{"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/21","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":21,"pages_in_order":50,"rows_per_page":100,"rows":[2001,2100],"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/20","next":"/task/quantization/papers/22","papers":[{"url":null,"slug":"dataset-distillation-as-pushforward-optimal","title":"Dataset Distillation as Pushforward Optimal Quantization","date":"2025-01-13","arxiv_id":"2501.07681","repositories_listed":0,"syntology":null},{"url":null,"slug":"flexquant-elastic-quantization-framework-for","title":"FlexQuant: Elastic Quantization Framework for Locally Hosted LLM on Edge Devices","date":"2025-01-13","arxiv_id":"2501.07139","repositories_listed":0,"syntology":null},{"url":null,"slug":"koopman-meets-limited-bandwidth-effect-of","title":"Koopman Meets Limited Bandwidth: Effect of Quantization on Data-Driven Linear Prediction and Control of Nonlinear Systems","date":"2025-01-13","arxiv_id":"2501.07714","repositories_listed":0,"syntology":null},{"url":null,"slug":"quantunev2-compiler-based-local-metric-driven","title":"QuantuneV2: Compiler-Based Local Metric-Driven Mixed Precision Quantization for Practical Embedded AI Applications","date":"2025-01-13","arxiv_id":"2501.07161","repositories_listed":0,"syntology":null},{"url":null,"slug":"zoqo-zero-order-quantized-optimization","title":"ZOQO: Zero-Order Quantized Optimization","date":"2025-01-12","arxiv_id":"2501.06736","repositories_listed":0,"syntology":null},{"url":null,"slug":"mix-qvit-mixed-precision-vision-transformer","title":"Mix-QViT: Mixed-Precision Vision Transformer Quantization Driven by Layer Importance and Quantization Sensitivity","date":"2025-01-10","arxiv_id":"2501.06357","repositories_listed":0,"syntology":null},{"url":null,"slug":"precoding-design-for-limited-feedback-miso","title":"Precoding Design for Limited-Feedback MISO Systems via Character-Polynomial Codes","date":"2025-01-10","arxiv_id":"2501.06178","repositories_listed":0,"syntology":null},{"url":null,"slug":"jaq-joint-efficient-architecture-design-and","title":"JAQ: Joint Efficient Architecture Design and Low-Bit Quantization with Hardware-Software Co-Exploration","date":"2025-01-09","arxiv_id":"2501.05339","repositories_listed":0,"syntology":null},{"url":null,"slug":"knowledge-transfer-in-model-based","title":"Knowledge Transfer in Model-Based Reinforcement Learning Agents for Efficient Multi-Task Learning","date":"2025-01-09","arxiv_id":"2501.05329","repositories_listed":0,"syntology":null},{"url":null,"slug":"histogram-equalized-quantization-for-logic","title":"Histogram-Equalized Quantization for logic-gated Residual Neural Networks","date":"2025-01-08","arxiv_id":"2501.04517","repositories_listed":0,"syntology":null},{"url":null,"slug":"upaq-a-framework-for-real-time-and-energy","title":"UPAQ: A Framework for Real-Time and Energy-Efficient 3D Object Detection in Autonomous Vehicles","date":"2025-01-08","arxiv_id":"2501.04213","repositories_listed":0,"syntology":null},{"url":null,"slug":"effective-and-efficient-mixed-precision","title":"Effective and Efficient Mixed Precision Quantization of Speech Foundation Models","date":"2025-01-07","arxiv_id":"2501.03643","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-novel-structure-agnostic-multi-objective","title":"A Novel Structure-Agnostic Multi-Objective Approach for Weight-Sharing Compression in Deep Neural Networks","date":"2025-01-06","arxiv_id":"2501.03095","repositories_listed":0,"syntology":null},{"url":null,"slug":"quantization-meets-reasoning-exploring-llm","title":"Quantization Meets Reasoning: Exploring LLM Low-Bit Quantization Degradation for Mathematical Reasoning","date":"2025-01-06","arxiv_id":"2501.03035","repositories_listed":0,"syntology":null},{"url":null,"slug":"scaling-laws-for-floating-point-quantization","title":"Scaling Laws for Floating Point Quantization Training","date":"2025-01-05","arxiv_id":"2501.02423","repositories_listed":0,"syntology":null},{"url":null,"slug":"tapas-thermal-and-power-aware-scheduling-for","title":"TAPAS: Thermal- and Power-Aware Scheduling for LLM Inference in Cloud Platforms","date":"2025-01-05","arxiv_id":"2501.02600","repositories_listed":0,"syntology":null},{"url":null,"slug":"optimizing-small-language-models-for-in","title":"Optimizing Small Language Models for In-Vehicle Function-Calling","date":"2025-01-04","arxiv_id":"2501.02342","repositories_listed":0,"syntology":null},{"url":null,"slug":"compressed-domain-prior-guided-video-super","title":"Compressed Domain Prior-Guided Video Super-Resolution