{"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/model-compression/papers/7","list_of":"/task/model-compression","task":"Model Compression","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":7,"pages_in_order":14,"rows_per_page":100,"rows":[601,700],"of":1356,"counts":{"archive_papers_tagged":1356,"with_a_code_link":440,"where_syntology_ran_a_sample":119,"not_listed_spam_title":0,"listed":1356,"listed_where_code_ran":119,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":97,"every_run_a_failure_of_syntologys_instrument":22,"listed_with_a_run_with_no_instrument_failure":97,"listed_every_run_a_failure_of_syntologys_instrument":22,"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/model-compression","prev":"/task/model-compression/papers/6","next":"/task/model-compression/papers/8","papers":[{"url":null,"slug":"nvrc-neural-video-representation-compression","title":"NVRC: Neural Video Representation Compression","date":"2024-09-11","arxiv_id":"2409.07414","repositories_listed":0,"syntology":null},{"url":null,"slug":"ultron-enabling-temporal-geometry-compression","title":"Ultron: Enabling Temporal Geometry Compression of 3D Mesh Sequences using Temporal Correspondence and Mesh Deformation","date":"2024-09-08","arxiv_id":"2409.05151","repositories_listed":0,"syntology":null},{"url":null,"slug":"loca-logit-calibration-for-knowledge","title":"LoCa: Logit Calibration for Knowledge Distillation","date":"2024-09-07","arxiv_id":"2409.04778","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-point-cloud-classification-via","title":"Efficient Point Cloud Classification via Offline Distillation Framework and Negative-Weight Self-Distillation Technique","date":"2024-09-03","arxiv_id":"2409.02020","repositories_listed":0,"syntology":null},{"url":null,"slug":"foundations-of-large-language-model","title":"Foundations of Large Language Model Compression -- Part 1: Weight Quantization","date":"2024-09-03","arxiv_id":"2409.02026","repositories_listed":0,"syntology":null},{"url":null,"slug":"edge-ai-evaluation-of-model-compression","title":"Edge AI: Evaluation of Model Compression Techniques for Convolutional Neural Networks","date":"2024-09-02","arxiv_id":"2409.02134","repositories_listed":0,"syntology":null},{"url":null,"slug":"convolutional-neural-network-compression-1","title":"Convolutional Neural Network Compression Based on Low-Rank Decomposition","date":"2024-08-29","arxiv_id":"2408.16289","repositories_listed":0,"syntology":null},{"url":null,"slug":"variational-autoencoder-based-neural-network","title":"Variational autoencoder-based neural network model compression","date":"2024-08-25","arxiv_id":"2408.14513","repositories_listed":0,"syntology":null},{"url":null,"slug":"mpruner-optimizing-neural-network-size-with","title":"MPruner: Optimizing Neural Network Size with CKA-Based Mutual Information Pruning","date":"2024-08-24","arxiv_id":"2408.13482","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-survey-on-drowsiness-detection-modern","title":"A Survey on Drowsiness Detection -- Modern Applications and Methods","date":"2024-08-23","arxiv_id":"2408.12990","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-web-based-solution-for-federated-learning","title":"A Web-Based Solution for Federated Learning with LLM-Based Automation","date":"2024-08-23","arxiv_id":"2408.13010","repositories_listed":0,"syntology":null},{"url":null,"slug":"fine-tuning-and-deploying-large-language","title":"Fine-Tuning and Deploying Large Language Models Over Edges: Issues and Approaches","date":"2024-08-20","arxiv_id":"2408.10691","repositories_listed":0,"syntology":null},{"url":null,"slug":"ner-vcp-a-video-content-protection-method","title":"NeR-VCP: A Video Content Protection Method Based on Implicit Neural Representation","date":"2024-08-20","arxiv_id":"2408.15281","repositories_listed":0,"syntology":null},{"url":null,"slug":"modegpt-modular-decomposition-for-large","title":"MoDeGPT: Modular Decomposition for Large Language Model