{"total":143,"rows":[{"id":"2309.17453","title":"Efficient Streaming Language Models with Attention Sinks","created":"2023-09-29","cited_by_count":2186,"area":null},{"id":"2211.10438","title":"SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models","created":"2022-11-18","cited_by_count":1386,"area":null},{"id":"2306.00978","title":"AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration","created":"2023-06-01","cited_by_count":1298,"area":null},{"id":"2407.02490","title":"MInference 1.0: Accelerating Pre-filling for Long-Context LLMs via Dynamic Sparse Attention","created":"2024-07-02","cited_by_count":383,"area":null},{"id":"2204.09656","title":"A Fast Post-Training Pruning Framework for Transformers","created":"2022-03-29","cited_by_count":162,"area":null},{"id":"2403.09636","title":"Dynamic Memory Compression: Retrofitting LLMs for Accelerated Inference","created":"2024-03-14","cited_by_count":116,"area":null},{"id":"2107.10845","title":"QuantumNAS: Noise-Adaptive Search for Robust Quantum Circuits","created":"2021-07-22","cited_by_count":98,"area":null},{"id":"2302.14017","title":"Full Stack Optimization of Transformer Inference: a Survey","created":"2023-02-27","cited_by_count":80,"area":null},{"id":"2203.10705","title":"Compression of Generative Pre-trained Language Models via Quantization","created":"2022-03-21","cited_by_count":79,"area":null},{"id":"2209.00099","title":"Efficient Methods for Natural Language Processing: A Survey","created":"2022-08-31","cited_by_count":78,"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":"2407.05858","title":"Fast On-device LLM Inference with NPUs","created":"2024-07-08","cited_by_count":62,"area":null},{"id":"2104.00769","title":"Keyword Transformer: A Self-Attention Model for Keyword Spotting","created":"2021-04-01","cited_by_count":60,"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":"2208.14286","title":"ANT: Exploiting Adaptive Numerical Data Type for Low-bit Deep Neural Network Quantization","created":"2022-08-30","cited_by_count":51,"area":null},{"id":"2209.10797","title":"DFX: A Low-latency Multi-FPGA Appliance for Accelerating Transformer-based Text Generation","created":"2022-09-22","cited_by_count":48,"area":null},{"id":"2403.17312","title":"ALISA: Accelerating Large Language Model Inference via Sparsity-Aware KV Caching","created":"2024-03-26","cited_by_count":48,"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":"2406.14909","title":"Mixture of Attention Spans: Optimizing LLM Inference Efficiency with Heterogeneous Sliding-Window Lengths","created":"2024-06-21","cited_by_count":44,"area":null},{"id":"2210.09573","title":"ViTCoD: Vision Transformer Acceleration via Dedicated Algorithm and Accelerator Co-Design","created":"2022-10-18","cited_by_count":41,"area":null},{"id":"2107.06419","title":"FLAT: An Optimized Dataflow for Mitigating Attention Bottlenecks","created":"2021-07-13","cited_by_count":39,"area":null},{"id":"2404.07236","title":"Lightweight Deep Learning for Resource-Constrained Environments: A Survey","created":"2024-04-08","cited_by_count":38,"area":null},{"id":"2307.07982","title":"A Survey of Techniques for Optimizing Transformer Inference","created":"2023-07-16","cited_by_count":35,"area":null},{"id":"2204.11786","title":"Enable Deep Learning on Mobile Devices: Methods, Systems, and Applications","created":"2022-04-25","cited_by_count":32,"area":null},{"id":"2209.09570","title":"Adaptable Butterfly Accelerator for Attention-based NNs via Hardware and Algorithm Co-design","created":"2022-09-20","cited_by_count":31,"area":null},{"id":"2302.03773","title":"What Matters In The Structured Pruning of Generative Language Models?","created":"2023-02-07","cited_by_count":30,"area":null},{"id":"2208.06118","title":"An Algorithm-Hardware Co-Optimized Framework for Accelerating N:M Sparse Transformers","created":"2022-08-12","cited_by_count":29,"area":null},{"id":"2211.05109","title":"ViTALiTy: Unifying Low-rank and Sparse Approximation for Vision Transformer Acceleration with a Linear Taylor Attention","created":"2022-11-09","cited_by_count":29,"area":null},{"id":"2406.12930","title":"Tender: Accelerating Large Language Models via Tensor Decomposition and Runtime Requantization","created":"2024-06-16","cited_by_count":28,"area":null},{"id":"2110.11331","title":"QuantumNAT: Quantum Noise-Aware Training with Noise Injection, Quantization and Normalization","created":"2021-10-21","cited_by_count":27,"area":null},{"id":"2110.09310","title":"Energon: Towards Efficient Acceleration of Transformers Using Dynamic Sparse Attention","created":"2021-10-18","cited_by_count":26,"area":null},{"id":"2303.04185","title":"Gradient-Free