transformer layer

Back Attention: Understanding and Enhancing Multi-Hop Reasoning in Large Language Models EMNLP 2025 Comprehensive Layer-wise Analysis of SSL Models for Audio Deepfake Detection NAACL 2025 DLF-EEND: Dynamic Layer Fusion for End-to-End Speaker Diarization Interspeech 2025 FREE: Fast and Robust Vision Language Models with Early Exits ACL 2025 IG-Pruning: Input-Guided Block Pruning for Large Language Models EMNLP 2025 PSReg: Prior-guided Sparse Mixture of Experts for Point Cloud Registration AAAI 2025 Quantifying Semantic Emergence in Language Models ACL 2025 Residual Matrix Transformers: Scaling the Size of the Residual Stream ICML 2025 Scaling Graph-Based Dependency Parsing with Arc Vectorization and Attention-Based Refinement NAACL 2025 Spelling-out is not Straightforward: LLMs’ Capability of Tokenization from Token to Characters EMNLP 2025 Towards Accurate Unified Anomaly Segmentation WACV 2025 A Layer-Anchoring Strategy for Enhancing Cross-Lingual Speech Emotion Recognition Interspeech 2024 Layer-Wise Representation Fusion for Compositional Generalization AAAI 2024 Mitigating the Alignment Tax of RLHF EMNLP 2024 Layered Bias: Interpreting Bias in Pretrained Large Language Models EMNLP 2023 Towards Adaptive Prefix Tuning for Parameter-Efficient Language Model Fine-tuning ACL 2023 DEFORMER: Coupling Deformed Localized Patterns with Global Context for Robust End-to-end Speech Recognition Interspeech 2022 SFE-AI at SemEval-2022 Task 11: Low-Resource Named Entity Recognition using Large Pre-trained Language Models SemEval 2022