{"total":139,"rows":[{"id":"2210.09461","title":"Token Merging: Your ViT But Faster","created":"2022-10-17","cited_by_count":1021,"area":"inference"},{"id":"2310.01801","title":"Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs","created":"2023-10-03","cited_by_count":474,"area":"inference"},{"id":"2111.11326","title":"DyTox: Transformers for Continual Learning with DYnamic TOken eXpansion","created":"2021-11-22","cited_by_count":291,"area":null},{"id":"2310.05736","title":"LLMLingua: Compressing Prompts for Accelerated Inference of Large Language Models","created":"2023-10-09","cited_by_count":287,"area":null},{"id":"2108.01390","title":"Evo-ViT: Slow-Fast Token Evolution for Dynamic Vision Transformer","created":"2021-08-03","cited_by_count":177,"area":"inference"},{"id":"2405.05803","title":"Boosting Multimodal Large Language Models with Visual Tokens Withdrawal for Rapid Inference","created":"2024-05-09","cited_by_count":139,"area":"mllm"},{"id":"2312.01026","title":"Token Fusion: Bridging the Gap between Token Pruning and Token Merging","created":"2023-12-02","cited_by_count":125,"area":"inference"},{"id":"2203.07259","title":"The Optimal BERT Surgeon: Scalable and Accurate Second-Order Pruning for Large Language Models","created":"2022-03-14","cited_by_count":115,"area":"inference"},{"id":"2505.23416","title":"KVzip: Query-Agnostic KV Cache Compression with Context Reconstruction","created":"2025-05-29","cited_by_count":95,"area":"inference"},{"id":"2412.00447","title":"ATP-LLaVA: Adaptive Token Pruning for Large Vision Language Models","created":"2024-11-30","cited_by_count":89,"area":"mllm"},{"id":"2302.14017","title":"Full Stack Optimization of Transformer Inference: a Survey","created":"2023-02-27","cited_by_count":80,"area":null},{"id":"2407.14057","title":"LazyLLM: Dynamic Token Pruning for Efficient Long Context LLM Inference","created":"2024-07-19","cited_by_count":70,"area":"inference"},{"id":"2305.15805","title":"Dynamic Context Pruning for Efficient and Interpretable Autoregressive Transformers","created":"2023-05-25","cited_by_count":67,"area":null},{"id":"2402.09748","title":"Model Compression and Efficient Inference for Large Language Models: A Survey","created":"2024-02-15","cited_by_count":64,"area":null},{"id":"2305.17328","title":"Zero-TPrune: Zero-Shot Token Pruning through Leveraging of the Attention Graph in Pre-Trained Transformers","created":"2023-05-27","cited_by_count":62,"area":"inference"},{"id":"2407.05858","title":"Fast On-device LLM Inference with NPUs","created":"2024-07-08","cited_by_count":62,"area":null},{"id":"2303.17605","title":"SparseViT: Revisiting Activation Sparsity for Efficient High-Resolution Vision Transformer","created":"2023-03-30","cited_by_count":60,"area":null},{"id":"2505.18227","title":"Token Reduction Should Go Beyond Efficiency in Generative Models -- From Vision, Language to Multimodality","created":"2025-05-23","cited_by_count":50,"area":"inference"},{"id":"2402.05964","title":"A Survey on Transformer Compression","created":"2024-02-05","cited_by_count":46,"area":null},{"id":"2202.07105","title":"A Survey on Model Compression and Acceleration for Pretrained Language Models","created":"2022-02-15","cited_by_count":45,"area":null},{"id":"2309.04255","title":"LLMCad: Fast and Scalable On-device Large Language Model Inference","created":"2023-09-08","cited_by_count":45,"area":null},{"id":"2305.17455","title":"CrossGET: Cross-Guided Ensemble of Tokens for Accelerating Vision-Language Transformers","created":"2023-05-27","cited_by_count":44,"area":"mllm"},{"id":"2412.03248","title":"AIM: Adaptive Inference of Multi-Modal LLMs via Token Merging and Pruning","created":"2024-12-04","cited_by_count":43,"area":"mllm"},{"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":"2404.01882","title":"Scene Adaptive Sparse Transformer for Event-based Object Detection","created":"2024-04-02","cited_by_count":39,"area":null},{"id":"2307.12612","title":"Less