{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/quantization/papers/28","list_of":"/task/quantization","task":"Quantization","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":28,"pages_in_order":50,"rows_per_page":100,"rows":[2701,2800],"of":4925,"counts":{"archive_papers_tagged":4925,"with_a_code_link":1596,"where_syntology_ran_a_sample":515,"not_listed_spam_title":0,"listed":4925,"listed_where_code_ran":515,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":452,"every_run_a_failure_of_syntologys_instrument":63,"listed_with_a_run_with_no_instrument_failure":452,"listed_every_run_a_failure_of_syntologys_instrument":63,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/task/quantization","prev":"/task/quantization/papers/27","next":"/task/quantization/papers/29","papers":[{"url":null,"slug":"optimal-and-near-optimal-adaptive-vector","title":"Optimal and Near-Optimal Adaptive Vector Quantization","date":"2024-02-05","arxiv_id":"2402.03158","repositories_listed":0,"syntology":null},{"url":null,"slug":"quantized-approximately-orthogonal-recurrent","title":"Quantized Approximately Orthogonal Recurrent Neural Networks","date":"2024-02-05","arxiv_id":"2402.04012","repositories_listed":0,"syntology":null},{"url":null,"slug":"foldtoken-learning-protein-language-via","title":"FoldToken: Learning Protein Language via Vector Quantization and Beyond","date":"2024-02-04","arxiv_id":"2403.09673","repositories_listed":0,"syntology":null},{"url":null,"slug":"stability-analysis-of-various-symbolic-rule","title":"Stability Analysis of Various Symbolic Rule Extraction Methods from Recurrent Neural Network","date":"2024-02-04","arxiv_id":"2402.02627","repositories_listed":0,"syntology":null},{"url":null,"slug":"locally-adaptive-quantization-for-streaming","title":"Locally-Adaptive Quantization for Streaming Vector Search","date":"2024-02-03","arxiv_id":"2402.02044","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-intra-brnn-and-gb-rvq-based-end-to-end","title":"An Intra-BRNN and GB-RVQ Based END-TO-END Neural Audio Codec","date":"2024-02-02","arxiv_id":"2402.01271","repositories_listed":0,"syntology":null},{"url":null,"slug":"faster-inference-of-integer-swin-transformer","title":"Faster Inference of Integer SWIN Transformer by Removing the GELU Activation","date":"2024-02-02","arxiv_id":"2402.01169","repositories_listed":0,"syntology":null},{"url":null,"slug":"fedshift-tackling-dual-heterogeneity-problem","title":"FedShift: Tackling Dual Heterogeneity Problem of Federated Learning via Weight Shift Aggregation","date":"2024-02-02","arxiv_id":"2402.01070","repositories_listed":0,"syntology":null},{"url":null,"slug":"hw-sw-optimization-of-dnns-for-privacy","title":"HW-SW Optimization of DNNs for Privacy-preserving People Counting on Low-resolution Infrared Arrays","date":"2024-02-02","arxiv_id":"2402.01226","repositories_listed":0,"syntology":null},{"url":null,"slug":"improved-quantization-strategies-for-managing","title":"Improved Quantization Strategies for Managing Heavy-tailed Gradients in Distributed Learning","date":"2024-02-02","arxiv_id":"2402.01798","repositories_listed":0,"syntology":null},{"url":null,"slug":"structured-world-modeling-via-semantic-vector","title":"Neural Language of Thought Models","date":"2024-02-02","arxiv_id":"2402.01203","repositories_listed":0,"syntology":null},{"url":null,"slug":"truncated-non-uniform-quantization-for","title":"Truncated Non-Uniform Quantization for Distributed SGD","date":"2024-02-02","arxiv_id":"2402.01160","repositories_listed":0,"syntology":null},{"url":null,"slug":"analog-digital-scheduling-for-federated","title":"Analog-digital Scheduling for Federated Learning: A Communication-Efficient Approach","date":"2024-02-01","arxiv_id":"2402.00318","repositories_listed":0,"syntology":null},{"url":null,"slug":"can-large-language-models-understand-context","title":"Can Large Language Models Understand Context?","date":"2024-02-01","arxiv_id":"2402.00858","repositories_listed":0,"syntology":null},{"url":null,"slug":"trainable-fixed-point-quantization-for-deep","title":"Trainable