Compression","date":"2024-08-19","arxiv_id":"2408.09632","repositories_listed":0,"syntology":null},{"url":null,"slug":"repcontrolnet-controlnet-reparameterization","title":"RepControlNet: ControlNet Reparameterization","date":"2024-08-17","arxiv_id":"2408.09240","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-effective-information-theoretic-framework","title":"An Effective Information Theoretic Framework for Channel Pruning","date":"2024-08-14","arxiv_id":"2408.16772","repositories_listed":0,"syntology":null},{"url":null,"slug":"infra-yolo-efficient-neural-network-structure","title":"Infra-YOLO: Efficient Neural Network Structure with Model Compression for Real-Time Infrared Small Object Detection","date":"2024-08-14","arxiv_id":"2408.07455","repositories_listed":0,"syntology":null},{"url":null,"slug":"adapmtl-adaptive-pruning-framework-for","title":"AdapMTL: Adaptive Pruning Framework for Multitask Learning Model","date":"2024-08-07","arxiv_id":"2408.03913","repositories_listed":0,"syntology":null},{"url":null,"slug":"2408-03274","title":"Compress and Compare: Interactively Evaluating Efficiency and Behavior Across ML Model Compression Experiments","date":"2024-08-06","arxiv_id":"2408.03274","repositories_listed":0,"syntology":null},{"url":null,"slug":"2408-03291","title":"DopQ-ViT: Towards Distribution-Friendly and Outlier-Aware Post-Training Quantization for Vision Transformers","date":"2024-08-06","arxiv_id":"2408.03291","repositories_listed":0,"syntology":null},{"url":null,"slug":"2408-01008","title":"Tensor Train Low-rank Approximation (TT-LoRA): Democratizing AI with Accelerated LLMs","date":"2024-08-02","arxiv_id":"2408.01008","repositories_listed":0,"syntology":null},{"url":null,"slug":"2408-02685","title":"Artificial Neural Networks for Photonic Applications: From Algorithms to Implementation","date":"2024-08-02","arxiv_id":"2408.02685","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-adaptive-tensor-train-decomposition","title":"An Efficient Real-Time Object Detection Framework on Resource-Constricted Hardware Devices via Software and Hardware Co-design","date":"2024-08-02","arxiv_id":"2408.01534","repositories_listed":0,"syntology":null},{"url":null,"slug":"neusemslice-towards-effective-dnn-model","title":"NeuSemSlice: Towards Effective DNN Model Maintenance via Neuron-level Semantic Slicing","date":"2024-07-26","arxiv_id":"2407.20281","repositories_listed":0,"syntology":null},{"url":null,"slug":"comprehensive-study-on-performance-evaluation","title":"Comprehensive Study on Performance Evaluation and Optimization of Model Compression: Bridging Traditional Deep Learning and Large Language Models","date":"2024-07-22","arxiv_id":"2407.15904","repositories_listed":0,"syntology":null},{"url":null,"slug":"lortsar-low-rank-transformer-for-skeleton","title":"LORTSAR: Low-Rank Transformer for Skeleton-based Action Recognition","date":"2024-07-19","arxiv_id":"2407.14655","repositories_listed":0,"syntology":null},{"url":null,"slug":"compressed-models-are-not-miniature-versions","title":"Compressed models are NOT miniature versions of large models","date":"2024-07-18","arxiv_id":"2407.13174","repositories_listed":0,"syntology":null},{"url":null,"slug":"mamba-ptq-outlier-channels-in-recurrent-large","title":"Mamba-PTQ: Outlier Channels in Recurrent Large Language Models","date":"2024-07-17","arxiv_id":"2407.12397","repositories_listed":0,"syntology":null},{"url":null,"slug":"inference-optimization-of-foundation-models","title":"Inference Optimization of Foundation Models on AI Accelerators","date":"2024-07-12","arxiv_id":"2407.09111","repositories_listed":0,"syntology":null},{"url":null,"slug":"explicit-nerf-qa-a-quality-assessment","title":"Explicit-NeRF-QA: A Quality Assessment Database for Explicit NeRF Model Compression","date":"2024-07-11","arxiv_id":"2407.08165","repositories_listed":0,"syntology":null},{"url":null,"slug":"quantizing-yolov7-a-comprehensive-study","title":"Quantizing YOLOv7: A Comprehensive Study","date":"2024-07-06","arxiv_id":"2407.04943","repositories_listed":0,"syntology":null},{"url":null,"slug":"amd-automatic-multi-step-distillation-of","title":"AMD: Automatic