visual token

Accelerating Streaming Video Large Language Models via Hierarchical Token Compression CVPR 2026 AgentOCR: Reimagining Agent History via Optical Self-Compression ACL 2026 Aligning What Vision-Language Models See and Perceive with Adaptive Information Flow CVPR 2026 Boosting Reasoning in Large Multimodal Models via Activation Replay CVPR 2026 CARES: Context-Aware Resolution Selector for VLMs ACL 2026 CATP: Contextually Adaptive Token Pruning for Efficient and Enhanced Multimodal In-Context Learning AAAI 2026 CoIn: Coverage and Informativeness-Guided Token Reduction for Efficient Large Multimodal Models CVPR 2026 D3ToM: Decider-Guided Dynamic Token Merging for Accelerating Diffusion MLLMs AAAI 2026 Efficient Segmentation with Multimodal Large Language Model via Token Routing AAAI 2026 Evaluating Generative Models via One-Dimensional Code Distributions CVPR 2026 EvoComp: Learning Visual Token Compression for Multimodal Large Language Models via Semantic-Guided Evolutionary Labeling CVPR 2026 FlexiVideo: Variation-Aware Temporal Dynamics Modeling for Efficient Video Understanding CVPR 2026 Focus, Don't Prune: Identifying Instruction-Relevant Regions for Information-Rich Image Understanding CVPR 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 Language-guided Frequency Modulation for Large Vision-Language Models CVPR 2026 Make LVLMs Focus: Context-Aware Attention Modulation for Better Multimodal In-Context Learning AAAI 2026 MeToM: Metadata-Guided Token Merging for Efficient Video LLMs CVPR 2026 PurMM: Attention-Guided Test-Time Backdoor Purification in Multimodal Large Language Models AAAI 2026 Rethinking Visual Token Reduction in LVLMs Under Cross-Modal Misalignment AAAI 2026 Seeing Clearly, Reasoning Confidently: Plug-and-Play Remedies for Vision Language Model Blindness CVPR 2026 Semantically Comprehensive Token Pruning in LVLMs via Maximizing Concept Coverage ACL 2026 SpaceVLLM: Endowing Multimodal Large Language Model with Spatio-Temporal Video Grounding Capability AAAI 2026 UniComp: Rethinking Video Compression Through Informational Uniqueness CVPR 2026