is More: Focus Attention for Efficient DETR","created":"2023-07-24","cited_by_count":38,"area":null},{"id":"2404.06918","title":"HRVDA: High-Resolution Visual Document Assistant","created":"2024-04-10","cited_by_count":37,"area":"mllm"},{"id":"2509.12594","title":"The Better You Learn, The Smarter You Prune: Towards Efficient Vision-language-action Models via Differentiable Token Pruning","created":"2025-09-16","cited_by_count":36,"area":"vla"},{"id":"2209.13802","title":"Adaptive Sparse ViT: Towards Learnable Adaptive Token Pruning by Fully Exploiting Self-Attention","created":"2022-09-28","cited_by_count":35,"area":"inference"},{"id":"2307.07982","title":"A Survey of Techniques for Optimizing Transformer Inference","created":"2023-07-16","cited_by_count":35,"area":null},{"id":"2405.16148","title":"Accelerating Transformers with Spectrum-Preserving Token Merging","created":"2024-05-25","cited_by_count":35,"area":"inference"},{"id":"2503.07588","title":"When Large Vision-Language Model Meets Large Remote Sensing Imagery: Coarse-to-Fine Text-Guided Token Pruning","created":"2025-03-10","cited_by_count":35,"area":"mllm"},{"id":"2310.03535","title":"Towards Unified Deep Image Deraining: A Survey and A New Benchmark","created":"2023-10-05","cited_by_count":34,"area":null},{"id":"2312.03771","title":"DreamInpainter: Text-Guided Subject-Driven Image Inpainting with Diffusion Models","created":"2023-12-05","cited_by_count":31,"area":"diffusion"},{"id":"2504.02441","title":"Cognitive Memory in Large Language Models","created":"2025-04-03","cited_by_count":29,"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":"2503.23798","title":"Adaptive Layer-skipping in Pre-trained LLMs","created":"2025-03-31","cited_by_count":27,"area":null},{"id":"2306.01160","title":"Faster Causal Attention Over Large Sequences Through Sparse Flash Attention","created":"2023-06-01","cited_by_count":25,"area":null},{"id":"2202.07101","title":"A Survey on Dynamic Neural Networks for Natural Language Processing","created":"2022-02-15","cited_by_count":24,"area":null},{"id":"2205.07324","title":"Transkimmer: Transformer Learns to Layer-wise Skim","created":"2022-05-15","cited_by_count":24,"area":null},{"id":"2210.07913","title":"Efficiently Controlling Multiple Risks with Pareto Testing","created":"2022-10-14","cited_by_count":22,"area":null},{"id":"2407.14439","title":"Token-level Correlation-guided Compression for Efficient Multimodal Document Understanding","created":"2024-07-19","cited_by_count":22,"area":"mllm"},{"id":"2307.10780","title":"Learned Thresholds Token Merging and Pruning for Vision Transformers","created":"2023-07-20","cited_by_count":21,"area":"inference"},{"id":"2412.12009","title":"SpeechPrune: Context-aware Token Pruning for Speech Information Retrieval","created":"2024-12-16","cited_by_count":21,"area":"inference"},{"id":"2210.09223","title":"CAP: Correlation-Aware Pruning for Highly-Accurate Sparse Vision Models","created":"2022-10-14","cited_by_count":20,"area":null},{"id":"2203.12758","title":"Mokey: Enabling Narrow Fixed-Point Inference for Out-of-the-Box Floating-Point Transformer Models","created":"2022-03-23","cited_by_count":19,"area":null},{"id":"2310.05015","title":"Compresso: Structured Pruning with Collaborative Prompting Learns Compact Large Language Models","created":"2023-10-08","cited_by_count":19,"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":"2407.08892","title":"Characterizing Prompt Compression Methods for Long Context Inference","created":"2024-07-11","cited_by_count":18,"area":"inference"},{"id":"2410.01537","title":"Attention layers provably solve single-location regression","created":"2024-10-02","cited_by_count":17,"area":null},{"id":"2111.00230","title":"Magic Pyramid: Accelerating Inference with Early Exiting and Token Pruning","created":"2021-10-30","cited_by_count":16,"area":"inference"},{"id":"2508.13305","title":"Prune2Drive: A Plug-and-Play Framework for Accelerating Vision-Language Models in Autonomous Driving","created":"2025-08-18","cited_by_count":16,"area":"mllm"},{"id":"2305.16503","title":"IMBERT: Making BERT Immune to Insertion-based Backdoor Attacks","created":"2023-05-25","cited_by_count":15,"area":"safety"},{"id":"2306.16009","title":"Accelerating Transducers through Adjacent Token Merging","created":"2023-06-28","cited_by_count":15,"area":"inference"},{"id":"2401.15347","title":"A Comprehensive Survey of Compression Algorithms for Language Models","created":"2024-01-27","cited_by_count":15,"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":"2212.03597","title":"DeepSpeed Data Efficiency: Improving Deep Learning Model Quality and Training Efficiency via Efficient Data Sampling and Routing","created":"2022-12-07","cited_by_count":13,"area":null},{"id":"2209.00606","title":"Sparse Attention Acceleration with Synergistic In-Memory Pruning and On-Chip Recomputation","created":"2022-09-01","cited_by_count":12,"area":null},{"id":"2304.04672","title":"Deep Image Matting: A Comprehensive Survey","created":"2023-04-10","cited_by_count":12,"area":null},{"id":"2503.16980","title":"VQToken: Neural Discrete Token Representation Learning for Extreme Token Reduction in Video Large Language Models","created":"2025-03-21","cited_by_count":12,"area":"inference"},{"id":"2211.11586","title":"Random-LTD: Random and Layerwise Token Dropping Brings Efficient Training for Large-scale Transformers","created":"2022-11-17","cited_by_count":11,"area":null},{"id":"2310.01777","title":"SEA: Sparse Linear Attention with Estimated Attention Mask","created":"2023-10-03","cited_by_count":10,"area":null},{"id":"2502.16782","title":"CipherPrune: Efficient and Scalable Private Transformer Inference","created":"2025-02-24","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":"2403.16020","title":"PaPr: Training-Free One-Step Patch Pruning with Lightweight ConvNets for Faster Inference","created":"2024-03-24","cited_by_count":9,"area":null},{"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":"2305.05433","title":"Tomography of Quantum States from Structured Measurements via quantum-aware transformer","created":"2023-05-09","cited_by_count":8,"area":null},{"id":"2404.01591","title":"Language Model Guided Interpretable Video Action Reasoning","created":"2024-04-02","cited_by_count":8,"area":"lr"},{"id":"2405.17052","title":"SelfCP: Compressing Over-Limit Prompt via the Frozen Large Language Model Itself","created":"2024-05-27","cited_by_count":8,"area":null},{"id":"2507.04636","title":"Put Teacher in Student's Shoes: Cross-Distillation for Ultra-compact Model Compression Framework","created":"2025-07-07","cited_by_count":8,"area":null},{"id":"2512.04550","title":"AdmTree: Compressing Lengthy Context with Adaptive Semantic Trees","created":"2025-12-04","cited_by_count":8,"area":"inference"},{"id":"2205.04157","title":"Task-specific Compression for Multi-task Language Models using Attribution-based Pruning","created":"2022-05-09","cited_by_count":7,"area":null},{"id":"2503.24358","title":"SQuat: Subspace-orthogonal KV Cache Quantization","created":"2025-03-31","cited_by_count":7,"area":"inference"},{"id":"2512.09927","title":"Token Expand-Merge: Training-Free Token Compression for Vision-Language-Action Models","created":"2025-12-10","cited_by_count":7,"area":"vla"},{"id":"2110.04711","title":"SuperShaper: Task-Agnostic Super Pre-training of BERT Models with Variable Hidden Dimensions","created":"2021-10-10","cited_by_count":6,"area":null},{"id":"2305.11392","title":"Fast-StrucTexT: An Efficient Hourglass Transformer with Modality-guided Dynamic Token Merge for Document Understanding","created":"2023-05-19","cited_by_count":6,"area":null},{"id":"2306.14393","title":"Constraint-aware and Ranking-distilled Token Pruning for Efficient Transformer