{"total":164,"rows":[{"id":"2210.09461","title":"Token Merging: Your ViT But Faster","created":"2022-10-17","cited_by_count":1021,"area":"inference"},{"id":"2302.01318","title":"Accelerating Large Language Model Decoding with Speculative Sampling","created":"2023-02-02","cited_by_count":1006,"area":"inference"},{"id":"2410.10781","title":"When Attention Sink Emerges in Language Models: An Empirical View","created":"2024-10-14","cited_by_count":208,"area":"inference"},{"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":"2112.13890","title":"SPViT: Enabling Faster Vision Transformers via Soft Token Pruning","created":"2021-12-27","cited_by_count":167,"area":"inference"},{"id":"2403.09054","title":"Keyformer: KV Cache Reduction through Key Tokens Selection for Efficient Generative Inference","created":"2024-03-14","cited_by_count":126,"area":"inference"},{"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":"2509.02560","title":"FastVGGT: Training-Free Acceleration of Visual Geometry Transformer","created":"2025-09-02","cited_by_count":98,"area":"inference"},{"id":"2407.12820","title":"PQCache: Product Quantization-based KVCache for Long Context LLM Inference","created":"2024-07-01","cited_by_count":95,"area":"inference"},{"id":"2304.10716","title":"Joint Token Pruning and Squeezing Towards More Aggressive Compression of Vision Transformers","created":"2023-04-21","cited_by_count":81,"area":"inference"},{"id":"2305.17997","title":"DiffRate : Differentiable Compression Rate for Efficient Vision Transformers","created":"2023-05-29","cited_by_count":77,"area":"inference"},{"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":"2308.01045","title":"Dynamic Token Pruning in Plain Vision Transformers for Semantic Segmentation","created":"2023-08-02","cited_by_count":62,"area":"inference"},{"id":"2308.04657","title":"Which Tokens to Use? Investigating Token Reduction in Vision Transformers","created":"2023-08-09","cited_by_count":60,"area":"inference"},{"id":"2403.02991","title":"MADTP: Multimodal Alignment-Guided Dynamic Token Pruning for Accelerating Vision-Language Transformer","created":"2024-03-05","cited_by_count":54,"area":"inference"},{"id":"2306.07050","title":"Revisiting Token Pruning for Object Detection and Instance Segmentation","created":"2023-06-12","cited_by_count":50,"area":"inference"},{"id":"2502.17363","title":"KV-Edit: Training-Free Image Editing for Precise Background Preservation","created":"2025-02-24","cited_by_count":49,"area":"inference"},{"id":"2211.08110","title":"HeatViT: Hardware-Efficient Adaptive Token Pruning for Vision Transformers","created":"2022-11-15","cited_by_count":46,"area":"inference"},{"id":"2402.13516","title":"ProSparse: Introducing and Enhancing Intrinsic Activation Sparsity within Large Language Models","created":"2024-02-21","cited_by_count":45,"area":"inference"},{"id":"2209.08310","title":"Learning to Weight Samples for Dynamic Early-exiting Networks","created":"2022-09-17","cited_by_count":44,"area":"inference"},{"id":"2409.01156","title":"TempMe: Video Temporal Token Merging for Efficient Text-Video Retrieval","created":"2024-09-02","cited_by_count":40,"area":"inference"},{"id":"2310.01812","title":"PPT: Token Pruning and Pooling for Efficient Vision Transformers","created":"2023-10-03","cited_by_count":38,"area":"inference"},{"id":"2512.00891","title":"Accelerating Streaming Video Large Language Models via Hierarchical Token Compression","created":"2025-11-30","cited_by_count":37,"area":"inference"},{"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":"2405.16148","title":"Accelerating Transformers with Spectrum-Preserving Token Merging","created":"2024-05-25","cited_by_count":35,"area":"inference"},{"id":"2308.00255","title":"LGViT: Dynamic Early Exiting for Accelerating Vision