visual token compression

AdaptVision: Efficient Vision-Language Models via Adaptive Visual Acquisition CVPR 2026 ApET: Approximation-Error Guided Token Compression for Efficient VLMs CVPR 2026 Are We Using the Right Benchmark: An Evaluation Framework for Visual Token Compression Methods ACL 2026 CORE: Compact Object-centric REpresentations as a New Paradigm for Token Merging in LVLMs CVPR 2026 AdaTP: Attention-Debiased Token Pruning for Video Large Language Models EMNLP 2025 FlashSloth : Lightning Multimodal Large Language Models via Embedded Visual Compression CVPR 2025 mPLUG-DocOwl2: High-resolution Compressing for OCR-free Multi-page Document Understanding ACL 2025 PVC: Progressive Visual Token Compression for Unified Image and Video Processing in Large Vision-Language Models CVPR 2025 Towards Text-Image Interleaved Retrieval ACL 2025 ViPE: Visual Perception in Parameter Space for Efficient Video-Language Understanding EMNLP 2025 Zero-shot 3D Question Answering via Voxel-based Dynamic Token Compression CVPR 2025 Efficient Large Multi-modal Models via Visual Context Compression NeurIPS 2024 Matryoshka Query Transformer for Large Vision-Language Models NeurIPS 2024 Query-based Cross-Modal Projector Bolstering Mamba Multimodal LLM EMNLP 2024