMLR 2004