{"total":85,"rows":[{"id":"2401.08092","title":"A Survey of Resource-efficient LLM and Multimodal Foundation Models","created":"2024-01-16","cited_by_count":86,"area":null},{"id":"2303.04935","title":"X-Pruner: eXplainable Pruning for Vision Transformers","created":"2023-03-08","cited_by_count":68,"area":null},{"id":"2411.05222","title":"Don't Look Twice: Faster Video Transformers with Run-Length Tokenization","created":"2024-11-07","cited_by_count":43,"area":null},{"id":"2207.01685","title":"Interaction Transformer for Human Reaction Generation","created":"2022-07-04","cited_by_count":42,"area":null},{"id":"2211.10705","title":"TORE: Token Reduction for Efficient Human Mesh Recovery with Transformer","created":"2022-11-19","cited_by_count":41,"area":null},{"id":"2309.02031","title":"A survey on efficient vision transformers: algorithms, techniques, and performance benchmarking","created":"2023-09-05","cited_by_count":41,"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":"2412.20522","title":"MaskGaussian: Adaptive 3D Gaussian Representation from Probabilistic Masks","created":"2024-12-29","cited_by_count":41,"area":null},{"id":"2404.01882","title":"Scene Adaptive Sparse Transformer for Event-based Object Detection","created":"2024-04-02","cited_by_count":39,"area":null},{"id":"2210.01035","title":"Expediting Large-Scale Vision Transformer for Dense Prediction without Fine-tuning","created":"2022-10-03","cited_by_count":33,"area":null},{"id":"2403.10030","title":"Multi-criteria Token Fusion with One-step-ahead Attention for Efficient Vision Transformers","created":"2024-03-15","cited_by_count":26,"area":null},{"id":"2306.06289","title":"SegViTv2: Exploring Efficient and Continual Semantic Segmentation with Plain Vision Transformers","created":"2023-06-09","cited_by_count":25,"area":null},{"id":"2412.12441","title":"Numerical Pruning for Efficient Autoregressive Models","created":"2024-12-17","cited_by_count":25,"area":null},{"id":"2301.02240","title":"Skip-Attention: Improving Vision Transformers by Paying Less Attention","created":"2023-01-05","cited_by_count":24,"area":null},{"id":"2503.02891","title":"Vision Transformers on the Edge: A Comprehensive Survey of Model Compression and Acceleration Strategies","created":"2025-02-26","cited_by_count":24,"area":null},{"id":"2306.11726","title":"How can objects help action recognition?","created":"2023-06-20","cited_by_count":21,"area":null},{"id":"2403.09192","title":"PYRA: Parallel Yielding Re-Activation for Training-Inference Efficient Task Adaptation","created":"2024-03-14","cited_by_count":17,"area":null},{"id":"2204.01244","title":"Dynamic Focus-aware Positional Queries for Semantic Segmentation","created":"2022-04-04","cited_by_count":16,"area":null},{"id":"2402.10787","title":"Squat: Quant Small Language Models on the Edge","created":"2024-02-16","cited_by_count":16,"area":null},{"id":"2407.02068","title":"LPViT: Low-Power Semi-structured Pruning for Vision Transformers","created":"2024-07-02","cited_by_count":16,"area":null},{"id":"2311.12028","title":"Hourglass Tokenizer for Efficient Transformer-Based 3D Human Pose Estimation","created":"2023-11-20","cited_by_count":15,"area":null},{"id":"2304.05659","title":"RIFormer: Keep Your Vision Backbone Effective While Removing Token Mixer","created":"2023-04-12","cited_by_count":13,"area":null},{"id":"2403.10799","title":"Toward Adaptive Large Language Models Structured Pruning via Hybrid-grained Weight Importance Assessment","created":"2024-03-16","cited_by_count":13,"area":null},{"id":"2409.11923","title":"Agglomerative Token Clustering","created":"2024-09-18","cited_by_count":13,"area":null},{"id":"2510.18091","title":"Accelerating Vision Transformers with Adaptive Patch Sizes","created":"2025-10-20","cited_by_count":13,"area":null},{"id":"2409.17978","title":"HydraViT: Stacking Heads for a Scalable ViT","created":"2024-09-26","cited_by_count":11,"area":null},{"id":"2407.05010","title":"PRANCE: Joint Token-Optimization and Structural Channel-Pruning for Adaptive ViT Inference","created":"2024-07-06","cited_by_count":10,"area":null},{"id":"2305.17223","title":"Do We Really Need a Large Number of Visual Prompts?","created":"2023-05-26","cited_by_count":9,"area":null},{"id":"2310.10700","title":"PELA: Learning Parameter-Efficient Models with Low-Rank Approximation","created":"2023-10-16","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":"2405.09789","title":"LeMeViT: