linear transformation

Closed-Form Concept Erasure via Double Projections CVPR 2026 From Parameter to Representation: A Closed-Form Approach for Controllable Model Merging AAAI 2026 Cross-model Transferability among Large Language Models on the Platonic Representations of Concepts ACL 2025 Distributed Differentially Private Data Analytics via Secure Sketching ICML 2025 Linear Relational Decoding of Morphology in Language Models NAACL 2025 LLaVA Steering: Visual Instruction Tuning with 500x Fewer Parameters through Modality Linear Representation-Steering ACL 2025 Origin Identification for Text-Guided Image-to-Image Diffusion Models ICML 2025 Rate-Preserving Reductions for Blackwell Approachability COLT 2025 Score-based Causal Representation Learning: Linear and General Transformations JMLR 2025 Superpose Task-specific Features for Model Merging EMNLP 2025 Test-time Correlation Alignment ICML 2025 WET: Overcoming Paraphrasing Vulnerabilities in Embeddings-as-a-Service with Linear Transformation Watermarks ACL 2025 Jump to Conclusions: Short-Cutting Transformers with Linear Transformations COLING 2024 Linear Causal Representation Learning from Unknown Multi-node Interventions NeurIPS 2024 Linear Cross-Lingual Mapping of Sentence Embeddings ACL 2024 Linearity of Relation Decoding in Transformer Language Models ICLR 2024 Normalized Narrow Jump To Conclusions: Normalized Narrow Shortcuts for Parameter Efficient Early Exit Transformer Prediction EMNLP 2024 RLE: A Unified Perspective of Data Augmentation for Cross-Spectral Re-Identification NeurIPS 2024 RSA: Resolving Scale Ambiguities in Monocular Depth Estimators through Language Descriptions NeurIPS 2024 Linear Causal Disentanglement via Interventions ICML 2023 Mid-Vision Feedback ICLR 2023 Neural Discovery of Permutation Subgroups AISTATS 2023 An Analysis of Euclidean vs. Graph-Based Framing for Bilingual Lexicon Induction from Word Embedding Spaces EMNLP 2021 Efficient Weight Factorization for Multilingual Speech Recognition Interspeech 2021 Linear Semantics in Generative Adversarial Networks CVPR 2021