Transformer","created":"2023-08-01","cited_by_count":31,"area":"inference"},{"id":"2411.00841","title":"A Theoretical Perspective for Speculative Decoding Algorithm","created":"2024-10-30","cited_by_count":29,"area":"inference"},{"id":"2505.09999","title":"ServeGen: Workload Characterization and Generation of Large Language Model Serving in Production","created":"2025-05-15","cited_by_count":29,"area":"inference"},{"id":"2106.15183","title":"Multi-Exit Vision Transformer for Dynamic Inference","created":"2021-06-29","cited_by_count":28,"area":"inference"},{"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":"2409.18962","title":"Exploring Token Pruning in Vision State Space Models","created":"2024-09-27","cited_by_count":28,"area":"inference"},{"id":"2410.17897","title":"Value Residual Learning","created":"2024-10-23","cited_by_count":27,"area":"inference"},{"id":"2105.09121","title":"Single-Layer Vision Transformers for More Accurate Early Exits with Less Overhead","created":"2021-05-19","cited_by_count":26,"area":"inference"},{"id":"2511.07278","title":"StreamKV: Streaming Video Question-Answering with Segment-based KV Cache Retrieval and Compression","created":"2025-11-10","cited_by_count":26,"area":"inference"},{"id":"2410.23782","title":"Video Token Merging for Long-form Video Understanding","created":"2024-10-31","cited_by_count":23,"area":"inference"},{"id":"2307.10780","title":"Learned Thresholds Token Merging and Pruning for Vision Transformers","created":"2023-07-20","cited_by_count":21,"area":"inference"},{"id":"2412.10569","title":"Learning to Merge Tokens via Decoupled Embedding for Efficient Vision Transformers","created":"2024-12-13","cited_by_count":21,"area":"inference"},{"id":"2503.10568","title":"Autoregressive Image Generation with Randomized Parallel Decoding","created":"2025-03-13","cited_by_count":20,"area":"inference"},{"id":"2311.03035","title":"GTP-ViT: Efficient Vision Transformers via Graph-based Token Propagation","created":"2023-11-06","cited_by_count":19,"area":"inference"},{"id":"2412.00965","title":"Token Cropr: Faster ViTs for Quite a Few Tasks","created":"2024-12-01","cited_by_count":19,"area":"inference"},{"id":"2602.08024","title":"FlashVID: Efficient Video Large Language Models via Training-free Tree-based Spatiotemporal Token Merging","created":"2026-02-08","cited_by_count":18,"area":"inference"},{"id":"2512.04939","title":"LiteVGGT: Boosting Vanilla VGGT via Geometry-aware Cached Token Merging","created":"2025-12-04","cited_by_count":17,"area":"inference"},{"id":"2403.01136","title":"LLM-PQ: Serving LLM on Heterogeneous Clusters with Phase-Aware Partition and Adaptive Quantization","created":"2024-03-02","cited_by_count":15,"area":"inference"},{"id":"2409.17372","title":"Search for Efficient Large Language Models","created":"2024-09-25","cited_by_count":14,"area":"inference"},{"id":"2505.21233","title":"CROP: Contextual Region-Oriented Visual Token Pruning","created":"2025-05-27","cited_by_count":14,"area":"inference"},{"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":"2504.00999","title":"MergeVQ: A Unified Framework for Visual Generation and Representation with Disentangled Token Merging and Quantization","created":"2025-04-01","cited_by_count":12,"area":"inference"},{"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":"2409.08464","title":"VLTP: Vision-Language Guided Token Pruning for Task-Oriented Segmentation","created":"2024-09-13","cited_by_count":11,"area":"inference"},{"id":"2506.20066","title":"ToSA: Token Merging with Spatial Awareness","created":"2025-06-24","cited_by_count":11,"area":"inference"},{"id":"2507.01438","title":"EdgeLoRA: An Efficient Multi-Tenant LLM Serving System on Edge Devices","created":"2025-07-02","cited_by_count":11,"area":"inference"},{"id":"2309.15755","title":"CAIT: Triple-Win Compression towards High Accuracy, Fast Inference, and Favorable Transferability For ViTs","created":"2023-09-27","cited_by_count":9,"area":"inference"},{"id":"2405.14467","title":"Segformer++: Efficient Token-Merging Strategies for High-Resolution Semantic Segmentation","created":"2024-05-23","cited_by_count":9,"area":"inference"},{"id":"2406.07368","title":"When Linear Attention Meets Autoregressive Decoding: Towards More Effective and Efficient Linearized Large Language Models","created":"2024-06-11","cited_by_count":9,"area":"inference"},{"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":"2409.00633","title":"Make Your ViT-based Multi-view 3D Detectors Faster via Token Compression","created":"2024-09-01","cited_by_count":9,"area":"inference"},{"id":"2409.14364","title":"Position IDs Matter: An Enhanced Position Layout for Efficient Context Compression in Large Language Models","created":"2024-09-22","cited_by_count":9,"area":"inference"},{"id":"2506.05709","title":"Token Transforming: A Unified and Training-Free Token Compression Framework for Vision Transformer Acceleration","created":"2025-06-06","cited_by_count":9,"area":"inference"},{"id":"2506.11418","title":"CentroidKV: Efficient Long-Context LLM Inference via KV Cache Clustering","created":"2025-06-13","cited_by_count":8,"area":"inference"},{"id":"2311.08623","title":"DEED: Dynamic Early Exit on Decoder for Accelerating Encoder-Decoder Transformer Models","created":"2023-11-15","cited_by_count":7,"area":"inference"},{"id":"2405.17951","title":"Efficient Time Series Processing for Transformers and State-Space Models through Token Merging","created":"2024-05-28","cited_by_count":7,"area":"inference"},{"id":"2407.15219","title":"Efficient Visual Transformer by Learnable Token Merging","created":"2024-07-21","cited_by_count":7,"area":"inference"},{"id":"2502.10659","title":"Pushing up to the Limit of Memory Bandwidth and Capacity Utilization for Efficient LLM Decoding on Embedded FPGA","created":"2025-02-15","cited_by_count":7,"area":"inference"},{"id":"2408.06798","title":"Token Compensator: Altering Inference Cost of Vision Transformer without Re-Tuning","created":"2024-08-13","cited_by_count":6,"area":"inference"},{"id":"2412.09919","title":"B-VLLM: A Vision Large Language Model with Balanced Spatio-Temporal Tokens","created":"2024-12-13","cited_by_count":6,"area":"inference"},{"id":"2511.05534","title":"FlowMM: Cross-Modal Information Flow Guided KV Cache Merging for Efficient Multimodal Context Inference","created":"2025-10-29","cited_by_count":6,"area":"inference"},{"id":"2210.15621","title":"Class Based Thresholding in Early Exit Semantic Segmentation Networks","created":"2022-10-27","cited_by_count":5,"area":"inference"},{"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":"2406.07676","title":"FastAST: Accelerating Audio Spectrogram Transformer via Token Merging and Cross-Model Knowledge Distillation","created":"2024-06-11","cited_by_count":5,"area":"inference"},{"id":"2411.16158","title":"MixPE: Quantization and Hardware Co-design for Efficient LLM Inference","created":"2024-11-25","cited_by_count":5,"area":"inference"},{"id":"2502.15955","title":"Compression Barriers for Autoregressive Transformers","created":"2025-02-21","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":"2603.01400","title":"Token Reduction via Local and Global Contexts Optimization for Efficient Video Large Language Models","created":"2026-03-02","cited_by_count":5,"area":"inference"},{"id":"2303.06522","title":"Token Sparsification for Faster Medical Image Segmentation","created":"2023-03-11","cited_by_count":4,"area":"inference"},{"id":"2403.17726","title":"Tiny Models are the Computational Saver for Large Models","created":"2024-03-26","cited_by_count":4,"area":"inference"},{"id":"2408.10497","title":"QUITO-X: A New Perspective on Context Compression from the Information Bottleneck Theory","created":"2024-08-20","cited_by_count":4,"area":"inference"},{"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":"2412.19325","title":"Performance Control in Early Exiting to Deploy Large Models at the Same Cost of Smaller Ones","created":"2024-12-26","cited_by_count":4,"area":"inference"},{"id":"2502.06474","title":"UniMoD: Efficient Unified Multimodal Transformers with Mixture-of-Depths","created":"2025-02-10","cited_by_count":4,"area":"inference"},{"id":"2503.20282","title":"Faster Parameter-Efficient Tuning with Token Redundancy Reduction","created":"2025-03-26","cited_by_count":4,"area":"inference"},{"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":"2506.03762","title":"AhaKV: Adaptive Holistic Attention-Driven KV Cache Eviction for Efficient Inference of Large Language Models","created":"2025-06-04","cited_by_count":4,"area":"inference"},{"id":"2510.16807","title":"Improving Model Representation and Reducing KV Cache via Skip Connections with First Value Heads","created":"2025-10-19","cited_by_count":4,"area":"inference"},{"id":"2512.23858","title":"Yggdrasil: Bridging Dynamic Speculation and Static Runtime for Latency-Optimal Tree-Based LLM Decoding","created":"2025-12-29","cited_by_count":4,"area":"inference"},{"id":"2603.00527","title":"TP-Spikformer: Token Pruned Spiking Transformer","created":"2026-02-28","cited_by_count":4,"area":"inference"},{"id":"2606.09659","title":"End-to-End Context Compression at Scale","created":"2026-06-08","cited_by_count":4,"area":"inference"},{"id":"2303.02331","title":"Training-Free Acceleration of ViTs with Delayed Spatial Merging","created":"2023-03-04","cited_by_count":3,"area":"inference"},{"id":"2410.09324","title":"Token Pruning using a Lightweight Background Aware Vision Transformer","created":"2024-10-12","cited_by_count":3,"area":"inference"},{"id":"2503.17497","title":"You Only Look Once at Anytime (AnytimeYOLO): Analysis and Optimization of Early-Exits for Object-Detection","created":"2025-03-21","cited_by_count":3,"area":"inference"},{"id":"2503.23459","title":"Reinforcement Learning-based Token Pruning in Vision Transformers: A Markov Game Approach","created":"2025-03-30","cited_by_count":3,"area":"inference"},{"id":"2505.15160","title":"Lossless Token Merging Even Without Fine-Tuning in Vision Transformers","created":"2025-05-21","cited_by_count":3,"area":"inference"},{"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":"2511.21477","title":"Frequency-Aware Token Reduction for Efficient Vision Transformer","created":"2025-11-26","cited_by_count":3,"area":"inference"},{"id":"2512.14661","title":"Focus: A Streaming Concentration Architecture for Efficient Vision-Language Models","created":"2025-12-16","cited_by_count":3,"area":"inference"},{"id":"2512.20120","title":"HEART-VIT: Hessian-Guided Efficient Dynamic Attention and Token Pruning in Vision Transformer","created":"2025-12-23","cited_by_count":3,"area":"inference"},{"id":"2512.21333","title":"Fast SAM2 with Text-Driven Token Pruning","created":"2025-12-24","cited_by_count":3,"area":"inference"},{"id":"2601.08273","title":"HIPPO: Accelerating Video Large Language Models Inference via Holistic-aware Parallel Speculative Decoding","created":"2026-01-13","cited_by_count":3,"area":"inference"},{"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":"2605.11605","title":"Keep What Audio Cannot Say: Context-Preserving Token Pruning for Omni-LLMs","created":"2026-05-12","cited_by_count":3,"area":"inference"},{"id":"2306.12185","title":"Adaptive DNN Surgery for Selfish Inference Acceleration with On-demand Edge Resource","created":"2023-06-21","cited_by_count":2,"area":"inference"}],"next_cursor":"100"}