{"total":80,"rows":[{"id":"2401.18079","title":"KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization","created":"2024-01-31","cited_by_count":591,"area":"inference"},{"id":"2306.07629","title":"SqueezeLLM: Dense-and-Sparse Quantization","created":"2023-06-13","cited_by_count":294,"area":null},{"id":"2402.16363","title":"LLM Inference Unveiled: Survey and Roofline Model Insights","created":"2024-02-26","cited_by_count":152,"area":"inference"},{"id":"2312.15234","title":"Towards Efficient Generative Large Language Model Serving: A Survey from Algorithms to Systems","created":"2023-12-23","cited_by_count":102,"area":"inference"},{"id":"2310.04564","title":"ReLU Strikes Back: Exploiting Activation Sparsity in Large Language Models","created":"2023-10-06","cited_by_count":94,"area":null},{"id":"2403.14123","title":"AI and Memory Wall","created":"2024-03-21","cited_by_count":92,"area":null},{"id":"2305.13144","title":"Response Length Perception and Sequence Scheduling: An LLM-Empowered LLM Inference Pipeline","created":"2023-05-22","cited_by_count":86,"area":"inference"},{"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":"2310.07707","title":"MatFormer: Nested Transformer for Elastic Inference","created":"2023-10-11","cited_by_count":85,"area":null},{"id":"2402.15220","title":"ChunkAttention: Efficient Self-Attention with Prefix-Aware KV Cache and Two-Phase Partition","created":"2024-02-23","cited_by_count":82,"area":"inference"},{"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":"2312.04916","title":"EE-LLM: Large-Scale Training and Inference of Early-Exit Large Language Models with 3D Parallelism","created":"2023-12-08","cited_by_count":69,"area":"inference"},{"id":"2403.20306","title":"Towards Greener LLMs: Bringing Energy-Efficiency to the Forefront of LLM Inference","created":"2024-03-29","cited_by_count":61,"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":"2404.08763","title":"CATS: Contextually-Aware Thresholding for Sparsity in Large Language Models","created":"2024-04-12","cited_by_count":41,"area":null},{"id":"2307.05908","title":"Predictive Pipelined Decoding: A Compute-Latency Trade-off for Exact LLM Decoding","created":"2023-07-12","cited_by_count":40,"area":null},{"id":"2312.15159","title":"Understanding the Potential of FPGA-Based Spatial Acceleration for Large Language Model Inference","created":"2023-12-23","cited_by_count":33,"area":null},{"id":"2401.07872","title":"The What, Why, and How of Context Length Extension Techniques in Large Language Models -- A Detailed Survey","created":"2024-01-15","cited_by_count":33,"area":null},{"id":"2505.06371","title":"The ML.ENERGY Benchmark: Toward Automated Inference Energy Measurement and Optimization","created":"2025-05-09","cited_by_count":33,"area":null},{"id":"2502.10424","title":"QuantSpec: Self-Speculative Decoding with Hierarchical Quantized KV Cache","created":"2025-02-05","cited_by_count":27,"area":"inference"},{"id":"2511.15915","title":"AccelOpt: A Self-Improving LLM Agentic System for AI Accelerator Kernel Optimization","created":"2025-11-19","cited_by_count":23,"area":"agents"},{"id":"2409.02141","title":"Efficient and Scalable Estimation of Tool Representations in Vector Space","created":"2024-09-02","cited_by_count":22,"area":"agents"},{"id":"2306.15552","title":"A Survey on Deep Learning Hardware Accelerators for Heterogeneous HPC Platforms","created":"2023-06-27","cited_by_count":21,"area":null},{"id":"2405.10480","title":"Lean Attention: Hardware-Aware Scalable Attention Mechanism for the Decode-Phase of Transformers","created":"2024-05-17","cited_by_count":16,"area":null},{"id":"2408.08274","title":"BAM! Just Like That: Simple and Efficient Parameter Upcycling for Mixture of Experts","created":"2024-08-15","cited_by_count":16,"area":"moe"},{"id":"2502.13575","title":"ETS: Efficient Tree Search for Inference-Time Scaling","created":"2025-02-19","cited_by_count":16,"area":"lr"},{"id":"2309.04902","title":"Transformers in Small Object Detection: A Benchmark and Survey of State-of-the-Art","created":"2023-09-10","cited_by_count":15,"area":null},{"id":"2401.15347","title":"A Comprehensive Survey of Compression Algorithms for Language