intrinsic dimension

Unveiling Intrinsic Dimension of Texts: from Academic Abstract to Creative Story EACL 2026 A Comparative Study of Learning Paradigms in Large Language Models via Intrinsic Dimension NAACL 2025 A Likelihood Based Approach to Distribution Regression Using Conditional Deep Generative Models ICML 2025 Discrepancies are Virtue: Weak-to-Strong Generalization through Lens of Intrinsic Dimension ICML 2025 GeLoRA: Geometric Adaptive Ranks For Efficient LoRA Fine-tuning EMNLP 2025 Generalization error bound for denoising score matching under relaxed manifold assumption COLT 2025 Geometric Signatures of Compositionality Across a Language Model’s Lifetime ACL 2025 Inspecting the Representation Manifold of Differentially-Private Text NAACL 2025 Linear Convergence of Diffusion Models Under the Manifold Hypothesis COLT 2025 Memorization in Language Models through the Lens of Intrinsic Dimension ACL 2025 On the Statistical Properties of Generative Adversarial Models for Low Intrinsic Data Dimension JMLR 2025 Score-based Pullback Riemannian Geometry: Extracting the Data Manifold Geometry using Anisotropic Flows ICML 2025 Textural or Textual: How Vision-Language Models Read Text in Images ICML 2025 A Geometric Explanation of the Likelihood OOD Detection Paradox ICML 2024 A Geometric View of Data Complexity: Efficient Local Intrinsic Dimension Estimation with Diffusion Models NeurIPS 2024 Characterizing Large Language Model Geometry Helps Solve Toxicity Detection and Generation ICML 2024 Deep Regression Representation Learning with Topology ICML 2024 Diffusion Models Encode the Intrinsic Dimension of Data Manifolds ICML 2024 Efficient Sketches for Training Data Attribution and Studying the Loss Landscape NeurIPS 2024 Exploring Intrinsic Dimension for Vision-Language Model Pruning ICML 2024 Stealth edits to large language models NeurIPS 2024 The Effect of Intrinsic Dataset Properties on Generalization: Unraveling Learning Differences Between Natural and Medical Images ICLR 2024 The Shape of Learning: Anisotropy and Intrinsic Dimensions in Transformer-Based Models EACL 2024 Bridging Information-Theoretic and Geometric Compression in Language Models EMNLP 2023 Data Representations’ Study of Latent Image Manifolds ICML 2023