Structured Pruning with Unlabeled Data","created":"2023-03-07","cited_by_count":26,"area":null},{"id":"2112.02191","title":"NN-LUT: Neural Approximation of Non-Linear Operations for Efficient Transformer Inference","created":"2021-12-03","cited_by_count":25,"area":null},{"id":"2301.10936","title":"PIT: Optimization of Dynamic Sparse Deep Learning Models via Permutation Invariant Transformation","created":"2023-01-26","cited_by_count":25,"area":null},{"id":"2303.07470","title":"X-Former: In-Memory Acceleration of Transformers","created":"2023-03-13","cited_by_count":25,"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":"2308.14363","title":"Mobile Foundation Model as Firmware","created":"2023-08-28","cited_by_count":25,"area":null},{"id":"2205.07324","title":"Transkimmer: Transformer Learns to Layer-wise Skim","created":"2022-05-15","cited_by_count":24,"area":null},{"id":"2211.10801","title":"Peeling the Onion: Hierarchical Reduction of Data Redundancy for Efficient Vision Transformer Training","created":"2022-11-19","cited_by_count":24,"area":null},{"id":"2302.14705","title":"AccelTran: A Sparsity-Aware Accelerator for Dynamic Inference with Transformers","created":"2023-02-28","cited_by_count":24,"area":null},{"id":"2202.13239","title":"QOC: Quantum On-Chip Training with Parameter Shift and Gradient Pruning","created":"2022-02-26","cited_by_count":23,"area":null},{"id":"2410.07265","title":"A Survey: Collaborative Hardware and Software Design in the Era of Large Language Models","created":"2024-10-08","cited_by_count":23,"area":null},{"id":"2208.03646","title":"A Length Adaptive Algorithm-Hardware Co-design of Transformer on FPGA Through Sparse Attention and Dynamic Pipelining","created":"2022-08-07","cited_by_count":22,"area":null},{"id":"2504.20966","title":"Softpick: No Attention Sink, No Massive Activations with Rectified Softmax","created":"2025-04-29","cited_by_count":22,"area":null},{"id":"2305.10727","title":"Boost Vision Transformer with GPU-Friendly Sparsity and Quantization","created":"2023-05-18","cited_by_count":20,"area":null},{"id":"2108.12594","title":"Layer-wise Model Pruning based on Mutual Information","created":"2021-08-28","cited_by_count":19,"area":null},{"id":"2110.11299","title":"Transformer Acceleration with Dynamic Sparse Attention","created":"2021-10-21","cited_by_count":19,"area":null},{"id":"2203.08991","title":"AdapLeR: Speeding up Inference by Adaptive Length Reduction","created":"2022-03-16","cited_by_count":19,"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":"2305.12356","title":"Integer or Floating Point? New Outlooks for Low-Bit Quantization on Large Language Models","created":"2023-05-21","cited_by_count":19,"area":null},{"id":"2401.09890","title":"A Survey on Hardware Accelerators for Large Language Models","created":"2024-01-18","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":"2110.03252","title":"Layer-wise Pruning of Transformer Attention Heads for Efficient Language Modeling","created":"2021-10-07","cited_by_count":14,"area":null},{"id":"2203.00091","title":"Dynamic N:M Fine-grained Structured Sparse Attention Mechanism","created":"2022-02-28","cited_by_count":14,"area":null},{"id":"2312.03134","title":"A Hardware Evaluation Framework for Large Language Model Inference","created":"2023-12-05","cited_by_count":14,"area":null},{"id":"2402.10930","title":"ConSmax: Hardware-Friendly Alternative Softmax with Learnable Parameters","created":"2024-01-31","cited_by_count":14,"area":null},{"id":"2201.00043","title":"Multi-Dimensional Model Compression of Vision Transformer","created":"2021-12-31","cited_by_count":13,"area":null},{"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":"2307.03493","title":"ITA: An Energy-Efficient Attention and Softmax Accelerator for Quantized Transformers","created":"2023-07-07","cited_by_count":12,"area":null},{"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":"2511.06767","title":"QUARK: Quantization-Enabled Circuit Sharing for Transformer Acceleration by Exploiting Common Patterns in Nonlinear Operations","created":"2025-11-10","cited_by_count":11,"area":null},{"id":"2206.14550","title":"SALO: An Efficient Spatial Accelerator Enabling Hybrid Sparse Attention Mechanisms for Long Sequences","created":"2022-06-29","cited_by_count":10,"area":null},{"id":"2311.16082","title":"Transformer-QEC: Quantum Error Correction Code Decoding with Transferable Transformers","created":"2023-11-27","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":"2204.03227","title":"Accelerating Attention through Gradient-Based Learned Runtime