for Cloud Gaming Content","date":"2025-01-03","arxiv_id":"2501.01773","repositories_listed":0,"syntology":null},{"url":null,"slug":"millimeter-wave-energy-efficient-hybrid","title":"Millimeter-Wave Energy-Efficient Hybrid Beamforming Architecture and Algorithm","date":"2025-01-03","arxiv_id":"2501.01684","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploiting-latent-properties-to-optimize","title":"Exploiting Latent Properties to Optimize Neural Codecs","date":"2025-01-02","arxiv_id":"2501.01231","repositories_listed":0,"syntology":null},{"url":null,"slug":"modulo-sampling-performance-guarantees-in-the","title":"Modulo Sampling: Performance Guarantees in The Presence of Quantization","date":"2025-01-02","arxiv_id":"2501.01506","repositories_listed":0,"syntology":null},{"url":null,"slug":"tabtreeformer-tree-augmented-tabular-data","title":"TabTreeFormer: Tabular Data Generation Using Hybrid Tree-Transformer","date":"2025-01-02","arxiv_id":"2501.01216","repositories_listed":0,"syntology":null},{"url":null,"slug":"cachequant-comprehensively-accelerated","title":"CacheQuant: Comprehensively Accelerated Diffusion Models","date":"2025-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"dynscene-scalable-generation-of-dynamic","title":"DynScene: Scalable Generation of Dynamic Robotic Manipulation Scenes for Embodied AI","date":"2025-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-decoupled-feature-3d-gaussian","title":"Efficient Decoupled Feature 3D Gaussian Splatting via Hierarchical Compression","date":"2025-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-diversity-for-data-free","title":"Enhancing Diversity for Data-free Quantization","date":"2025-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"frequency-biased-synergistic-design-for-image","title":"Frequency-Biased Synergistic Design for Image Compression and Compensation","date":"2025-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"multirate-neural-image-compression-with","title":"Multirate Neural Image Compression with Adaptive Lattice Vector Quantization","date":"2025-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"pillarhist-a-quantization-aware-pillar-1","title":"PillarHist: A Quantization-aware Pillar Feature Encoder based on Height-aware Histogram","date":"2025-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"pioneering-4-bit-fp-quantization-for","title":"Pioneering 4-Bit FP Quantization for Diffusion Models: Mixup-Sign Quantization and Timestep-Aware Fine-Tuning","date":"2025-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"rethinking-diffusion-for-text-driven-human-1","title":"Rethinking Diffusion for Text-Driven Human Motion Generation: Redundant Representations, Evaluation, and Masked Autoregression","date":"2025-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"secret-lies-in-color-enhancing-ai-generated","title":"Secret Lies in Color: Enhancing AI-Generated Images Detection with Color Distribution Analysis","date":"2025-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"self-supervised-learning-for-color-spike","title":"Self-Supervised Learning for Color Spike Camera Reconstruction","date":"2025-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"steps-sequential-probability-tensor","title":"STEPS: Sequential Probability Tensor Estimation for Text-to-Image Hard Prompt Search","date":"2025-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"intuitive-analysis-of-the-quantization-based","title":"Intuitive Analysis of the Quantization-based Optimization: From Stochastic and Quantum Mechanical Perspective","date":"2024-12-31","arxiv_id":"2501.00436","repositories_listed":0,"syntology":null},{"url":null,"slug":"accelerating-energy-efficient-federated","title":"Accelerating Energy-Efficient Federated Learning in Cell-Free Networks with Adaptive Quantization","date":"2024-12-30","arxiv_id":"2412.20785","repositories_listed":0,"syntology":null},{"url":null,"slug":"dota-weight-decomposed-tensor-adaptation-for","title":"DoTA: Weight-Decomposed Tensor Adaptation for Large Language Models","date":"2024-12-30","arxiv_id":"2412.20891","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-acoustic-scene-classification-in","title":"Improving Acoustic Scene Classification in Low-Resource Conditions","date":"2024-12-30","arxiv_id":"2412.20722","repositories_listed":0,"syntology":null},{"url":null,"slug":"pqd-post-training-quantization-for-efficient","title":"PQD: Post-training Quantization for Efficient Diffusion