{"total":53,"rows":[{"id":"2210.09461","title":"Token Merging: Your ViT But Faster","created":"2022-10-17","cited_by_count":1021,"area":"inference"},{"id":"2303.14189","title":"FastViT: A Fast Hybrid Vision Transformer using Structural Reparameterization","created":"2023-03-24","cited_by_count":162,"area":null},{"id":"2404.03384","title":"LongVLM: Efficient Long Video Understanding via Large Language Models","created":"2024-04-04","cited_by_count":147,"area":null},{"id":"2205.13213","title":"Fast Vision Transformers with HiLo Attention","created":"2022-05-26","cited_by_count":78,"area":null},{"id":"2111.04060","title":"Are we ready for a new paradigm shift? A Survey on Visual Deep MLP","created":"2021-11-07","cited_by_count":63,"area":null},{"id":"2211.03295","title":"MogaNet: Multi-order Gated Aggregation Network","created":"2022-11-07","cited_by_count":59,"area":null},{"id":"2304.06446","title":"SpectFormer: Frequency and Attention is what you need in a Vision Transformer","created":"2023-04-13","cited_by_count":48,"area":null},{"id":"2403.13347","title":"vid-TLDR: Training Free Token merging for Light-weight Video Transformer","created":"2024-03-20","cited_by_count":41,"area":null},{"id":"2302.06586","title":"Stitchable Neural Networks","created":"2023-02-13","cited_by_count":26,"area":null},{"id":"2306.00396","title":"Lightweight Vision Transformer with Bidirectional Interaction","created":"2023-06-01","cited_by_count":25,"area":null},{"id":"2111.11802","title":"Pruning Self-attentions into Convolutional Layers in Single Path","created":"2021-11-23","cited_by_count":24,"area":null},{"id":"2211.13955","title":"MPCViT: Searching for Accurate and Efficient MPC-Friendly Vision Transformer with Heterogeneous Attention","created":"2022-11-25","cited_by_count":20,"area":null},{"id":"2303.11126","title":"Robustifying Token Attention for Vision Transformers","created":"2023-03-20","cited_by_count":19,"area":null},{"id":"2311.01310","title":"Scattering Vision Transformer: Spectral Mixing Matters","created":"2023-11-02","cited_by_count":17,"area":null},{"id":"2207.10448","title":"An Efficient Spatio-Temporal Pyramid Transformer for Action Detection","created":"2022-07-21","cited_by_count":16,"area":null},{"id":"2303.01542","title":"Self-attention in Vision Transformers Performs Perceptual Grouping, Not Attention","created":"2023-03-02","cited_by_count":16,"area":null},{"id":"2308.02620","title":"Frequency Disentangled Features in Neural Image Compression","created":"2023-08-04","cited_by_count":14,"area":null},{"id":"2409.11923","title":"Agglomerative Token Clustering","created":"2024-09-18","cited_by_count":13,"area":null},{"id":"2411.14401","title":"Beyond Training: Dynamic Token Merging for Zero-Shot Video Understanding","created":"2024-11-21","cited_by_count":13,"area":"mllm"},{"id":"2309.04038","title":"S-Adapter: Generalizing Vision Transformer for Face Anti-Spoofing with Statistical Tokens","created":"2023-09-07","cited_by_count":11,"area":null},{"id":"2412.06263","title":"iLLaVA: An Image is Worth Fewer Than 1/3 Input Tokens in Large Multimodal Models","created":"2024-12-09","cited_by_count":11,"area":"mllm"},{"id":"2403.07965","title":"Conditional computation in neural networks: principles and research trends","created":"2024-03-12","cited_by_count":10,"area":"moe"},{"id":"2403.15520","title":"GTC: GNN-Transformer Co-contrastive Learning for Self-supervised Heterogeneous Graph Representation","created":"2024-03-22","cited_by_count":9,"area":null},{"id":"2404.09490","title":"Leveraging Temporal Contextualization for Video Action Recognition","created":"2024-04-15","cited_by_count":9,"area":null},{"id":"2211.07198","title":"Fcaformer: Forward Cross Attention in Hybrid Vision Transformer","created":"2022-11-14","cited_by_count":7,"area":null},{"id":"2406.00427","title":"You Only Need Less Attention at Each Stage in Vision Transformers","created":"2024-06-01","cited_by_count":7,"area":null},{"id":"2406.01283","title":"Focus on the Core: Efficient Attention via Pruned Token Compression for Document Classification","created":"2024-06-03","cited_by_count":7,"area":"inference"},{"id":"2509.00419","title":"LightVLM: Acceleraing Large Multimodal Models with Pyramid Token Merging and KV Cache Compression","created":"2025-08-30","cited_by_count":7,"area":"mllm"},{"id":"2302.08374","title":"Efficiency 360: Efficient Vision Transformers","created":"2023-02-16","cited_by_count":6,"area":null},{"id":"2408.01708","title":"AVESFormer: Efficient Transformer Design for Real-Time Audio-Visual Segmentation","created":"2024-08-03","cited_by_count":6,"area":null},{"id":"2303.17803","title":"Rethinking Local Perception in Lightweight Vision Transformer","created":"2023-03-31","cited_by_count":5,"area":null},{"id":"2111.13677","title":"SWAT: Spatial Structure Within and Among Tokens","created":"2021-11-26","cited_by_count":4,"area":null},{"id":"2401.00254","title":"Morphing Tokens Draw Strong Masked Image Models","created":"2023-12-30","cited_by_count":4,"area":null},{"id":"2402.11303","title":"FViT: A Focal Vision Transformer with Gabor Filter","created":"2024-02-17","cited_by_count":3,"area":null},{"id":"2308.05525","title":"Robustifying Point Cloud Networks by Refocusing","created":"2023-08-10","cited_by_count":2,"area":null},{"id":"2512.13855","title":"Improvise, Adapt, Overcome -- Telescopic Adapters for Efficient Fine-tuning of Vision Language Models in Medical Imaging","created":"2025-12-15","cited_by_count":2,"area":"mllm"},{"id":"2208.09968","title":"Transfer Ranking in Finance: Applications to Cross-Sectional Momentum with Data Scarcity","created":"2022-08-21","cited_by_count":1,"area":null},{"id":"2210.14319","title":"Explicitly Increasing Input Information Density for Vision Transformers on Small Datasets","created":"2022-10-25","cited_by_count":1,"area":null},{"id":"2211.14255","title":"Degenerate Swin to Win: Plain Window-based Transformer without Sophisticated Operations","created":"2022-11-25","cited_by_count":1,"area":null},{"id":"2310.06629","title":"EViT: An Eagle Vision Transformer with Bi-Fovea Self-Attention","created":"2023-10-10","cited_by_count":1,"area":null},{"id":"2311.13986","title":"FViT-Grasp: Grasping Objects With Using Fast Vision Transformers","created":"2023-11-23","cited_by_count":1,"area":null},{"id":"2409.07024","title":"SCLNet: A Scale-Robust Complementary Learning Network for Object Detection in UAV Images","created":"2024-09-11","cited_by_count":1,"area":null},{"id":"2211.12698","title":"Rega-Net:Retina Gabor Attention for Deep Convolutional Neural Networks","created":"2022-11-23","cited_by_count":0,"area":null},{"id":"2305.14840","title":"Predicting Token Impact Towards Efficient Vision Transformer","created":"2023-05-24","cited_by_count":0,"area":null},{"id":"2409.06963","title":"Brain-Inspired Stepwise Patch Merging for Vision Transformers","created":"2024-09-11","cited_by_count":0,"area":null},{"id":"2411.14789","title":"Simplifying CLIP: Unleashing the Power of Large-Scale Models on Consumer-level Computers","created":"2024-11-22","cited_by_count":0,"area":null},{"id":"2412.16491","title":"ImagePiece: Content-aware Re-tokenization for Efficient Image Recognition","created":"2024-12-21","cited_by_count":0,"area":null},{"id":"2508.01994","title":"Deeply Dual Supervised learning for melanoma recognition","created":"2025-08-04","cited_by_count":0,"area":null},{"id":"2508.06805","title":"Edge Detection for Organ Boundaries via Top Down Refinement and SubPixel Upsampling","created":"2025-08-09","cited_by_count":0,"area":null},{"id":"2508.06816","title":"DualResolution Residual Architecture with Artifact Suppression for Melanocytic Lesion Segmentation","created":"2025-08-09","cited_by_count":0,"area":null},{"id":"2508.06819","title":"VesselRW: Weakly Supervised Subcutaneous Vessel Segmentation via Learned Random Walk Propagation","created":"2025-08-09","cited_by_count":0,"area":null},{"id":"2603.20074","title":"MFil-Mamba: Multi-Filter Scanning for Spatial Redundancy-Aware Visual State Space Models","created":"2026-03-20","cited_by_count":0,"area":"ssm"},{"id":"2605.00789","title":"Make Your LVLM KV Cache More Lightweight","created":"2026-05-01","cited_by_count":0,"area":"mllm"}],"next_cursor":null}