Fixed-Point Quantization for Deep Learning Acceleration on FPGAs","date":"2024-01-31","arxiv_id":"2401.17544","repositories_listed":0,"syntology":null},{"url":null,"slug":"effect-of-weight-quantization-on-learning","title":"Effect of Weight Quantization on Learning Models by Typical Case Analysis","date":"2024-01-30","arxiv_id":"2401.17269","repositories_listed":0,"syntology":null},{"url":null,"slug":"hequant-marrying-homomorphic-encryption-and","title":"HEQuant: Marrying Homomorphic Encryption and Quantization for Communication-Efficient Private Inference","date":"2024-01-29","arxiv_id":"2401.15970","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-comprehensive-survey-of-compression","title":"A Comprehensive Survey of Compression Algorithms for Language Models","date":"2024-01-27","arxiv_id":"2401.15347","repositories_listed":0,"syntology":null},{"url":null,"slug":"transformer-based-clipped-contrastive","title":"Transformer-based Clipped Contrastive Quantization Learning for Unsupervised Image Retrieval","date":"2024-01-27","arxiv_id":"2401.15362","repositories_listed":0,"syntology":null},{"url":null,"slug":"lite-snn-designing-lightweight-and-efficient","title":"LitE-SNN: Designing Lightweight and Efficient Spiking Neural Network through Spatial-Temporal Compressive Network Search and Joint Optimization","date":"2024-01-26","arxiv_id":"2401.14652","repositories_listed":0,"syntology":null},{"url":null,"slug":"mptq-vit-mixed-precisionpost","title":"MPTQ-ViT: Mixed-Precision Post-Training Quantization for Vision Transformer","date":"2024-01-26","arxiv_id":"2401.14895","repositories_listed":0,"syntology":null},{"url":null,"slug":"compactifai-extreme-compression-of-large","title":"CompactifAI: Extreme Compression of Large Language Models using Quantum-Inspired Tensor Networks","date":"2024-01-25","arxiv_id":"2401.14109","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-cheaper-inference-in-deep-networks","title":"Towards Cheaper Inference in Deep Networks with Lower Bit-Width Accumulators","date":"2024-01-25","arxiv_id":"2401.14110","repositories_listed":0,"syntology":null},{"url":null,"slug":"within-basket-recommendation-via-neural","title":"Within-basket Recommendation via Neural Pattern Associator","date":"2024-01-25","arxiv_id":"2401.16433","repositories_listed":0,"syntology":null},{"url":null,"slug":"value-driven-mixed-precision-quantization-for","title":"Value-Driven Mixed-Precision Quantization for Patch-Based Inference on Microcontrollers","date":"2024-01-24","arxiv_id":"2401.13714","repositories_listed":0,"syntology":null},{"url":null,"slug":"iterated-relevance-matrix-analysis-irma-for","title":"Iterated Relevance Matrix Analysis (IRMA) for the identification of class-discriminative subspaces","date":"2024-01-23","arxiv_id":"2401.12842","repositories_listed":0,"syntology":null},{"url":null,"slug":"robustness-to-distribution-shifts-of","title":"Robustness to distribution shifts of compressed networks for edge devices","date":"2024-01-22","arxiv_id":"2401.12014","repositories_listed":0,"syntology":null},{"url":null,"slug":"scaling-up-quantization-aware-neural","title":"Scaling Up Quantization-Aware Neural Architecture Search for Efficient Deep Learning on the Edge","date":"2024-01-22","arxiv_id":"2401.12350","repositories_listed":0,"syntology":null},{"url":null,"slug":"another-way-to-the-top-exploit-contextual","title":"Another Way to the Top: Exploit Contextual Clustering in Learned Image Coding","date":"2024-01-21","arxiv_id":"2401.11615","repositories_listed":0,"syntology":null},{"url":null,"slug":"edge-enabled-real-time-railway-track","title":"Edge-Enabled Real-time Railway Track Segmentation","date":"2024-01-21","arxiv_id":"2401.11492","repositories_listed":0,"syntology":null},{"url":null,"slug":"lrp-qvit-mixed-precision-vision-transformer","title":"LRP-QViT: Mixed-Precision Vision Transformer Quantization via Layer-wise Relevance