Inference","created":"2023-06-26","cited_by_count":6,"area":"inference"},{"id":"2304.01016","title":"Quick Dense Retrievers Consume KALE: Post Training Kullback Leibler Alignment of Embeddings for Asymmetrical dual encoders","created":"2023-03-31","cited_by_count":5,"area":null},{"id":"2403.14047","title":"Accelerating ViT Inference on FPGA through Static and Dynamic Pruning","created":"2024-03-21","cited_by_count":5,"area":"inference"},{"id":"2412.12496","title":"Faster Vision Mamba is Rebuilt in Minutes via Merged Token Re-training","created":"2024-12-17","cited_by_count":5,"area":"ssm"},{"id":"2504.04514","title":"Saliency-driven Dynamic Token Pruning for Large Language Models","created":"2025-04-06","cited_by_count":5,"area":"inference"},{"id":"2508.00367","title":"Representation Shift: Unifying Token Compression with FlashAttention","created":"2025-08-01","cited_by_count":5,"area":"inference"},{"id":"2406.07588","title":"AIM: Let Any Multi-modal Large Language Models Embrace Efficient In-Context Learning","created":"2024-06-11","cited_by_count":4,"area":"mllm"},{"id":"2409.10593","title":"CSKV: Training-Efficient Channel Shrinking for KV Cache in Long-Context Scenarios","created":"2024-09-16","cited_by_count":4,"area":"inference"},{"id":"2412.12147","title":"Meta-Controller: Few-Shot Imitation of Unseen Embodiments and Tasks in Continuous Control","created":"2024-12-10","cited_by_count":4,"area":null},{"id":"2412.13437","title":"Deploying Foundation Model Powered Agent Services: A Survey","created":"2024-12-18","cited_by_count":4,"area":"agents"},{"id":"2603.25340","title":"Large Language Model as Token Compressor and Decompressor","created":"2026-03-26","cited_by_count":4,"area":null},{"id":"2301.09262","title":"AttMEMO : Accelerating Transformers with Memoization on Big Memory Systems","created":"2023-01-23","cited_by_count":3,"area":null},{"id":"2305.08285","title":"Parameter-Efficient Fine-Tuning with Layer Pruning on Free-Text Sequence-to-Sequence Modeling","created":"2023-05-15","cited_by_count":3,"area":null},{"id":"2308.14909","title":"Pruning Self-Attention for Zero-Shot Multi-Speaker Text-to-Speech","created":"2023-08-28","cited_by_count":3,"area":null},{"id":"2312.05479","title":"Exploring Sparsity in Graph Transformers","created":"2023-12-09","cited_by_count":3,"area":null},{"id":"2401.06340","title":"A Temporal-Spectral Fusion Transformer with Subject-Specific Adapter for Enhancing RSVP-BCI Decoding","created":"2024-01-12","cited_by_count":3,"area":null},{"id":"2505.22195","title":"S2AFormer: Strip Self-Attention for Efficient Vision Transformer","created":"2025-05-28","cited_by_count":3,"area":null},{"id":"2509.09785","title":"Purge-Gate: Backpropagation-Free Test-Time Adaptation for Point Clouds Classification via Token Purging","created":"2025-09-11","cited_by_count":3,"area":null},{"id":"2511.07237","title":"The Few Govern the Many:Unveiling Few-Layer Dominance for Time Series Models","created":"2025-11-10","cited_by_count":3,"area":null},{"id":"2603.05663","title":"Keeping the Evidence Chain: Semantic Evidence Allocation for Training-Free Token Pruning in Video Temporal Grounding","created":"2026-03-05","cited_by_count":3,"area":"inference"},{"id":"2605.20551","title":"Faster or Stronger: Towards Flexible Visual Place Recognition via Weighted Aggregation and Token Pruning","created":"2026-05-19","cited_by_count":3,"area":null},{"id":"2204.03479","title":"Delta Keyword Transformer: Bringing Transformers to the Edge through Dynamically Pruned Multi-Head Self-Attention","created":"2022-03-20","cited_by_count":2,"area":null},{"id":"2305.12458","title":"Infor-Coef: Information Bottleneck-based Dynamic Token Downsampling for Compact and Efficient language model","created":"2023-05-21","cited_by_count":2,"area":null},{"id":"2311.02344","title":"You Only Forward Once: Prediction and Rationalization in A Single Forward Pass","created":"2023-11-04","cited_by_count":2,"area":null}],"next_cursor":"100"}