Multi-step Distillation of Large-scale Vision Models","date":"2024-07-05","arxiv_id":"2407.04208","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-impact-of-quantization-and-pruning-on","title":"The Impact of Quantization and Pruning on Deep Reinforcement Learning Models","date":"2024-07-05","arxiv_id":"2407.04803","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-dnn-powered-software-with-fair","title":"Efficient DNN-Powered Software with Fair Sparse Models","date":"2024-07-03","arxiv_id":"2407.02805","repositories_listed":0,"syntology":null},{"url":null,"slug":"mlkd-bert-multi-level-knowledge-distillation","title":"MLKD-BERT: Multi-level Knowledge Distillation for Pre-trained Language Models","date":"2024-07-03","arxiv_id":"2407.02775","repositories_listed":0,"syntology":null},{"url":null,"slug":"foldgpt-simple-and-effective-large-language","title":"FoldGPT: Simple and Effective Large Language Model Compression Scheme","date":"2024-07-01","arxiv_id":"2407.00928","repositories_listed":0,"syntology":null},{"url":null,"slug":"mcnc-manifold-constrained-network-compression","title":"MCNC: Manifold Constrained Network Compression","date":"2024-06-27","arxiv_id":"2406.19301","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-compressibility-of-transformer","title":"Exploring compressibility of transformer based text-to-music (TTM) models","date":"2024-06-24","arxiv_id":"2406.17159","repositories_listed":0,"syntology":null},{"url":null,"slug":"speeding-up-image-classifiers-with-little","title":"Speeding Up Image Classifiers with Little Companions","date":"2024-06-24","arxiv_id":"2406.17117","repositories_listed":0,"syntology":null},{"url":null,"slug":"failure-resilient-distributed-inference-with","title":"Failure-Resilient Distributed Inference with Model Compression over Heterogeneous Edge Devices","date":"2024-06-20","arxiv_id":"2406.14185","repositories_listed":0,"syntology":null},{"url":null,"slug":"sdq-sparse-decomposed-quantization-for-llm","title":"SDQ: Sparse Decomposed Quantization for LLM Inference","date":"2024-06-19","arxiv_id":"2406.13868","repositories_listed":0,"syntology":null},{"url":null,"slug":"finding-task-specific-subnetworks-in-multi","title":"Finding Task-specific Subnetworks in Multi-task Spoken Language Understanding Model","date":"2024-06-18","arxiv_id":"2406.12317","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-empirical-investigation-of-matrix","title":"An Empirical Investigation of Matrix Factorization Methods for Pre-trained Transformers","date":"2024-06-17","arxiv_id":"2406.11307","repositories_listed":0,"syntology":null},{"url":null,"slug":"compress-then-serve-serving-thousands-of-lora","title":"Compress then Serve: Serving Thousands of LoRA Adapters with Little Overhead","date":"2024-06-17","arxiv_id":"2407.00066","repositories_listed":0,"syntology":null},{"url":null,"slug":"model-adaptation-for-time-constrained-1","title":"Model Adaptation for Time Constrained Embodied Control","date":"2024-06-17","arxiv_id":"2406.11128","repositories_listed":0,"syntology":null},{"url":null,"slug":"knowledge-distillation-in-federated-learning","title":"Knowledge Distillation in Federated Learning: a Survey on Long Lasting Challenges and New Solutions","date":"2024-06-16","arxiv_id":"2406.10861","repositories_listed":0,"syntology":null},{"url":null,"slug":"implicit-neural-representation-for-videos","title":"Implicit Neural Representation for Videos Based on Residual Connection","date":"2024-06-15","arxiv_id":"2407.06164","repositories_listed":0,"syntology":null},{"url":null,"slug":"enccluster-scalable-functional-encryption-in","title":"EncCluster: Scalable Functional Encryption in Federated Learning through Weight Clustering and Probabilistic Filters","date":"2024-06-13","arxiv_id":"2406.09152","repositories_listed":0,"syntology":null},{"url":null,"slug":"pc-lora-low-rank-adaptation-for-progressive","title":"PC-LoRA: Low-Rank Adaptation for Progressive Model Compression with Knowledge Distillation","date":"2024-06-13","arxiv_id":"2406.09117","repositories_listed":0,"syntology":null},{"url":null,"slug":"distildoc-knowledge-distillation-for-visually","title":"DistilDoc: Knowledge Distillation for Visually-Rich Document Applications","date":"2024-06-12","arxiv_id":"2406.08226","repositories_listed":0,"syntology":null},{"url":null,"slug":"mobileaibench-benchmarking-llms-and-lmms-for","title":"MobileAIBench: Benchmarking LLMs and LMMs for On-Device Use Cases","date":"2024-06-12","arxiv_id":"2406.10290","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-the-social-bias-of-speech-self-supervised","title":"On the social bias of speech self-supervised models","date":"2024-06-07","arxiv_id":"2406.04997","repositories_listed":0,"syntology":null},{"url":null,"slug":"reweighted-solutions-for-weighted-low-rank","title":"Reweighted Solutions for Weighted Low Rank Approximation","date":"2024-06-04","arxiv_id":"2406.02431","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-efficient-deep-spiking-neural","title":"Towards Efficient Deep Spiking Neural Networks Construction with Spiking Activity based Pruning","date":"2024-06-03","arxiv_id":"2406.01072","repositories_listed":0,"syntology":null},{"url":null,"slug":"effective-interplay-between-sparsity-and","title":"Effective Interplay between Sparsity and Quantization: From Theory to Practice","date":"2024-05-31","arxiv_id":"2405.20935","repositories_listed":0,"syntology":null},{"url":null,"slug":"lcq-low-rank-codebook-based-quantization-for","title":"LCQ: Low-Rank Codebook based Quantization for Large Language Models","date":"2024-05-31","arxiv_id":"2405.20973","repositories_listed":0,"syntology":null},{"url":null,"slug":"dual-sparse-training-framework-inducing","title":"Dual sparse training framework: inducing activation map sparsity via Transformed $\\ell1$ regularization","date":"2024-05-30","arxiv_id":"2405.19652","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-model-compression-for-hierarchical","title":"Efficient Model Compression for Hierarchical Federated Learning","date":"2024-05-27","arxiv_id":"2405.17522","repositories_listed":0,"syntology":null},{"url":null,"slug":"extrememeta-high-speed-lightweight-image","title":"ExtremeMETA: High-speed Lightweight Image Segmentation Model by Remodeling Multi-channel Metamaterial Imagers","date":"2024-05-27","arxiv_id":"2405.17568","repositories_listed":0,"syntology":null},{"url":null,"slug":"nv-embed-improved-techniques-for-training","title":"NV-Embed: Improved Techniques for Training LLMs as Generalist Embedding Models","date":"2024-05-27","arxiv_id":"2405.17428","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficiency-optimization-of-large-scale","title":"Efficiency optimization of large-scale language models based on deep learning in natural language processing tasks","date":"2024-05-20","arxiv_id":"2405.11704","repositories_listed":0,"syntology":null},{"url":null,"slug":"tinym-2-net-v3-memory-aware-compressed","title":"TinyM$^2$Net-V3: Memory-Aware Compressed Multimodal Deep Neural Networks for Sustainable Edge Deployment","date":"2024-05-20","arxiv_id":"2405.12353","repositories_listed":0,"syntology":null},{"url":null,"slug":"densely-distilling-cumulative-knowledge-for","title":"Densely Distilling Cumulative Knowledge for Continual Learning","date":"2024-05-16","arxiv_id":"2405.09820","repositories_listed":0,"syntology":null},{"url":null,"slug":"adakd-dynamic-knowledge-distillation-of-asr","title":"AdaKD: Dynamic Knowledge Distillation of ASR models using Adaptive Loss Weighting","date":"2024-05-11","arxiv_id":"2405.08019","repositories_listed":0,"syntology":null},{"url":null,"slug":"characterizing-the-accuracy-efficiency-trade","title":"Characterizing the Accuracy -- Efficiency Trade-off of Low-rank Decomposition in Language Models","date":"2024-05-10","arxiv_id":"2405.06626","repositories_listed":0,"syntology":null},{"url":null,"slug":"from-algorithm-to-hardware-a-survey-on","title":"From Algorithm to Hardware: A Survey on Efficient and Safe Deployment of Deep Neural Networks","date":"2024-05-09","arxiv_id":"2405.06038","repositories_listed":0,"syntology":null},{"url":null,"slug":"nurturenet-a-multi-task-video-based-approach","title":"NurtureNet: A Multi-task Video-based Approach for Newborn Anthropometry","date":"2024-05-09","arxiv_id":"2405.05530","repositories_listed":0,"syntology":null},{"url":null,"slug":"light-field-compression-based-on-implicit","title":"Light Field Compression Based on Implicit Neural Representation","date":"2024-05-07","arxiv_id":"2407.10325","repositories_listed":0,"syntology":null},{"url":null,"slug":"communication-efficient-federated-learning-24","title":"Communication-Efficient Federated Learning with Adaptive Compression under Dynamic Bandwidth","date":"2024-05-06","arxiv_id":"2405.03248","repositories_listed":0,"syntology":null},{"url":null,"slug":"dependency-aware-semi-structured-sparsity-of","title":"Dependency-Aware Semi-Structured Sparsity of GLU Variants in Large Language Models","date":"2024-05-03","arxiv_id":"2405.01943","repositories_listed":0,"syntology":null},{"url":null,"slug":"fedgreen-carbon-aware-federated-learning-with","title":"FedGreen: Carbon-aware Federated Learning with Model Size Adaptation","date":"2024-04-23","arxiv_id":"2404.15503","repositories_listed":0,"syntology":null},{"url":null,"slug":"rapid-deployment-of-dnns-for-edge-computing","title":"Rapid Deployment of DNNs for Edge Computing via Structured Pruning at Initialization","date":"2024-04-22","arxiv_id":"2404.16877","repositories_listed":0,"syntology":null},{"url":null,"slug":"nongemm-bench-understanding-the-performance","title":"Understanding the Performance Horizon of the Latest ML Workloads with NonGEMM Workloads","date":"2024-04-17","arxiv_id":"2404.11788","repositories_listed":0,"syntology":null},{"url":null,"slug":"comprehensive-survey-of-model-compression-and","title":"Comprehensive Survey of Model Compression and Speed up for Vision Transformers","date":"2024-04-16","arxiv_id":"2404.10407","repositories_listed":0,"syntology":null},{"url":null,"slug":"structured-model-pruning-for-efficient","title":"Structured Model Pruning for Efficient Inference in Computational Pathology","date":"2024-04-12","arxiv_id":"2404.08831","repositories_listed":0,"syntology":null},{"url":null,"slug":"bayesian-federated-model-compression-for","title":"Bayesian Federated Model Compression for Communication and Computation Efficiency","date":"2024-04-11","arxiv_id":"2404.07532","repositories_listed":0,"syntology":null},{"url":null,"slug":"simplifying-two-stage-detectors-for-on-device","title":"Simplifying Two-Stage Detectors for On-Device Inference in Remote Sensing","date":"2024-04-11","arxiv_id":"2404.07405","repositories_listed":0,"syntology":null},{"url":null,"slug":"automated-inference-of-graph-transformation","title":"Automated Inference of Graph Transformation Rules","date":"2024-04-03","arxiv_id":"2404.02692","repositories_listed":0,"syntology":null},{"url":null,"slug":"improve-knowledge-distillation-via-label","title":"Improve Knowledge Distillation via Label Revision and Data Selection","date":"2024-04-03","arxiv_id":"2404.03693","repositories_listed":0,"syntology":null},{"url":null,"slug":"knowledge-distillation-with-multi-granularity","title":"Knowledge Distillation with Multi-granularity Mixture of Priors for Image Super-Resolution","date":"2024-04-03","arxiv_id":"2404.02573","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-linearizing-structured-data-in-encoder","title":"On Linearizing Structured Data in Encoder-Decoder Language Models: Insights from Text-to-SQL","date":"2024-04-03","arxiv_id":"2404.02389","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-inference-efficiency-of-large","title":"Enhancing Inference Efficiency of Large Language Models: Investigating Optimization Strategies and Architectural Innovations","date":"2024-04-02","arxiv_id":"2404.05741","repositories_listed":0,"syntology":null},{"url":null,"slug":"instance-aware-group-quantization-for-vision","title":"Instance-Aware Group Quantization for Vision Transformers","date":"2024-04-01","arxiv_id":"2404.00928","repositories_listed":0,"syntology":null},{"url":null,"slug":"dense-vision-transformer-compression-with-few","title":"Dense