Pruning","created":"2022-04-07","cited_by_count":8,"area":null},{"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":"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":"2105.14636","title":"LEAP: Learnable Pruning for Transformer-based Models","created":"2021-05-30","cited_by_count":7,"area":null},{"id":"2502.02790","title":"Leveraging the true depth of LLMs","created":"2025-02-05","cited_by_count":7,"area":null},{"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":"2310.11096","title":"Sparse-DySta: Sparsity-Aware Dynamic and Static Scheduling for Sparse Multi-DNN Workloads","created":"2023-10-17","cited_by_count":6,"area":null},{"id":"2505.14884","title":"Polar Sparsity: High Throughput Batched LLM Inferencing with Scalable Contextual Sparsity","created":"2025-05-20","cited_by_count":6,"area":null},{"id":"2404.03353","title":"Towards Pareto Optimal Throughput in Small Language Model Serving","created":"2024-04-04","cited_by_count":5,"area":null},{"id":"2407.14106","title":"TorchGT: A Holistic System for Large-scale Graph Transformer Training","created":"2024-07-19","cited_by_count":5,"area":null},{"id":"2505.10909","title":"Phi: Leveraging Pattern-based Hierarchical Sparsity for High-Efficiency Spiking Neural Networks","created":"2025-05-16","cited_by_count":5,"area":null},{"id":"2506.14107","title":"D\\'ej\\`a Vu: Efficient Video-Language Query Engine with Learning-based Inter-Frame Computation Reuse","created":"2025-06-17","cited_by_count":5,"area":null},{"id":"2508.12969","title":"Compact Attention: Exploiting Structured Spatio-Temporal Sparsity for Fast Video Generation","created":"2025-08-18","cited_by_count":5,"area":null},{"id":"2510.17189","title":"SOLE: Hardware-Software Co-design of Softmax and LayerNorm for Efficient Transformer Inference","created":"2025-10-20","cited_by_count":5,"area":null},{"id":"2404.09336","title":"Self-Selected Attention Span for Accelerating Large Language Model Inference","created":"2024-04-14","cited_by_count":4,"area":null},{"id":"2404.11788","title":"Understanding the Performance Horizon of the Latest ML Workloads with NonGEMM Workloads","created":"2024-04-17","cited_by_count":4,"area":null},{"id":"2411.17847","title":"SoftmAP: Software-Hardware Co-design for Integer-Only Softmax on Associative Processors","created":"2024-11-26","cited_by_count":4,"area":null},{"id":"2508.16703","title":"ShadowNPU: System and Algorithm Co-design for NPU-Centric On-Device LLM Inference","created":"2025-08-22","cited_by_count":4,"area":null},{"id":"2206.11062","title":"Answer Fast: Accelerating BERT on the Tensor Streaming Processor","created":"2022-06-22","cited_by_count":3,"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":"2302.09221","title":"Moby: Empowering 2D Models for Efficient Point Cloud Analytics on the Edge","created":"2023-02-18","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":"2407.15131","title":"Token-Picker: Accelerating Attention in Text Generation with Minimized Memory Transfer via Probability Estimation","created":"2024-07-21","cited_by_count":3,"area":null},{"id":"2407.19014","title":"Sparse Refinement for Efficient High-Resolution Semantic Segmentation","created":"2024-07-26","cited_by_count":3,"area":null},{"id":"2409.03384","title":"Hardware Acceleration of LLMs: A comprehensive survey and comparison","created":"2024-09-05","cited_by_count":3,"area":null},{"id":"2409.15342","title":"Recall: Empowering Multimodal Embedding for Edge Devices","created":"2024-09-09","cited_by_count":3,"area":null},{"id":"2602.01194","title":"EMFormer: Efficient Multi-Scale Transformer for Accumulative Context Weather Forecasting","created":"2026-02-01","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":"2210.03731","title":"Demystifying Map Space Exploration for NPUs","created":"2022-10-07","cited_by_count":2,"area":null},{"id":"2303.13745","title":"EdgeTran: Co-designing Transformers for Efficient Inference on Mobile Edge Platforms","created":"2023-03-24","cited_by_count":2,"area":null},{"id":"2306.09552","title":"Retrospective: EIE: Efficient Inference Engine on Sparse and Compressed Neural Network","created":"2023-06-15","cited_by_count":2,"area":null},{"id":"2407.12893","title":"Hybrid Dynamic Pruning: A Pathway to Efficient Transformer Inference","created":"2024-07-17","cited_by_count":2,"area":null},{"id":"2408.12742","title":"TReX- Reusing Vision Transformer's Attention for Efficient Xbar-based Computing","created":"2024-08-22","cited_by_count":2,"area":null},{"id":"2412.19842","title":"Multimodal joint prediction of traffic spatial-temporal data with graph sparse attention mechanism and bidirectional temporal convolutional network","created":"2024-12-24","cited_by_count":2,"area":null}],"next_cursor":"100"}