{"total":109,"rows":[{"id":"2102.05426","title":"BRECQ: Pushing the Limit of Post-Training Quantization by Block Reconstruction","created":"2021-02-10","cited_by_count":479,"area":null},{"id":"2304.07493","title":"OliVe: Accelerating Large Language Models via Hardware-friendly Outlier-Victim Pair Quantization","created":"2023-04-15","cited_by_count":92,"area":null},{"id":"2110.06554","title":"Towards Mixed-Precision Quantization of Neural Networks via Constrained Optimization","created":"2021-10-13","cited_by_count":61,"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":"2111.03759","title":"MQBench: Towards Reproducible and Deployable Model Quantization Benchmark","created":"2021-11-05","cited_by_count":40,"area":null},{"id":"2102.10462","title":"BSQ: Exploring Bit-Level Sparsity for Mixed-Precision Neural Network Quantization","created":"2021-02-20","cited_by_count":39,"area":null},{"id":"2203.08737","title":"Hardware Approximate Techniques for Deep Neural Network Accelerators: A Survey","created":"2022-03-16","cited_by_count":39,"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":"2206.04459","title":"SDQ: Stochastic Differentiable Quantization with Mixed Precision","created":"2022-06-09","cited_by_count":28,"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":"2411.05282","title":"MicroScopiQ: Accelerating Foundational Models through Outlier-Aware Microscaling Quantization","created":"2024-11-08","cited_by_count":28,"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":"2103.02800","title":"Hardware Acceleration of Fully Quantized BERT for Efficient Natural Language Processing","created":"2021-03-04","cited_by_count":22,"area":null},{"id":"2209.09004","title":"EcoFormer: Energy-Saving Attention with Linear Complexity","created":"2022-09-19","cited_by_count":21,"area":null},{"id":"2203.17008","title":"It's All In the Teacher: Zero-Shot Quantization Brought Closer to the Teacher","created":"2022-03-31","cited_by_count":20,"area":null},{"id":"2110.11299","title":"Transformer Acceleration with Dynamic Sparse Attention","created":"2021-10-21","cited_by_count":19,"area":null},{"id":"2501.11211","title":"Ditto: Accelerating Diffusion Model via Temporal Value Similarity","created":"2025-01-20","cited_by_count":18,"area":"diffusion"},{"id":"2307.00331","title":"Quantization Variation: A New Perspective on Training Transformers with Low-Bit Precision","created":"2023-07-01","cited_by_count":17,"area":null},{"id":"2502.18755","title":"M-ANT: Efficient Low-bit Group Quantization for LLMs via Mathematically Adaptive Numerical Type","created":"2025-02-26","cited_by_count":16,"area":null},{"id":"2103.15750","title":"Enabling Design Methodologies and Future Trends for Edge AI: Specialization and Co-design","created":"2021-03-25","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":"2301.12195","title":"BAFFLE: A Baseline of Backpropagation-Free Federated Learning","created":"2023-01-28","cited_by_count":12,"area":null},{"id":"2309.08186","title":"A Precision-Scalable RISC-V DNN Processor with On-Device Learning Capability at the Extreme Edge","created":"2023-09-15","cited_by_count":11,"area":null},{"id":"2203.06673","title":"FlexBlock: A Flexible DNN Training Accelerator with Multi-Mode Block Floating Point Support","created":"2022-03-13","cited_by_count":10,"area":null},{"id":"2112.15131","title":"Resource-Efficient Deep Learning: A Survey on Model-, Arithmetic-, and Implementation-Level Techniques","created":"2021-12-30","cited_by_count":9,"area":null},{"id":"2411.15982","title":"Anda: Unlocking Efficient LLM Inference with a Variable-Length Grouped Activation Data Format","created":"2024-11-24","cited_by_count":9,"area":"inference"},{"id":"2204.03227","title":"Accelerating Attention through Gradient-Based Learned Runtime Pruning","created":"2022-04-07","cited_by_count":8,"area":null},{"id":"2304.10618","title":"ULEEN: A Novel Architecture for Ultra Low-Energy Edge Neural