attention score

Contribution-aware Token Compression for Efficient Video Understanding via Reinforcement Learning AAAI 2026 Do LLMs Encode Functional Importance of Reasoning Tokens ? ACL 2026 QuietPrune: Query-Guided Early Token Pruning for Vision-Language Models CVPR 2026 Accelerating Multimodal Large Language Models by Searching Optimal Vision Token Reduction CVPR 2025 Emergence of Episodic Memory in Transformers: Characterizing Changes in Temporal Structure of Attention Scores During Training NAACL 2025 LEANCODE: Understanding Models Better for Code Simplification of Pre-trained Large Language Models ACL 2025 Mask-Enhanced Autoregressive Prediction: Pay Less Attention to Learn More ICML 2025 RobustKV: Defending Large Language Models against Jailbreak Attacks via KV Eviction ICLR 2025 SelfElicit: Your Language Model Secretly Knows Where is the Relevant Evidence ACL 2025 TableKV: KV Cache Compression for In-Context Table Processing ACL 2025 Think Clearly: Improving Reasoning via Redundant Token Pruning EMNLP 2025 This is not a Disimprovement: Improving Negation Reasoning in Large Language Models via Prompt Engineering EMNLP 2025 A Simple and Effective L_2 Norm-Based Strategy for KV Cache Compression EMNLP 2024 CaM: Cache Merging for Memory-efficient LLMs Inference ICML 2024 Dynamic Multi-granularity Attribution Network for Aspect-based Sentiment Analysis EMNLP 2024 Evaluating Webcam-based Gaze Data as an Alternative for Human Rationale Annotations COLING 2024 Even Sparser Graph Transformers NeurIPS 2024 Exploring Memorization in Fine-tuned Language Models ACL 2024 IntactKV: Improving Large Language Model Quantization by Keeping Pivot Tokens Intact ACL 2024 Interpretable Composition Attribution Enhancement for Visio-linguistic Compositional Understanding EMNLP 2024 NACL: A General and Effective KV Cache Eviction Framework for LLM at Inference Time ACL 2024 ZipCache: Accurate and Efficient KV Cache Quantization with Salient Token Identification NeurIPS 2024 Can Current Explainability Help Provide References in Clinical Notes to Support Humans Annotate Medical Codes? EMNLP 2022 CAT-probing: A Metric-based Approach to Interpret How Pre-trained Models for Programming Language Attend Code Structure EMNLP 2022 Distilling Knowledge from Reader to Retriever for Question Answering ICLR 2021