token pruning

Adaptive Compute Efficient Learning via Conceptual-Criticality (Student Abstract) AAAI 2026 AdaSpark: Adaptive Sparsity for Efficient Long-Video Understanding CVPR 2026 CATP: Contextually Adaptive Token Pruning for Efficient and Enhanced Multimodal In-Context Learning AAAI 2026 Collaborative Multi-Mode Pruning for Vision-Language Models CVPR 2026 Content-Aware Dynamic Patchification for Efficient Video Diffusion CVPR 2026 D²Pruner: Debiased Importance and Structural Diversity for MLLM Token Pruning AAAI 2026 DocPrune: Efficient Document Question Answering via Background, Question, and Comprehension-aware Token Pruning CVPR 2026 EQUIP: EQUivariant preserving In-Place updates for Efficient Token Pruning ACL 2026 FastDriveVLA: Efficient End-to-End Driving via Plug-and-Play Reconstruction-based Token Pruning AAAI 2026 From Inheritance to Saturation: Disentangling the Evolution of Visual Redundancy for Architecture-Aware MLLM Inference Acceleration ACL 2026 Hi-Lo Prune: Look at What You'll Lose before Pruning with Hierarchical Token Selection CVPR 2026 IF-Prune: Information-Flow Guided Token Pruning for Efficient Vision-Language Models CVPR 2026 KTV: Keyframes and Key Tokens Selection for Efficient Training-Free Video LLMs AAAI 2026 LazyVAR: Accelerating Visual Autoregressive Models via Scale-wise Token Pruning and Parallel Group Decoding CVPR 2026 Learnable Motion-Focused Tokenization for Effective and Efficient Video Unsupervised Domain Adaptation CVPR 2026 Lethe: Layer- and Time-Adaptive KV Cache Pruning for Reasoning-Intensive LLM Serving AAAI 2026 LightMover: Generative Light Movement with Color and Intensity Controls CVPR 2026 ParallelVLM: Lossless Video-LLM Acceleration with Visual Alignment Aware Parallel Speculative Decoding CVPR 2026 QuoTA: Query-oriented Token Assignment via CoT Query Decouple for Long Video Comprehension AAAI 2026 RADAR: VQ-VAE Decoder of VAR is a Good Student for Restoring Against Degradation by Acceleration CVPR 2026 Reducing Token Redundancy in LVLMs: A Systematic Review of Token Pruning Methods ACL 2026 ReGATE: Learning Faster and Better with Fewer Tokens in MLLMs ACL 2026 Semantically Comprehensive Token Pruning in LVLMs via Maximizing Concept Coverage ACL 2026 SlimInfer: Accelerating Long-Context LLM Inference via Dynamic Token Pruning AAAI 2026 SODA: Sensitivity-Oriented Dynamic Acceleration for Diffusion Transformer CVPR 2026