Models","created":"2024-01-27","cited_by_count":15,"area":null},{"id":"2312.08583","title":"ZeroQuant(4+2): Redefining LLMs Quantization with a New FP6-Centric Strategy for Diverse Generative Tasks","created":"2023-12-14","cited_by_count":14,"area":null},{"id":"2410.22391","title":"A Large Recurrent Action Model: xLSTM enables Fast Inference for Robotics Tasks","created":"2024-10-29","cited_by_count":14,"area":"deeprl"},{"id":"2405.00314","title":"Model Quantization and Hardware Acceleration for Vision Transformers: A Comprehensive Survey","created":"2024-05-01","cited_by_count":13,"area":null},{"id":"2510.04146","title":"Beyond Next-Token Prediction: A Performance Characterization of Diffusion versus Autoregressive Language Models","created":"2025-10-05","cited_by_count":13,"area":null},{"id":"2401.14112","title":"FP6-LLM: Efficiently Serving Large Language Models Through FP6-Centric Algorithm-System Co-Design","created":"2024-01-25","cited_by_count":12,"area":null},{"id":"2402.13485","title":"ProPD: Dynamic Token Tree Pruning and Generation for LLM Parallel Decoding","created":"2024-02-21","cited_by_count":12,"area":"inference"},{"id":"2406.01698","title":"Demystifying AI Platform Design for Distributed Inference of Next-Generation LLM models","created":"2024-06-03","cited_by_count":12,"area":"inference"},{"id":"2310.00576","title":"GrowLength: Accelerating LLMs Pretraining by Progressively Growing Training Length","created":"2023-10-01","cited_by_count":11,"area":null},{"id":"2510.10467","title":"AnyBCQ: Hardware Efficient Flexible Binary-Coded Quantization for Multi-Precision LLMs","created":"2025-10-12","cited_by_count":9,"area":null},{"id":"2502.12665","title":"A$^2$ATS: Retrieval-Based KV Cache Reduction via Windowed Rotary Position Embedding and Query-Aware Vector Quantization","created":"2025-02-18","cited_by_count":7,"area":"inference"},{"id":"2312.09084","title":"Language Modeling on a SpiNNaker 2 Neuromorphic Chip","created":"2023-12-14","cited_by_count":6,"area":null},{"id":"2312.10359","title":"Conformer-Based Speech Recognition On Extreme Edge-Computing Devices","created":"2023-12-16","cited_by_count":6,"area":null},{"id":"2412.04180","title":"SKIM: Any-bit Quantization Pushing The Limits of Post-Training Quantization","created":"2024-12-05","cited_by_count":6,"area":null},{"id":"2510.05688","title":"vAttention: Verified Sparse Attention","created":"2025-10-07","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":"2412.10059","title":"Panacea: Novel DNN Accelerator using Accuracy-Preserving Asymmetric Quantization and Energy-Saving Bit-Slice Sparsity","created":"2024-12-13","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":"2604.09048","title":"Watt Counts: Energy-Aware Benchmark for Sustainable LLM Inference on Heterogeneous GPU Architectures","created":"2026-04-10","cited_by_count":5,"area":"inference"},{"id":"2405.06626","title":"Characterizing the Accuracy -- Efficiency Trade-off of Low-rank Decomposition in Language Models","created":"2024-05-10","cited_by_count":4,"area":null},{"id":"2410.18952","title":"Dynamic Vocabulary Pruning in Early-Exit LLMs","created":"2024-10-24","cited_by_count":4,"area":"inference"},{"id":"2508.06041","title":"DP-LLM: Runtime Model Adaptation with Dynamic Layer-wise Precision Assignment","created":"2025-08-08","cited_by_count":4,"area":null},{"id":"2508.10395","title":"XQuant: Breaking the Memory Wall for LLM Inference with KV Cache Rematerialization","created":"2025-08-14","cited_by_count":4,"area":"inference"},{"id":"2404.11502","title":"Towards Coarse-to-Fine Evaluation of Inference Efficiency for Large Language Models","created":"2024-04-17","cited_by_count":3,"area":null},{"id":"2405.03882","title":"Trio-ViT: Post-Training Quantization and Acceleration for Softmax-Free Efficient Vision Transformer","created":"2024-05-06","cited_by_count":3,"area":null},{"id":"2407.14982","title":"GreenStableYolo: Optimizing Inference Time and Image Quality of Text-to-Image Generation","created":"2024-07-20","cited_by_count":3,"area":null},{"id":"2503.18216","title":"Adaptive Rank Allocation: Speeding Up Modern Transformers with RaNA Adapters","created":"2025-03-23","cited_by_count":3,"area":null},{"id":"2504.02118","title":"LLMPi: Optimizing LLMs for High-Throughput