Propagation","date":"2024-01-20","arxiv_id":"2401.11243","repositories_listed":0,"syntology":null},{"url":null,"slug":"dynamic-q-a-of-clinical-documents-with-large","title":"Dynamic Q&A of Clinical Documents with Large Language Models","date":"2024-01-19","arxiv_id":"2401.10733","repositories_listed":0,"syntology":null},{"url":null,"slug":"enabling-on-device-continual-learning-with","title":"Enabling On-device Continual Learning with Binary Neural Networks","date":"2024-01-18","arxiv_id":"2401.09916","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploration-of-activation-fault-reliability","title":"Exploration of Activation Fault Reliability in Quantized Systolic Array-Based DNN Accelerators","date":"2024-01-17","arxiv_id":"2401.09509","repositories_listed":0,"syntology":null},{"url":null,"slug":"hybrid-of-diffstride-and-spectral-pooling-in","title":"Hybrid of DiffStride and Spectral Pooling in Convolutional Neural Networks","date":"2024-01-17","arxiv_id":"2401.09008","repositories_listed":0,"syntology":null},{"url":null,"slug":"tp-aware-dequantization","title":"TP-Aware Dequantization","date":"2024-01-15","arxiv_id":"2402.04925","repositories_listed":0,"syntology":null},{"url":null,"slug":"ented-enhanced-neural-texture-extraction-and","title":"ENTED: Enhanced Neural Texture Extraction and Distribution for Reference-based Blind Face Restoration","date":"2024-01-13","arxiv_id":"2401.06978","repositories_listed":0,"syntology":null},{"url":null,"slug":"correlated-quantization-for-faster-nonconvex","title":"Correlated Quantization for Faster Nonconvex Distributed Optimization","date":"2024-01-10","arxiv_id":"2401.05518","repositories_listed":0,"syntology":null},{"url":null,"slug":"memory-efficient-personalization-using","title":"Memory-Efficient Fine-Tuning for Quantized Diffusion Model","date":"2024-01-09","arxiv_id":"2401.04339","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-video-coding-method-based-on-neural-network","title":"A Video Coding Method Based on Neural Network for CLIC2024","date":"2024-01-08","arxiv_id":"2401.03623","repositories_listed":0,"syntology":null},{"url":null,"slug":"detecting-face-synthesis-using-a-concealed","title":"Detecting Face Synthesis Using a Concealed Fusion Model","date":"2024-01-08","arxiv_id":"2401.04257","repositories_listed":0,"syntology":null},{"url":null,"slug":"flightllm-efficient-large-language-model","title":"FlightLLM: Efficient Large Language Model Inference with a Complete Mapping Flow on FPGAs","date":"2024-01-08","arxiv_id":"2401.03868","repositories_listed":0,"syntology":null},{"url":null,"slug":"data-driven-dynamic-event-triggered-control","title":"Data-driven Dynamic Event-triggered Control","date":"2024-01-07","arxiv_id":"2401.03363","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-cost-efficient-fpga-implementation-of-tiny","title":"A Cost-Efficient FPGA Implementation of Tiny Transformer Model using Neural ODE","date":"2024-01-05","arxiv_id":"2401.02721","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-generalization-of-invisible-facial","title":"Enhancing Generalization of Invisible Facial Privacy Cloak via Gradient Accumulation","date":"2024-01-03","arxiv_id":"2401.01575","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-model-free-lqr-control-over-rate","title":"Model-Free Learning for the Linear Quadratic Regulator over Rate-Limited Channels","date":"2024-01-02","arxiv_id":"2401.01258","repositories_listed":0,"syntology":null},{"url":null,"slug":"are-conventional-snns-really-efficient-a","title":"Are Conventional SNNs Really Efficient? A Perspective from Network Quantization","date":"2024-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"data-free-quantization-via-pseudo-label","title":"Data-Free Quantization via Pseudo-label Filtering","date":"2024-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-post-training-quantization","title":"Enhancing Post-training Quantization Calibration through Contrastive Learning","date":"2024-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"pikelpn-mitigating-overlooked-inefficiencies","title":"PikeLPN: Mitigating Overlooked Inefficiencies