Networks","created":"2023-04-20","cited_by_count":8,"area":null},{"id":"2403.14353","title":"DaCapo: Accelerating Continuous Learning in Autonomous Systems for Video Analytics","created":"2024-03-21","cited_by_count":8,"area":null},{"id":"2208.06064","title":"Mixed-Precision Neural Networks: A Survey","created":"2022-08-11","cited_by_count":7,"area":null},{"id":"2311.06798","title":"MetaMix: Meta-state Precision Searcher for Mixed-precision Activation Quantization","created":"2023-11-12","cited_by_count":7,"area":null},{"id":"2403.05465","title":"Algorithm-Hardware Co-Design of Distribution-Aware Logarithmic-Posit Encodings for Efficient DNN Inference","created":"2024-03-08","cited_by_count":7,"area":null},{"id":"2403.18587","title":"The Impact of Uniform Inputs on Activation Sparsity and Energy-Latency Attacks in Computer Vision","created":"2024-03-27","cited_by_count":7,"area":null},{"id":"2101.04935","title":"Single-path Bit Sharing for Automatic Loss-aware Model Compression","created":"2021-01-13","cited_by_count":6,"area":null},{"id":"2103.02904","title":"Effective and Fast: A Novel Sequential Single Path Search for Mixed-Precision Quantization","created":"2021-03-04","cited_by_count":6,"area":null},{"id":"2104.08323","title":"Random and Adversarial Bit Error Robustness: Energy-Efficient and Secure DNN Accelerators","created":"2021-04-16","cited_by_count":6,"area":null},{"id":"2112.13972","title":"HiKonv: High Throughput Quantized Convolution With Novel Bit-wise Management and Computation","created":"2021-12-28","cited_by_count":6,"area":null},{"id":"2301.00290","title":"BARVINN: Arbitrary Precision DNN Accelerator Controlled by a RISC-V CPU","created":"2022-12-31","cited_by_count":6,"area":null},{"id":"2509.13765","title":"TENET: An Efficient Sparsity-Aware LUT-Centric Architecture for Ternary LLM Inference On Edge","created":"2025-09-17","cited_by_count":6,"area":null},{"id":"2109.05223","title":"2-in-1 Accelerator: Enabling Random Precision Switch for Winning Both Adversarial Robustness and Efficiency","created":"2021-09-11","cited_by_count":5,"area":null},{"id":"2201.12861","title":"Neural-PIM: Efficient Processing-In-Memory with Neural Approximation of Peripherals","created":"2022-01-30","cited_by_count":5,"area":null},{"id":"2203.11540","title":"Scale-out Systolic Arrays","created":"2022-03-22","cited_by_count":5,"area":null},{"id":"2311.02758","title":"M4BRAM: Mixed-Precision Matrix-Matrix Multiplication in FPGA Block RAMs","created":"2023-11-05","cited_by_count":5,"area":null},{"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":"2411.18065","title":"FlexiBit: Fully Flexible Precision Bit-parallel Accelerator Architecture for Arbitrary Mixed Precision AI","created":"2024-11-27","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":"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":"2510.16805","title":"Mixed-Precision Quantization for Language Models: Techniques and Prospects","created":"2025-10-19","cited_by_count":5,"area":null},{"id":"2101.11748","title":"Rethinking Floating Point Overheads for Mixed Precision DNN Accelerators","created":"2021-01-27","cited_by_count":4,"area":null},{"id":"2103.05363","title":"MWQ: Multiscale Wavelet Quantized Neural Networks","created":"2021-03-09","cited_by_count":4,"area":null},{"id":"2311.09775","title":"MEGA: A Memory-Efficient GNN Accelerator Exploiting Degree-Aware Mixed-Precision Quantization","created":"2023-11-16","cited_by_count":4,"area":null},{"id":"2509.10372","title":"MCBP: A Memory-Compute Efficient LLM Inference Accelerator Leveraging Bit-Slice-enabled Sparsity and Repetitiveness","created":"2025-09-12","cited_by_count":4,"area":"inference"},{"id":"2105.10554","title":"GNNIE: GNN Inference Engine with Load-balancing and Graph-Specific Caching","created":"2021-05-21","cited_by_count":3,"area":null},{"id":"2201.11651","title":"Bit-serial Weight Pools: Compression and Arbitrary Precision Execution of Neural Networks