linear probing

Align Once to Explain: Feature Alignment for Scalable B-cosification of Foundational Vision Transformers CVPR 2026 Beyond Transcription: Mechanistic Interpretability in ASR AAAI 2026 Denoising Concept Vectors with Sparse Autoencoders for Improved Language Model Steering EACL 2026 LatentGate: Low-Latency Semantic Routing via Frozen-Backbone Probing of Small Language Models ACL 2026 LLM Safety From Within: Detecting Harmful Content with Internal Representations ACL 2026 Measuring and Mitigating Shortcut Reliance in Language Models with Probe-Based Representation Entanglement ACL 2026 Pluggable Pruning with Contiguous Layer Distillation for Diffusion Transformers CVPR 2026 ProM3E: Probabilistic Masked MultiModal Embedding Model for Ecology CVPR 2026 Residual Connections Harm Generative Representation Learning CVPR 2026 Rhetorical Questions in LLM Representations: A Linear Probing Study ACL 2026 RNN as Linear Transformer: A Closer Investigation into Representational Potentials of Visual Mamba Models CVPR 2026 Same Benchmark, Same Subspace: Task-Selective Convergence in LLM Representations UAI 2026 The Universal Normal Embedding CVPR 2026 Addition in Four Movements: Mapping Layer-wise Information Trajectories in LLMs EMNLP 2025 Boosting Masked ECG-Text Auto-Encoders as Discriminative Learners ICML 2025 Calibrating Verbal Uncertainty as a Linear Feature to Reduce Hallucinations EMNLP 2025 Detecting Hallucination in Large Language Models Through Deep Internal Representation Analysis IJCAI 2025 ExPLoRA: Parameter-Efficient Extended Pre-Training to Adapt Vision Transformers under Domain Shifts ICML 2025 How Not to Stitch Representations to Measure Similarity: Task Loss Matching Versus Direct Matching AAAI 2025 Improving Preference Extraction In LLMs By Identifying Latent Knowledge Through Classifying Probes ACL 2025 Interpreting Multi-Attribute Confounding through Numerical Attributes in Large Language Models IJCNLP 2025 “I’ve Decided to Leak”: Probing Internals Behind Prompt Leakage Intents EMNLP 2025 Latent Action Learning Requires Supervision in the Presence of Distractors ICML 2025 Linear Decoding of Morphology Relations in Language Models (Student Abstract) AAAI 2025 LP-FT-LoRA: A Three-Stage PEFT Framework for Efficient Domain Adaptation in Bangla NLP Tasks AACL 2025