{"total":60,"rows":[{"id":"2403.15388","title":"LLaVA-PruMerge: Adaptive Token Reduction for Efficient Large Multimodal Models","created":"2024-03-22","cited_by_count":402,"area":"lr"},{"id":"2509.02560","title":"FastVGGT: Training-Free Acceleration of Visual Geometry Transformer","created":"2025-09-02","cited_by_count":98,"area":"inference"},{"id":"2405.17430","title":"Matryoshka Multimodal Models","created":"2024-05-27","cited_by_count":84,"area":"mllm"},{"id":"2406.05127","title":"Towards Semantic Equivalence of Tokenization in Multimodal LLM","created":"2024-06-07","cited_by_count":45,"area":"mllm"},{"id":"2403.10254","title":"Magic Tokens: Select Diverse Tokens for Multi-modal Object Re-Identification","created":"2024-03-15","cited_by_count":35,"area":null},{"id":"2404.10308","title":"Hierarchical Context Merging: Better Long Context Understanding for Pre-trained LLMs","created":"2024-04-16","cited_by_count":30,"area":null},{"id":"2505.19147","title":"Shifting AI Efficiency From Model-Centric to Data-Centric Compression","created":"2025-05-25","cited_by_count":29,"area":"mllm"},{"id":"2406.09936","title":"ALGM: Adaptive Local-then-Global Token Merging for Efficient Semantic Segmentation with Plain Vision Transformers","created":"2024-06-14","cited_by_count":28,"area":"inference"},{"id":"2411.16720","title":"Importance-Based Token Merging for Efficient Image and Video Generation","created":"2024-11-23","cited_by_count":22,"area":"diffusion"},{"id":"2402.14327","title":"Subobject-level Image Tokenization","created":"2024-02-22","cited_by_count":21,"area":null},{"id":"2412.00965","title":"Token Cropr: Faster ViTs for Quite a Few Tasks","created":"2024-12-01","cited_by_count":19,"area":"inference"},{"id":"2511.19515","title":"Fewer Tokens, Greater Scaling: Self-Adaptive Visual Bases for Efficient and Expansive Representation Learning","created":"2025-11-24","cited_by_count":16,"area":null},{"id":"2512.02541","title":"AVGGT: Rethinking Global Attention for Accelerating VGGT","created":"2025-12-02","cited_by_count":16,"area":null},{"id":"2510.17777","title":"SparseVILA: Decoupling Visual Sparsity for Efficient VLM Inference","created":"2025-10-20","cited_by_count":15,"area":"mllm"},{"id":"2410.17241","title":"Frontiers in Intelligent Colonoscopy","created":"2024-10-22","cited_by_count":14,"area":null},{"id":"2409.11923","title":"Agglomerative Token Clustering","created":"2024-09-18","cited_by_count":13,"area":null},{"id":"2405.14700","title":"Sparse-Tuning: Adapting Vision Transformers with Efficient Fine-tuning and Inference","created":"2024-05-23","cited_by_count":12,"area":null},{"id":"2504.01690","title":"Token Pruning in Audio Transformers: Optimizing Performance and Decoding Patch Importance","created":"2025-04-02","cited_by_count":12,"area":"inference"},{"id":"2403.07965","title":"Conditional computation in neural networks: principles and research trends","created":"2024-03-12","cited_by_count":10,"area":"moe"},{"id":"2407.05941","title":"Pruning One More Token is Enough: Leveraging Latency-Workload Non-Linearities for Vision Transformers on the Edge","created":"2024-07-01","cited_by_count":9,"area":"inference"},{"id":"2405.17815","title":"Visual Anchors Are Strong Information Aggregators For Multimodal Large Language Model","created":"2024-05-28","cited_by_count":8,"area":"mllm"},{"id":"2411.15446","title":"freePruner: A Training-free Approach for Large Multimodal Model Acceleration","created":"2024-11-23","cited_by_count":8,"area":"mllm"},{"id":"2312.10193","title":"Adaptive Computation Modules: Granular Conditional Computation For Efficient Inference","created":"2023-12-15","cited_by_count":6,"area":null},{"id":"2410.07278","title":"PAR: Prompt-Aware Token Reduction Method for Efficient Large Multimodal Models","created":"2024-10-09","cited_by_count":5,"area":"mllm"},{"id":"2505.18051","title":"LookWhere? Efficient Visual Recognition by Learning Where to Look and What to See from Self-Supervision","created":"2025-05-23","cited_by_count":5,"area":null},{"id":"2408.17062","title":"Vote&Mix: Plug-and-Play Token Reduction for Efficient Vision Transformer","created":"2024-08-30","cited_by_count":4,"area":"inference"},{"id":"2412.13437","title":"Deploying Foundation Model Powered Agent Services: A Survey","created":"2024-12-18","cited_by_count":4,"area":"agents"},{"id":"2503.23455","title":"Efficient Token Compression for Vision Transformer with Spatial Information Preserved","created":"2025-03-30","cited_by_count":4,"area":"inference"},{"id":"2506.07077","title":"Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models","created":"2025-06-08","cited_by_count":4,"area":"mllm"},{"id":"2510.27186","title":"Sparse Model Inversion: Efficient Inversion of Vision Transformers for Data-Free Applications","created":"2025-10-31","cited_by_count":4,"area":null},{"id":"2412.16553","title":"Semantic Alignment and Reinforcement for Data-Free