of Low-Precision Neural Networks","date":"2024-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"predtoken-predicting-unknown-tokens-and","title":"PredToken: Predicting Unknown Tokens and Beyond with Coarse-to-Fine Iterative Decoding","date":"2024-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"reg-ptq-regression-specialized-post-training","title":"Reg-PTQ: Regression-specialized Post-training Quantization for Fully Quantized Object Detector","date":"2024-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"hq-vae-hierarchical-discrete-representation","title":"HQ-VAE: Hierarchical Discrete Representation Learning with Variational Bayes","date":"2023-12-31","arxiv_id":"2401.00365","repositories_listed":0,"syntology":null},{"url":null,"slug":"compact-neural-graphics-primitives-with","title":"Compact Neural Graphics Primitives with Learned Hash Probing","date":"2023-12-28","arxiv_id":"2312.17241","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-sdm-accelerating-stable-diffusion-through","title":"A-SDM: Accelerating Stable Diffusion through Redundancy Removal and Performance Optimization","date":"2023-12-24","arxiv_id":"2312.15516","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-asynchronous-federated-learning","title":"Efficient Asynchronous Federated Learning with Sparsification and Quantization","date":"2023-12-23","arxiv_id":"2312.15186","repositories_listed":0,"syntology":null},{"url":null,"slug":"hardware-aware-dnn-compression-via-diverse","title":"Hardware-Aware DNN Compression via Diverse Pruning and Mixed-Precision Quantization","date":"2023-12-23","arxiv_id":"2312.15322","repositories_listed":0,"syntology":null},{"url":null,"slug":"cross-layer-optimization-for-fault-tolerant","title":"Cross-Layer Optimization for Fault-Tolerant Deep Learning","date":"2023-12-21","arxiv_id":"2312.13754","repositories_listed":0,"syntology":null},{"url":null,"slug":"simq-nas-simultaneous-quantization-policy-and","title":"SimQ-NAS: Simultaneous Quantization Policy and Neural Architecture Search","date":"2023-12-19","arxiv_id":"2312.13301","repositories_listed":0,"syntology":null},{"url":null,"slug":"power-efficient-sampling","title":"Power-Efficient Sampling","date":"2023-12-18","arxiv_id":"2312.10966","repositories_listed":0,"syntology":null},{"url":null,"slug":"quantized-decoder-in-learned-image","title":"Quantized Decoder in Learned Image Compression for Deterministic Reconstruction","date":"2023-12-18","arxiv_id":"2312.11209","repositories_listed":0,"syntology":null},{"url":null,"slug":"iqnet-image-quality-assessment-guided-just","title":"IQNet: Image Quality Assessment Guided Just Noticeable Difference Prefiltering For Versatile Video Coding","date":"2023-12-15","arxiv_id":"2312.09799","repositories_listed":0,"syntology":null},{"url":null,"slug":"design-space-exploration-of-low-bit-quantized","title":"Design Space Exploration of Low-Bit Quantized Neural Networks for Visual Place Recognition","date":"2023-12-14","arxiv_id":"2312.09028","repositories_listed":0,"syntology":null},{"url":null,"slug":"cbq-cross-block-quantization-for-large","title":"CBQ: Cross-Block Quantization for Large Language Models","date":"2023-12-13","arxiv_id":"2312.07950","repositories_listed":0,"syntology":null},{"url":null,"slug":"usm-lite-quantization-and-sparsity-aware-fine","title":"USM-Lite: Quantization and Sparsity Aware Fine-tuning for Speech Recognition with Universal Speech Models","date":"2023-12-13","arxiv_id":"2312.08553","repositories_listed":0,"syntology":null},{"url":"/paper/expand-and-quantize-unsupervised-semantic","slug":"expand-and-quantize-unsupervised-semantic","title":"Expand-and-Quantize: Unsupervised Semantic Segmentation Using High-Dimensional Space and Product Quantization","date":"2023-12-12","arxiv_id":"2312.07342","repositories_listed":0,"syntology":null},{"url":null,"slug":"idkm-memory-efficient-neural-network","title":"IDKM: Memory Efficient Neural Network Quantization via Implicit, Differentiable