visual token

Unified Spatiotemporal Token Compression for Video-LLMs at Ultra-Low Retention CVPR 2026 VisRef: Visual Refocusing while Thinking Improves Test-Time Scaling in Multi-Modal Large Reasoning Models CVPR 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 AIM: Adaptive Inference of Multi-Modal LLMs via Token Merging and Pruning ICCV 2025 AirCache: Activating Inter-modal Relevancy KV Cache Compression for Efficient Large Vision-Language Model Inference ICCV 2025 An Empirical Study of Autoregressive Pre-training from Videos ICCV 2025 ART: Anonymous Region Transformer for Variable Multi-Layer Transparent Image Generation CVPR 2025 Autoregressive Sequence Modeling for 3D Medical Image Representation AAAI 2025 AVG-LLaVA: An Efficient Large Multimodal Model with Adaptive Visual Granularity ACL 2025 Boosting Multimodal Large Language Models with Visual Tokens Withdrawal for Rapid Inference AAAI 2025 B-VLLM: A Vision Large Language Model with Balanced Spatio-Temporal Tokens ICCV 2025 D-Attn: Decomposed Attention for Large Vision-and-Language Model ICCV 2025 DisCo: Towards Distinct and Coherent Visual Encapsulation in Video MLLMs ICCV 2025 DocKylin: A Large Multimodal Model for Visual Document Understanding with Efficient Visual Slimming AAAI 2025 DToMA: Training-free Dynamic Token MAnipulation for Long Video Understanding IJCAI 2025 Eagle: Exploring The Design Space for Multimodal LLMs with Mixture of Encoders ICLR 2025 Generative Multimodal Pretraining with Discrete Diffusion Timestep Tokens CVPR 2025 HiRED: Attention-Guided Token Dropping for Efficient Inference of High-Resolution Vision-Language Models AAAI 2025 HiRes-LLaVA: Restoring Fragmentation Input in High-Resolution Large Vision-Language Models CVPR 2025 Holistic Tokenizer for Autoregressive Image Generation ICCV 2025 How Can Objects Help Video-Language Understanding? ICCV 2025 Hybrid-Level Instruction Injection for Video Token Compression in Multi-modal Large Language Models CVPR 2025 Improving LLM Video Understanding with 16 Frames Per Second ICML 2025 Inference Optimal VLMs Need Fewer Visual Tokens and More Parameters ICLR 2025