on Resource Constrained Processors","created":"2022-01-25","cited_by_count":3,"area":null},{"id":"2205.15437","title":"AMED: Automatic Mixed-Precision Quantization for Edge Devices","created":"2022-05-30","cited_by_count":3,"area":null},{"id":"2208.00338","title":"Symmetry Regularization and Saturating Nonlinearity for Robust Quantization","created":"2022-07-31","cited_by_count":3,"area":null},{"id":"2208.04854","title":"Design of High-Throughput Mixed-Precision CNN Accelerators on FPGA","created":"2022-08-09","cited_by_count":3,"area":null},{"id":"2402.06357","title":"The SkipSponge Attack: Sponge Weight Poisoning of Deep Neural Networks","created":"2024-02-09","cited_by_count":3,"area":null},{"id":"2408.02412","title":"PENDRAM: Enabling High-Performance and Energy-Efficient Processing of Deep Neural Networks through a Generalized DRAM Data Mapping Policy","created":"2024-08-05","cited_by_count":3,"area":null},{"id":"2409.05227","title":"BBS: Bi-directional Bit-level Sparsity for Deep Learning Acceleration","created":"2024-09-08","cited_by_count":3,"area":null},{"id":"2411.01417","title":"BF-IMNA: A Bit Fluid In-Memory Neural Architecture for Neural Network Acceleration","created":"2024-11-03","cited_by_count":3,"area":null},{"id":"2506.11431","title":"TruncQuant: Truncation-Ready Quantization for DNNs with Flexible Weight Bit Precision","created":"2025-06-13","cited_by_count":3,"area":null},{"id":"2106.15021","title":"How to Reach Real-Time AI on Consumer Devices? Solutions for Programmable and Custom Architectures","created":"2021-06-21","cited_by_count":2,"area":null},{"id":"2203.07713","title":"LDP: Learnable Dynamic Precision for Efficient Deep Neural Network Training and Inference","created":"2022-03-15","cited_by_count":2,"area":null},{"id":"2203.12091","title":"FxP-QNet: A Post-Training Quantizer for the Design of Mixed Low-Precision DNNs with Dynamic Fixed-Point Representation","created":"2022-03-22","cited_by_count":2,"area":null},{"id":"2208.01944","title":"PalQuant: Accelerating High-precision Networks on Low-precision Accelerators","created":"2022-08-03","cited_by_count":2,"area":null},{"id":"2302.05996","title":"Quark: An Integer RISC-V Vector Processor for Sub-Byte Quantized DNN Inference","created":"2023-02-12","cited_by_count":2,"area":null},{"id":"2302.12510","title":"DyBit: Dynamic Bit-Precision Numbers for Efficient Quantized Neural Network Inference","created":"2023-02-24","cited_by_count":2,"area":null},{"id":"2306.07215","title":"Efficient and Robust Quantization-aware Training via Adaptive Coreset Selection","created":"2023-06-12","cited_by_count":2,"area":null},{"id":"2412.03101","title":"Mixed-Precision Quantization: Make the Best Use of Bits Where They Matter Most","created":"2024-12-04","cited_by_count":2,"area":null},{"id":"2506.23717","title":"Towards Efficient and Accurate Spiking Neural Networks via Adaptive Bit Allocation","created":"2025-06-30","cited_by_count":2,"area":null},{"id":"2508.09500","title":"MiCo: End-to-End Mixed Precision Neural Network Co-Exploration Framework for Edge AI","created":"2025-08-13","cited_by_count":2,"area":null},{"id":"2103.01308","title":"SWIS -- Shared Weight bIt Sparsity for Efficient Neural Network Acceleration","created":"2021-03-01","cited_by_count":1,"area":null},{"id":"2103.14493","title":"RCT: Resource Constrained Training for Edge AI","created":"2021-03-26","cited_by_count":1,"area":null},{"id":"2110.07331","title":"Plug-Tagger: A Pluggable Sequence Labeling Framework Using Language Models","created":"2021-10-14","cited_by_count":1,"area":null},{"id":"2202.02310","title":"EcoFlow: Efficient Convolutional Dataflows for Low-Power Neural Network Accelerators","created":"2022-02-04","cited_by_count":1,"area":null},{"id":"2304.12949","title":"eFAT: Improving the Effectiveness of Fault-Aware Training for Mitigating Permanent Faults in DNN Hardware Accelerators","created":"2023-04-20","cited_by_count":1,"area":null},{"id":"2305.10947","title":"Revisiting 