Quantization of Vision Transformers","created":"2024-12-21","cited_by_count":3,"area":null},{"id":"2507.09702","title":"Token Compression Meets Compact Vision Transformers: A Survey and Comparative Evaluation for Edge AI","created":"2025-07-13","cited_by_count":3,"area":"inference"},{"id":"2407.13750","title":"PO-GUISE+: Pose and object guided transformer token selection for efficient driver action recognition","created":"2024-07-18","cited_by_count":2,"area":null},{"id":"2409.07613","title":"Token Turing Machines are Efficient Vision Models","created":"2024-09-11","cited_by_count":2,"area":null},{"id":"2412.18675","title":"TAB: Transformer Attention Bottlenecks enable User Intervention and Debugging in Vision-Language Models","created":"2024-12-24","cited_by_count":2,"area":"mllm"},{"id":"2505.23004","title":"QLIP: A Dynamic Quadtree Vision Prior Enhances MLLM Performance Without Retraining","created":"2025-05-29","cited_by_count":2,"area":"mllm"},{"id":"2509.13255","title":"ResidualViT for Efficient Temporally Dense Video Encoding","created":"2025-09-16","cited_by_count":2,"area":null},{"id":"2509.17809","title":"MTM: A Multi-Scale Token Mixing Transformer for Irregular Multivariate Time Series Classification","created":"2025-09-22","cited_by_count":2,"area":null},{"id":"2603.26336","title":"From Pixels to Privacy: Temporally Consistent Video Anonymization via Token Pruning for Privacy Preserving Action Recognition","created":"2026-03-27","cited_by_count":2,"area":null},{"id":"2604.07994","title":"SAT: Selective Aggregation Transformer for Image Super-Resolution","created":"2026-04-09","cited_by_count":2,"area":null},{"id":"2507.14042","title":"Training-free Token Reduction for Vision Mamba","created":"2025-07-18","cited_by_count":1,"area":"ssm"},{"id":"2508.16311","title":"Exploiting Information Redundancy in Attention Maps for Extreme Quantization of Vision Transformers","created":"2025-08-22","cited_by_count":1,"area":null},{"id":"2603.14549","title":"ASAP: Attention-Shift-Aware Pruning for Efficient LVLM Inference","created":"2026-03-15","cited_by_count":1,"area":"mllm"},{"id":"2606.18439","title":"RegimeVGGT: Layer-Wise Spatially Preserving Redundancy Removal for Visual Geometry Grounded Transformer","created":"2026-06-16","cited_by_count":1,"area":null},{"id":"2308.13505","title":"Joint Modeling of Feature, Correspondence, and a Compressed Memory for Video Object Segmentation","created":"2023-08-25","cited_by_count":0,"area":null},{"id":"2410.07737","title":"Plug-and-Play Performance Estimation for LLM Services without Relying on Labeled Data","created":"2024-10-10","cited_by_count":0,"area":null},{"id":"2411.18092","title":"Training Noise Token Pruning","created":"2024-11-27","cited_by_count":0,"area":"inference"},{"id":"2508.05851","title":"Temporal Cluster Assignment for Efficient Real-Time Video Segmentation","created":"2025-08-07","cited_by_count":0,"area":null},{"id":"2509.04009","title":"Token-Based Detection of Spurious Correlations in Vision Transformers","created":"2025-09-04","cited_by_count":0,"area":null},{"id":"2510.23665","title":"Transformers from Compressed Representations","created":"2025-10-26","cited_by_count":0,"area":null},{"id":"2601.21362","title":"ViTMAlis: Towards Latency-Critical Mobile Video Analytics with Vision Transformers","created":"2026-01-29","cited_by_count":0,"area":null},{"id":"2603.29460","title":"Square Superpixel Generation and Representation Learning via Granular Ball Computing","created":"2026-03-31","cited_by_count":0,"area":null},{"id":"2604.18367","title":"EAST: Early Action Prediction Sampling Strategy with Token Masking","created":"2026-04-20","cited_by_count":0,"area":null},{"id":"2607.02237","title":"When Token Compression Breaks: Structural Pruning vs. Token Reduction for Robust ViT Segmentation under High Compression","created":"2026-07-02","cited_by_count":0,"area":"inference"},{"id":"2607.15563","title":"Are All Tokens Necessary for Visual Place Recognition? An Empirical Study of Token Reduction for Efficient Inference","created":"2026-07-17","cited_by_count":0,"area":"inference"},{"id":"2608.10989","title":"Putting Registers to Work: Task Registers for Token Pruning in Vision Transformers","created":"2026-08-11","cited_by_count":0,"area":"inference"},{"id":"2608.23142","title":"How Merge-Tolerant Are Vision Transformers for Wheat Phenotyping?","created":"2026-08-24","cited_by_count":0,"area":null},{"id":"2608.28706","title":"Variable-Granularity Tokenization for High-Resolution Object Detection","created":"2026-08-27","cited_by_count":0,"area":null},{"id":"2609.04698","title":"LookThere! Sparse Vision by Reinforced Selection","created":"2026-09-04","cited_by_count":0,"area":null},{"id":"2610.18039","title":"Scaling Vision Transformers Without Training: Prune-and-Merge Token Compression","created":"2026-10-13","cited_by_count":0,"area":"inference"}],"next_cursor":null}