token pruning

Stability Implies Redundancy: Delta Attention Selective Halting for Efficient Long-Context Prefilling ACL 2026 SToRe3D: Sparse Token Relevance in ViTs for Efficient Multi-View 3D Object Detection CVPR 2026 TabFlash: Efficient Table Understanding with Progressive Question Conditioning and Token Focusing AAAI 2026 Token Pruning for Improving Graph-Generating State Space Model Performance EACL 2026 Token Reduction via Local and Global Contexts Optimization for Efficient Video Large Language Models CVPR 2026 TOP-RL: Task-Optimized Progressive Token Pruning with Reinforcement Learning for Vision Language Models AAAI 2026 TransPrune: Token Transition Pruning for Efficient Large Vision-Language Model CVPR 2026 UTPTrack: Towards Simple and Unified Token Pruning for Visual Tracking CVPR 2026 VLM-Pruner: Buffering for Spatial Sparsity in an Efficient VLM Centrifugal Token Pruning Paradigm CVPR 2026 V-Pruner: A Fast and Globally-informed Token Pruning Framework for Vision Transformer AAAI 2026 What Do Visual Tokens Really Encode? Uncovering Sparsity and Redundancy in Multimodal Large Language Models CVPR 2026 When Token Pruning is Worse than Random: Understanding Visual Token Information in VLLMs CVPR 2026 ZOO-Prune: Training-Free Token Pruning via Zeroth-Order Gradient Estimation in Vision-Language Models CVPR 2026 AdaTP: Attention-Debiased Token Pruning for Video Large Language Models EMNLP 2025 A Hidden Stumbling Block in Generalized Category Discovery: Distracted Attention ICCV 2025 AIM: Adaptive Inference of Multi-Modal LLMs via Token Merging and Pruning ICCV 2025 A Stitch in Time Saves Nine: Small VLM is a Precise Guidance for Accelerating Large VLMs CVPR 2025 ATP-LLaVA: Adaptive Token Pruning for Large Vision Language Models CVPR 2025 Beyond Text-Visual Attention: Exploiting Visual Cues for Effective Token Pruning in VLMs ICCV 2025 CipherPrune: Efficient and Scalable Private Transformer Inference ICLR 2025 CoreMatching: A Co-adaptive Sparse Inference Framework with Token and Neuron Pruning for Comprehensive Acceleration of Vision-Language Models ICML 2025 CoViPAL: Layer-wise Contextualized Visual Token Pruning for Large Vision-Language Models EMNLP 2025 DisComp: A Two-Stage Prompt Optimization Framework Combining Task-Agnostic and Task-Aware Compression NAACL 2025 DivPrune: Diversity-based Visual Token Pruning for Large Multimodal Models CVPR 2025 FastVAR: Linear Visual Autoregressive Modeling via Cached Token Pruning ICCV 2025