Efficient Vision Transformer with Learnable Meta Tokens for Remote Sensing Image Interpretation","created":"2024-05-16","cited_by_count":9,"area":null},{"id":"2407.20021","title":"MimiQ: Low-Bit Data-Free Quantization of Vision Transformers with Encouraging Inter-Head Attention Similarity","created":"2024-07-29","cited_by_count":9,"area":null},{"id":"2211.01484","title":"Data Level Lottery Ticket Hypothesis for Vision Transformers","created":"2022-11-02","cited_by_count":7,"area":null},{"id":"2211.14742","title":"Dynamic Feature Pruning and Consolidation for Occluded Person Re-Identification","created":"2022-11-27","cited_by_count":7,"area":null},{"id":"2501.16811","title":"Not Every Patch is Needed: Towards a More Efficient and Effective Backbone for Video-based Person Re-identification","created":"2025-01-28","cited_by_count":7,"area":null},{"id":"2310.05654","title":"No Token Left Behind: Efficient Vision Transformer via Dynamic Token Idling","created":"2023-10-09","cited_by_count":5,"area":null},{"id":"2504.02168","title":"MDP: Multidimensional Vision Model Pruning with Latency Constraint","created":"2025-04-02","cited_by_count":5,"area":null},{"id":"2505.21847","title":"RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers","created":"2025-05-28","cited_by_count":5,"area":null},{"id":"2506.11131","title":"Segment This Thing: Foveated Tokenization for Efficient Point-Prompted Segmentation","created":"2025-06-10","cited_by_count":5,"area":null},{"id":"2509.06956","title":"H$_{2}$OT: Hierarchical Hourglass Tokenizer for Efficient Video Pose Transformers","created":"2025-09-08","cited_by_count":5,"area":null},{"id":"2512.22208","title":"Open-Source Multimodal Moxin Models with Moxin-VLM and Moxin-VLA","created":"2025-12-22","cited_by_count":5,"area":null},{"id":"2402.06004","title":"Memory-Efficient Vision Transformers: An Activation-Aware Mixed-Rank Compression Strategy","created":"2024-02-08","cited_by_count":4,"area":null},{"id":"2406.12079","title":"Multi-Dimensional Pruning: Joint Channel, Layer and Block Pruning with Latency Constraint","created":"2024-06-17","cited_by_count":4,"area":null},{"id":"2410.14729","title":"Is Less More? Exploring Token Condensation as Training-free Test-time Adaptation","created":"2024-10-16","cited_by_count":4,"area":null},{"id":"2412.02054","title":"Redundant Queries in DETR-Based 3D Detection Methods: Unnecessary and Prunable","created":"2024-12-03","cited_by_count":4,"area":null},{"id":"2504.04024","title":"Window Token Concatenation for Efficient Visual Large Language Models","created":"2025-04-05","cited_by_count":3,"area":null},{"id":"2507.14315","title":"A Hidden Stumbling Block in Generalized Category Discovery: Distracted Attention","created":"2025-07-18","cited_by_count":3,"area":null},{"id":"2507.19131","title":"MixA-Q: Revisiting Activation Sparsity for Vision Transformers from a Mixed-Precision Quantization Perspective","created":"2025-07-25","cited_by_count":3,"area":null},{"id":"2404.00672","title":"A General and Efficient Training for Transformer via Token Expansion","created":"2024-03-31","cited_by_count":2,"area":null},{"id":"2404.15802","title":"Raformer: Redundancy-Aware Transformer for Video Wire Inpainting","created":"2024-04-24","cited_by_count":2,"area":null},{"id":"2408.13963","title":"Shifted Window Fourier Transform And Retention For Image Captioning","created":"2024-08-25","cited_by_count":2,"area":null},{"id":"2409.09708","title":"ELSA: Exploiting Layer-wise N:M Sparsity for Vision Transformer Acceleration","created":"2024-09-15","cited_by_count":2,"area":null},{"id":"2409.19850","title":"SATA: Spatial Autocorrelation Token Analysis for Enhancing the Robustness of Vision Transformers","created":"2024-09-30","cited_by_count":2,"area":null},{"id":"2411.15397","title":"Visual-Word Tokenizer: Beyond Fixed Sets of Tokens in Vision Transformers","created":"2024-11-23","cited_by_count":2,"area":null},{"id":"2505.03113","title":"Image Recognition with Online Lightweight Vision Transformer: A Survey","created":"2025-05-06","cited_by_count":2,"area":null},{"id":"2512.21867","title":"DPAR: Dynamic Patchification for Efficient Autoregressive Visual Generation","created":"2025-12-26","cited_by_count":2,"area":null},{"id":"2312.16392","title":"Adaptive Depth Networks with Skippable Sub-Paths","created":"2023-12-27","cited_by_count":1,"area":null},{"id":"2406.03088","title":"HASS: Hardware-Aware Sparsity Search for Dataflow DNN Accelerator","created":"2024-06-05","cited_by_count":1,"area":null},{"id":"2409.05642","title":"Prototype-Driven Multi-Feature Generation for Visible-Infrared Person Re-identification","created":"2024-09-09","cited_by_count":1,"area":null},{"id":"2410.07268","title":"Learning Content-Aware Multi-Modal Joint Input Pruning via Bird's-Eye-View Representation","created":"2024-10-09","cited_by_count":1,"area":null},{"id":"2507.10283","title":"FTCFormer: Fuzzy Token Clustering Transformer for Image Classification","created":"2025-07-14","cited_by_count":1,"area":null},{"id":"2509.03872","title":"Focus Through Motion: RGB-Event Collaborative Token Sparsification for Efficient Object Detection","created":"2025-09-04","cited_by_count":1,"area":null},{"id":"2510.09553","title":"Hierarchical Indexing with Knowledge Enrichment for Multilingual Video Corpus Retrieval","created":"2025-10-10","cited_by_count":1,"area":null},{"id":"2601.02437","title":"TAP-ViTs: Task-Adaptive Pruning for On-Device Deployment of Vision Transformers","created":"2026-01-05","cited_by_count":1,"area":null},{"id":"2405.15633","title":"Less is more: Summarizing Patch Tokens for efficient Multi-Label Class-Incremental Learning","created":"2024-05-24","cited_by_count":0,"area":null},{"id":"2407.16716","title":"Exploring The Neural Burden In Pruned Models: An Insight Inspired By Neuroscience","created":"2024-07-23","cited_by_count":0,"area":null},{"id":"2507.12125","title":"Block-based Symmetric Pruning and Fusion for Efficient Vision Transformers","created":"2025-07-16","cited_by_count":0,"area":null},{"id":"2507.12780","title":"Compact Vision Transformer by Reduction of Kernel Complexity","created":"2025-07-17","cited_by_count":0,"area":null},{"id":"2508.05851","title":"Temporal Cluster Assignment for Efficient Real-Time Video Segmentation","created":"2025-08-07","cited_by_count":0,"area":null},{"id":"2511.14111","title":"CascadedViT: Cascaded Chunk-FeedForward and Cascaded Group Attention Vision Transformer","created":"2025-11-18","cited_by_count":0,"area":null},{"id":"2511.22281","title":"Collapse of Patches: Ranking Image Patches for Efficient Visual Modeling","created":"2025-11-27","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":"2602.15720","title":"ToaSt: Token Channel Selection and Structured Pruning for Efficient ViT","created":"2026-02-17","cited_by_count":0,"area":null},{"id":"2603.12222","title":"HiAP: A Multi-Granular Stochastic Auto-Pruning Framework for Vision Transformers","created":"2026-03-12","cited_by_count":0,"area":null},{"id":"2604.03803","title":"R\\'enyi Attention Entropy for Patch Pruning","created":"2026-04-04","cited_by_count":0,"area":null},{"id":"2604.11415","title":"Observe Less, Understand More: Cost-aware Cross-scale Observation for Remote Sensing Understanding","created":"2026-04-13","cited_by_count":0,"area":null},{"id":"2605.01742","title":"Joint Architecture-Token-Bitwidth Multi-Axis Optimization of Vision Transformers for Semiconductor IC Packaging","created":"2026-05-03","cited_by_count":0,"area":null},{"id":"2605.14110","title":"SToRe3D: Sparse Token Relevance in ViTs for Efficient Multi-View 3D Object Detection","created":"2026-05-13","cited_by_count":0,"area":null},{"id":"2606.31676","title":"REDI: Corpus Aware Patch Ranking for DINOv3 Token Reduction","created":"2026-06-30","cited_by_count":0,"area":null},{"id":"2607.02829","title":"Less Tokens, Better Forecasts: Sparse Residual Routing for Efficient Weather Prediction","created":"2026-07-02","cited_by_count":0,"area":null},{"id":"2608.12045","title":"Localizing to Debias: A Patch-Level Benchmark and Baseline for Weakly Supervised Spatial Anomaly Detection","created":"2026-08-12","cited_by_count":0,"area":null},{"id":"2608.19232","title":"Active Spiking Perception: The Membrane Potential as a Belief State for Anytime 3D Point Cloud Recognition","created":"2026-08-04","cited_by_count":0,"area":null},{"id":"2609.18578","title":"Learning Where to Focus: Self-Supervised Multi-Scale ViTs for Histopathology","created":"2026-09-16","cited_by_count":0,"area":null},{"id":"2609.30613","title":"MedTokenBudget: Lesion-Preserving Token Routing for Dermoscopic Image Classification","created":"2026-09-24","cited_by_count":0,"area":null},{"id":"2610.20588","title":"Your Transformer Is Secretly Elastic","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}