k-Means","date":"2023-12-12","arxiv_id":"2312.07759","repositories_listed":0,"syntology":null},{"url":null,"slug":"when-bio-inspired-computing-meets-deep","title":"When Bio-Inspired Computing meets Deep Learning: Low-Latency, Accurate, & Energy-Efficient Spiking Neural Networks from Artificial Neural Networks","date":"2023-12-12","arxiv_id":"2312.06900","repositories_listed":0,"syntology":null},{"url":null,"slug":"fp8-bert-post-training-quantization-for","title":"FP8-BERT: Post-Training Quantization for Transformer","date":"2023-12-10","arxiv_id":"2312.05725","repositories_listed":0,"syntology":null},{"url":null,"slug":"neural-architecture-codesign-for-fast-bragg","title":"Neural Architecture Codesign for Fast Bragg Peak Analysis","date":"2023-12-10","arxiv_id":"2312.05978","repositories_listed":0,"syntology":null},{"url":null,"slug":"qmgeo-differentially-private-federated","title":"QMGeo: Differentially Private Federated Learning via Stochastic Quantization with Mixed Truncated Geometric Distribution","date":"2023-12-10","arxiv_id":"2312.05761","repositories_listed":0,"syntology":null},{"url":null,"slug":"automotive-radar-sensing-with-sparse-linear","title":"Automotive Radar Sensing with Sparse Linear Arrays Using One-Bit Hankel Matrix Completion","date":"2023-12-09","arxiv_id":"2312.05423","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-quantization-strategies-for-latent","title":"Efficient Quantization Strategies for Latent Diffusion Models","date":"2023-12-09","arxiv_id":"2312.05431","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-experimental-study-assessing-the-combined","title":"An Experimental Study: Assessing the Combined Framework of WavLM and BEST-RQ for Text-to-Speech Synthesis","date":"2023-12-08","arxiv_id":"2312.05415","repositories_listed":0,"syntology":null},{"url":null,"slug":"rate-splitting-multiple-access-for-5","title":"Rate-splitting Multiple Access for Hierarchical HAP-LAP Networks under Limited Fronthaul","date":"2023-12-07","arxiv_id":"2312.04081","repositories_listed":0,"syntology":null},{"url":null,"slug":"stableq-enhancing-data-scarce-quantization","title":"GenQ: Quantization in Low Data Regimes with Generative Synthetic Data","date":"2023-12-07","arxiv_id":"2312.05272","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-kinship-verification-through","title":"Enhancing Kinship Verification through Multiscale Retinex and Combined Deep-Shallow features","date":"2023-12-06","arxiv_id":"2312.03562","repositories_listed":0,"syntology":null},{"url":null,"slug":"all-rivers-run-to-the-sea-private-learning","title":"All Rivers Run to the Sea: Private Learning with Asymmetric Flows","date":"2023-12-05","arxiv_id":"2312.05264","repositories_listed":0,"syntology":null},{"url":null,"slug":"unified-learning-based-lossy-and-lossless","title":"Unified learning-based lossy and lossless JPEG recompression","date":"2023-12-05","arxiv_id":"2312.02705","repositories_listed":0,"syntology":null},{"url":null,"slug":"low-precision-mixed-computation-models-for","title":"Low-Precision Mixed-Computation Models for Inference on Edge","date":"2023-12-03","arxiv_id":"2312.02210","repositories_listed":0,"syntology":null},{"url":null,"slug":"adaptive-resource-allocation-for-semantic","title":"Adaptive Resource Allocation for Semantic Communication Networks","date":"2023-12-02","arxiv_id":"2312.01081","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-new-old-idea-beam-steering-reflectarrays","title":"A New Old Idea: Beam-Steering Reflectarrays for Efficient Sub-THz Multiuser MIMO","date":"2023-11-30","arxiv_id":"2311.18593","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-the-robustness-of-quantized-deep","title":"Improving the Robustness of Quantized Deep Neural Networks to White-Box Attacks using Stochastic Quantization and Information-Theoretic Ensemble Training","date":"2023-11-30","arxiv_id":"2312.00105","repositories_listed":0,"syntology":null},{"url":null,"slug":"fault-tolerant-four-dimensional-constellation","title":"Fault-Tolerant Four-Dimensional Constellation for Coherent Optical Transmission