on Raspberry Pi","created":"2025-04-02","cited_by_count":3,"area":null},{"id":"2505.22842","title":"Bayesian Attention Mechanism: A Probabilistic Framework for Positional Encoding and Context Length Extrapolation","created":"2025-05-28","cited_by_count":3,"area":null},{"id":"2506.10205","title":"AWP: Activation-Aware Weight Pruning and Quantization with Projected Gradient Descent","created":"2025-06-11","cited_by_count":3,"area":null},{"id":"2506.22776","title":"Smaller = Weaker? Benchmarking Robustness of Quantized LLMs in Code Generation","created":"2025-06-28","cited_by_count":3,"area":null},{"id":"2408.03130","title":"Inference Optimizations for Large Language Models: Effects, Challenges, and Practical Considerations","created":"2024-08-06","cited_by_count":2,"area":null},{"id":"2408.11939","title":"Matmul or No Matmul in the Era of 1-bit LLMs","created":"2024-08-21","cited_by_count":2,"area":null},{"id":"2410.19456","title":"Computational Bottlenecks of Training Small-scale Large Language Models","created":"2024-10-25","cited_by_count":2,"area":null},{"id":"2503.12211","title":"Changing Base Without Losing Pace: A GPU-Efficient Alternative to MatMul in DNNs","created":"2025-03-15","cited_by_count":2,"area":null},{"id":"2602.09075","title":"Learning to Remember, Learn, and Forget in Attention-Based Models","created":"2026-02-09","cited_by_count":2,"area":null},{"id":"2312.13000","title":"Accelerator-driven Data Arrangement to Minimize Transformers Run-time on Multi-core Architectures","created":"2023-12-20","cited_by_count":1,"area":null},{"id":"2312.15896","title":"WWW: What, When, Where to Compute-in-Memory","created":"2023-12-26","cited_by_count":1,"area":null},{"id":"2410.18701","title":"BATON: Enhancing Batch-wise Inference Efficiency for Large Language Models via Dynamic Re-batching","created":"2024-10-24","cited_by_count":1,"area":null},{"id":"2411.03934","title":"Interactions Across Blocks in Post-Training Quantization of Large Language Models","created":"2024-11-06","cited_by_count":1,"area":null},{"id":"2504.01994","title":"PIM-LLM: A High-Throughput Hybrid PIM Architecture for 1-bit LLMs","created":"2025-03-31","cited_by_count":1,"area":null},{"id":"2505.03745","title":"AccLLM: Accelerating Long-Context LLM Inference Via Algorithm-Hardware Co-Design","created":"2025-04-07","cited_by_count":1,"area":null},{"id":"2509.25853","title":"SAIL: SRAM-Accelerated LLM Inference System with Lookup-Table-based GEMV","created":"2025-09-30","cited_by_count":1,"area":"inference"},{"id":"2510.24985","title":"FaRAccel: FPGA-Accelerated Defense Architecture for Efficient Bit-Flip Attack Resilience in Transformer Models","created":"2025-10-28","cited_by_count":1,"area":null},{"id":"2512.06457","title":"BitStopper: An Efficient Transformer Attention Accelerator via Stage-fusion and Early Termination","created":"2025-12-06","cited_by_count":1,"area":null},{"id":"2512.07855","title":"LAPA: Log-Domain Prediction-Driven Dynamic Sparsity Accelerator for Transformer Model","created":"2025-11-26","cited_by_count":1,"area":null},{"id":"2402.03435","title":"Psychological Assessments with Large Language Models: A Privacy-Focused and Cost-Effective Approach","created":"2024-02-05","cited_by_count":0,"area":null},{"id":"2412.04778","title":"IterL2Norm: Fast Iterative L2-Normalization","created":"2024-12-06","cited_by_count":0,"area":null},{"id":"2512.07312","title":"DCO: Dynamic Cache Orchestration for LLM Accelerators through Predictive Management","created":"2025-12-08","cited_by_count":0,"area":null},{"id":"2602.06252","title":"D-Legion: A Scalable Many-Core Architecture for Accelerating Matrix Multiplication in Quantized LLMs","created":"2026-02-05","cited_by_count":0,"area":null},{"id":"2602.08060","title":"Compiler-Assisted Speculative Sampling for Accelerated LLM Inference on Heterogeneous Edge Devices","created":"2026-02-08","cited_by_count":0,"area":"inference"},{"id":"2604.11512","title":"EdgeCIM: A Hardware-Software Co-Design for CIM-Based Acceleration of Small Language Models","created":"2026-04-13","cited_by_count":0,"area":null},{"id":"2608.21621","title":"FrugalSOT - Frugal Search Over the Models","created":"2026-08-21","cited_by_count":0,"area":null}],"next_cursor":null}