representation similarity

Why LLM Safety Guardrails Collapse After Fine-tuning: A Similarity Analysis Between Alignment and Fine-tuning Datasets ACL 2026 Enhancing Audio Deepfake Detection by Improving Representation Similarity of Bonafide Speech Interspeech 2025 Frozen Language Models Are Gradient Coherence Rectifiers in Vision Transformers AAAI 2025 How Not to Stitch Representations to Measure Similarity: Task Loss Matching Versus Direct Matching AAAI 2025 Inference-Time Decomposition of Activations (ITDA): A Scalable Approach to Interpreting Large Language Models ICML 2025 Multimodal Language Models See Better When They Look Shallower EMNLP 2025 Similarity-Guided Layer-Adaptive Vision Transformer for UAV Tracking CVPR 2025 Tracing Representation Progression: Analyzing and Enhancing Layer-Wise Similarity ICLR 2025 Understanding the Modality Gap: An Empirical Study on the Speech-Text Alignment Mechanism of Large Speech Language Models EMNLP 2025 Be Your Own Neighborhood: Detecting Adversarial Examples by the Neighborhood Relations Built on Self-Supervised Learning ICML 2024 Hardware Aware Evolutionary Neural Architecture Search Using Representation Similarity Metric WACV 2024 Rethinking Centered Kernel Alignment in Knowledge Distillation IJCAI 2024 Deep Spiking Neural Networks with High Representation Similarity Model Visual Pathways of Macaque and Mouse AAAI 2023 Script, Language, and Labels: Overcoming Three Discrepancies for Low-Resource Language Specialization AAAI 2023 Tied-Augment: Controlling Representation Similarity Improves Data Augmentation ICML 2023 Cross-lingual Similarity of Multilingual Representations Revisited AACL 2022 Deconfounded Representation Similarity for Comparison of Neural Networks NeurIPS 2022 Measuring Representational Robustness of Neural Networks Through Shared Invariances ICML 2022 Understanding Robust Learning through the Lens of Representation Similarities NeurIPS 2022 Fine-Tuned Transformers Show Clusters of Similar Representations Across Layers EMNLP 2021 Grounding Representation Similarity Through Statistical Testing NeurIPS 2021 Model-Contrastive Federated Learning CVPR 2021 Investigating Multilingual NMT Representations at Scale EMNLP 2019