Systems","date":"2023-11-29","arxiv_id":"2311.17698","repositories_listed":0,"syntology":null},{"url":null,"slug":"mixed-precision-quantization-for-federated","title":"Mixed-Precision Quantization for Federated Learning on Resource-Constrained Heterogeneous Devices","date":"2023-11-29","arxiv_id":"2311.18129","repositories_listed":0,"syntology":null},{"url":null,"slug":"enabling-fast-2-bit-llm-on-gpus-memory","title":"Fast and Efficient 2-bit LLM Inference on GPU: 2/4/16-bit in a Weight Matrix with Asynchronous Dequantization","date":"2023-11-28","arxiv_id":"2311.16442","repositories_listed":0,"syntology":null},{"url":null,"slug":"pipe-parallelized-inference-through-post","title":"PIPE : Parallelized Inference Through Post-Training Quantization Ensembling of Residual Expansions","date":"2023-11-27","arxiv_id":"2311.15806","repositories_listed":0,"syntology":null},{"url":null,"slug":"relationship-between-model-compression-and","title":"Relationship between Model Compression and Adversarial Robustness: A Review of Current Evidence","date":"2023-11-27","arxiv_id":"2311.15782","repositories_listed":0,"syntology":null},{"url":null,"slug":"snn-architecture-for-differential-time","title":"SNN Architecture for Differential Time Encoding Using Decoupled Processing Time","date":"2023-11-24","arxiv_id":"2311.14447","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-blockchain-solution-for-collaborative","title":"A Blockchain Solution for Collaborative Machine Learning over IoT","date":"2023-11-23","arxiv_id":"2311.14136","repositories_listed":0,"syntology":null},{"url":null,"slug":"sysmol-a-hardware-software-co-design","title":"SySMOL: Co-designing Algorithms and Hardware for Neural Networks with Heterogeneous Precisions","date":"2023-11-23","arxiv_id":"2311.14114","repositories_listed":0,"syntology":null},{"url":null,"slug":"modulation-for-modulo-a-sampling-efficient","title":"Modulation For Modulo: A Sampling-Efficient High-Dynamic Range ADC","date":"2023-11-22","arxiv_id":"2311.13282","repositories_listed":0,"syntology":null},{"url":null,"slug":"uncertainty-estimation-in-multi-agent","title":"Uncertainty Estimation in Multi-Agent Distributed Learning","date":"2023-11-22","arxiv_id":"2311.13356","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-learning-based-real-time-quality-control","title":"Deep Learning-Based Real-Time Quality Control of Standard Video Compression for Live Streaming","date":"2023-11-21","arxiv_id":"2311.12918","repositories_listed":0,"syntology":null},{"url":null,"slug":"post-training-quantization-with-low-precision","title":"Shedding the Bits: Pushing the Boundaries of Quantization with Minifloats on FPGAs","date":"2023-11-21","arxiv_id":"2311.12359","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-neural-networks-for-tiny-machine","title":"Efficient Neural Networks for Tiny Machine Learning: A Comprehensive Review","date":"2023-11-20","arxiv_id":"2311.11883","repositories_listed":0,"syntology":null},{"url":null,"slug":"tiny-vbf-resource-efficient-vision","title":"Tiny-VBF: Resource-Efficient Vision Transformer based Lightweight Beamformer for Ultrasound Single-Angle Plane Wave Imaging","date":"2023-11-20","arxiv_id":"2311.12082","repositories_listed":0,"syntology":null},{"url":null,"slug":"low-precision-floating-point-for-efficient-on","title":"Low-Precision Floating-Point for Efficient On-Board Deep Neural Network Processing","date":"2023-11-18","arxiv_id":"2311.11172","repositories_listed":0,"syntology":null},{"url":null,"slug":"is-conventional-snn-really-efficient-a","title":"Is Conventional SNN Really Efficient? A Perspective from Network Quantization","date":"2023-11-17","arxiv_id":"2311.10802","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-speed-odyssey-for-deployable-quantization","title":"A Speed Odyssey for Deployable Quantization of LLMs","date":"2023-11-16","arxiv_id":"2311.09550","repositories_listed":0,"syntology":null}],"record_sha256":"e994658c1984cc1dd74fd31d6e636338074fbc34f724e9e4817ebbef83969742","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}