Vision Transformer Compression with Few Samples","date":"2024-03-27","arxiv_id":"2403.18708","repositories_listed":0,"syntology":null},{"url":null,"slug":"chain-of-compression-a-systematic-approach-to","title":"Order of Compression: A Systematic and Optimal Sequence to Combinationally Compress CNN","date":"2024-03-26","arxiv_id":"2403.17447","repositories_listed":0,"syntology":null},{"url":null,"slug":"magic-for-the-age-of-quantized-dnns","title":"Magic for the Age of Quantized DNNs","date":"2024-03-22","arxiv_id":"2403.14999","repositories_listed":0,"syntology":null},{"url":null,"slug":"advancing-iiot-with-over-the-air-federated","title":"Advancing IIoT with Over-the-Air Federated Learning: The Role of Iterative Magnitude Pruning","date":"2024-03-21","arxiv_id":"2403.14120","repositories_listed":0,"syntology":null},{"url":null,"slug":"dipaco-distributed-path-composition","title":"DiPaCo: Distributed Path Composition","date":"2024-03-15","arxiv_id":"2403.10616","repositories_listed":0,"syntology":null},{"url":null,"slug":"briedge-eeg-adaptive-edge-ai-for-multi-brain","title":"BRIEDGE: EEG-Adaptive Edge AI for Multi-Brain to Multi-Robot Interaction","date":"2024-03-14","arxiv_id":"2403.15432","repositories_listed":0,"syntology":null},{"url":null,"slug":"maxwell-s-demon-at-work-efficient-pruning-by","title":"Maxwell's Demon at Work: Efficient Pruning by Leveraging Saturation of Neurons","date":"2024-03-12","arxiv_id":"2403.07688","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhanced-sparsification-via-stimulative","title":"Enhanced Sparsification via Stimulative Training","date":"2024-03-11","arxiv_id":"2403.06417","repositories_listed":0,"syntology":null},{"url":null,"slug":"optimal-policy-sparsification-and-low-rank","title":"Optimal Policy Sparsification and Low Rank Decomposition for Deep Reinforcement Learning","date":"2024-03-10","arxiv_id":"2403.06313","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-efficient-deep-autoencoders-for","title":"Towards efficient deep autoencoders for multivariate time series anomaly detection","date":"2024-03-04","arxiv_id":"2403.02429","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-method-for-s4-with-diagonal-state","title":"Model Compression Method for S4 with Diagonal State Space Layers using Balanced Truncation","date":"2024-02-25","arxiv_id":"2402.15993","repositories_listed":0,"syntology":null},{"url":null,"slug":"fingpt-hpc-efficient-pretraining-and","title":"FinGPT-HPC: Efficient Pretraining and Finetuning Large Language Models for Financial Applications with High-Performance Computing","date":"2024-02-21","arxiv_id":"2402.13533","repositories_listed":0,"syntology":null},{"url":null,"slug":"from-cloud-to-edge-rethinking-generative-ai","title":"From Cloud to Edge: Rethinking Generative AI for Low-Resource Design Challenges","date":"2024-02-20","arxiv_id":"2402.12702","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-a-tailored-mixed-precision-sub-8bit","title":"Towards a tailored mixed-precision sub-8-bit quantization scheme for Gated Recurrent Units using Genetic Algorithms","date":"2024-02-19","arxiv_id":"2402.12263","repositories_listed":0,"syntology":null},{"url":null,"slug":"extraction-of-nonlinearity-in-neural-networks","title":"Extraction of nonlinearity in neural networks with Koopman operator","date":"2024-02-18","arxiv_id":"2402.11740","repositories_listed":0,"syntology":null},{"url":null,"slug":"model-compression-and-efficient-inference-for","title":"Model Compression and Efficient Inference for Large Language Models: A Survey","date":"2024-02-15","arxiv_id":"2402.09748","repositories_listed":0,"syntology":null},{"url":null,"slug":"bayesian-federated-learning-via-expectation","title":"Bayesian Deep Learning Via Expectation Maximization and Turbo Deep Approximate Message Passing","date":"2024-02-12","arxiv_id":"2402.07366","repositories_listed":0,"syntology":null}],"record_sha256":"3b5401f1e0e11a42a1c8bd6e41e8238d8d8b231f22d4a9e711ed6e2a25744998","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}