16-bit Neural Network Training: A Practical Approach for Resource-Limited Learning","created":"2023-05-18","cited_by_count":1,"area":null},{"id":"2410.24214","title":"ARQ: A Mixed-Precision Quantization Framework for Accurate and Certifiably Robust DNNs","created":"2024-10-31","cited_by_count":1,"area":null},{"id":"2412.13724","title":"USEFUSE: Uniform Stride for Enhanced Performance in Fused Layer Architecture of Deep Neural Networks","created":"2024-12-18","cited_by_count":1,"area":null},{"id":"2501.09849","title":"Coded Deep Learning: Framework and Algorithm","created":"2025-01-16","cited_by_count":1,"area":null},{"id":"2509.12053","title":"LEGO: Spatial Accelerator Generation and Optimization for Tensor Applications","created":"2025-09-15","cited_by_count":1,"area":null},{"id":"2601.20317","title":"VersaQ-3D: Architecture Support for Visual Geometry Grounded Transformers via Versatile Quantization","created":"2026-01-28","cited_by_count":1,"area":null},{"id":"2602.15563","title":"1-Bit Wonder: Improving QAT Performance in the Low-Bit Regime through K-Means Quantization","created":"2026-02-17","cited_by_count":1,"area":null},{"id":"2101.08884","title":"Direct Spatial Implementation of Sparse Matrix Multipliers for Reservoir Computing","created":"2021-01-21","cited_by_count":0,"area":null},{"id":"2108.01192","title":"MOHAQ: Multi-Objective Hardware-Aware Quantization of Recurrent Neural Networks","created":"2021-08-02","cited_by_count":0,"area":null},{"id":"2111.05936","title":"SPA-GCN: Efficient and Flexible GCN Accelerator with an Application for Graph Similarity Computation","created":"2021-11-10","cited_by_count":0,"area":null},{"id":"2203.07679","title":"Energy-efficient Dense DNN Acceleration with Signed Bit-slice Architecture","created":"2022-03-15","cited_by_count":0,"area":null},{"id":"2208.00763","title":"HiKonv: Maximizing the Throughput of Quantized Convolution With Novel Bit-wise Management and Computation","created":"2022-07-22","cited_by_count":0,"area":null},{"id":"2301.12809","title":"The Hidden Power of Pure 16-bit Floating-Point Neural Networks","created":"2023-01-30","cited_by_count":0,"area":null},{"id":"2302.09564","title":"Fixflow: A Framework to Evaluate Fixed-point Arithmetic in Light-Weight CNN Inference","created":"2023-02-19","cited_by_count":0,"area":null},{"id":"2311.14114","title":"SONIQ: System-Optimized Noise-Injected Ultra-Low-Precision Quantization with Full-Precision Parity","created":"2023-11-23","cited_by_count":0,"area":null},{"id":"2404.05368","title":"Exploring Quantization and Mapping Synergy in Hardware-Aware Deep Neural Network Accelerators","created":"2024-04-08","cited_by_count":0,"area":null},{"id":"2411.19114","title":"PREBA: A Hardware/Software Co-Design for Multi-Instance GPU based AI Inference Servers","created":"2024-11-28","cited_by_count":0,"area":null},{"id":"2502.19662","title":"HALO: Hardware-aware quantization with low critical-path-delay weights for LLM acceleration","created":"2025-02-27","cited_by_count":0,"area":null},{"id":"2505.05893","title":"LightNobel: Improving Sequence Length Limitation in Protein Structure Prediction Model via Adaptive Activation Quantization","created":"2025-05-09","cited_by_count":0,"area":null},{"id":"2507.01429","title":"Hardware-software co-exploration with racetrack memory based in-memory computing for CNN inference in embedded systems","created":"2025-07-02","cited_by_count":0,"area":null},{"id":"2507.22760","title":"Of Good Demons and Bad Angels: Guaranteeing Safe Control under Finite Precision","created":"2025-07-30","cited_by_count":0,"area":null},{"id":"2508.07142","title":"Why Does Stochastic Gradient Descent Slow Down in Low-Precision Training?","created":"2025-08-10","cited_by_count":0,"area":null},{"id":"2511.19740","title":"CAMformer: Associative Memory is All You Need","created":"2025-11-24","cited_by_count":0,"area":null}],"next_cursor":"100"}