Models","date":"2024-12-30","arxiv_id":"2501.00124","repositories_listed":0,"syntology":null},{"url":null,"slug":"imssa-deploying-modern-state-space-models-on","title":"IMSSA: Deploying modern state-space models on memristive in-memory compute hardware","date":"2024-12-28","arxiv_id":"2412.20215","repositories_listed":0,"syntology":null},{"url":null,"slug":"pushing-the-envelope-of-low-bit-llm-via","title":"Pushing the Envelope of Low-Bit LLM via Dynamic Error Compensation","date":"2024-12-28","arxiv_id":"2412.20185","repositories_listed":0,"syntology":null},{"url":null,"slug":"data-free-group-wise-fully-quantized-winograd","title":"Data-Free Group-Wise Fully Quantized Winograd Convolution via Learnable Scales","date":"2024-12-27","arxiv_id":"2412.19867","repositories_listed":0,"syntology":null},{"url":null,"slug":"causal-speech-enhancement-with-predicting","title":"Causal Speech Enhancement with Predicting Semantics based on Quantized Self-supervised Learning Features","date":"2024-12-26","arxiv_id":"2412.19248","repositories_listed":0,"syntology":null},{"url":null,"slug":"semantic-residual-for-multimodal-unified","title":"Semantic Residual for Multimodal Unified Discrete Representation","date":"2024-12-26","arxiv_id":"2412.19128","repositories_listed":0,"syntology":null},{"url":null,"slug":"recommending-pre-trained-models-for-iot","title":"Recommending Pre-Trained Models for IoT Devices","date":"2024-12-25","arxiv_id":"2412.18972","repositories_listed":0,"syntology":null},{"url":null,"slug":"resource-efficient-transformer-architecture","title":"Resource-Efficient Transformer Architecture: Optimizing Memory and Execution Time for Real-Time Applications","date":"2024-12-25","arxiv_id":"2501.00042","repositories_listed":0,"syntology":null},{"url":null,"slug":"1-58-bit-flux","title":"1.58-bit FLUX","date":"2024-12-24","arxiv_id":"2412.18653","repositories_listed":0,"syntology":null},{"url":null,"slug":"achieving-robustness-in-blind-modulo-analog","title":"Achieving Robustness in Blind Modulo Analog-to-Digital Conversion","date":"2024-12-24","arxiv_id":"2412.18312","repositories_listed":0,"syntology":null},{"url":null,"slug":"lsaq-layer-specific-adaptive-quantization-for","title":"LSAQ: Layer-Specific Adaptive Quantization for Large Language Model Deployment","date":"2024-12-24","arxiv_id":"2412.18135","repositories_listed":0,"syntology":null},{"url":null,"slug":"unified-stochastic-framework-for-neural","title":"Unified Stochastic Framework for Neural Network Quantization and Pruning","date":"2024-12-24","arxiv_id":"2412.18184","repositories_listed":0,"syntology":null},{"url":null,"slug":"gqsa-group-quantization-and-sparsity-for","title":"GQSA: Group Quantization and Sparsity for Accelerating Large Language Model Inference","date":"2024-12-23","arxiv_id":"2412.17560","repositories_listed":0,"syntology":null},{"url":null,"slug":"adaptive-dataset-quantization","title":"Adaptive Dataset Quantization","date":"2024-12-22","arxiv_id":"2412.16895","repositories_listed":0,"syntology":null},{"url":null,"slug":"semantics-prompting-data-free-quantization","title":"Semantics Prompting Data-Free Quantization for Low-Bit Vision Transformers","date":"2024-12-21","arxiv_id":"2412.16553","repositories_listed":0,"syntology":null},{"url":null,"slug":"tcaq-dm-timestep-channel-adaptive","title":"TCAQ-DM: Timestep-Channel Adaptive Quantization for Diffusion Models","date":"2024-12-21","arxiv_id":"2412.16700","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-quantization-aware-training-of-low","title":"Improving Quantization-aware Training of Low-Precision Network via Block Replacement on Full-Precision Counterpart","date":"2024-12-20","arxiv_id":"2412.15846","repositories_listed":0,"syntology":null},{"url":null,"slug":"mixllm-llm-quantization-with-global-mixed","title":"MixLLM: LLM Quantization with Global Mixed-precision between Output-features and Highly-efficient System Design","date":"2024-12-19","arxiv_id":"2412.14590","repositories_listed":0,"syntology":null},{"url":null,"slug":"progressive-fine-to-coarse-reconstruction-for","title":"Progressive Fine-to-Coarse Reconstruction for Accurate Low-Bit Post-Training Quantization in Vision Transformers","date":"2024-12-19","arxiv_id":"2412.14633","repositories_listed":0,"syntology":null},{"url":null,"slug":"qua-2-sedimo-quantifiable-quantization","title":"Qua$^2$SeDiMo: Quantifiable Quantization Sensitivity of Diffusion Models","date":"2024-12-19","arxiv_id":"2412.14628","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-the-compression-of-language-models-for","title":"On the Compression of Language Models for Code: An Empirical Study on CodeBERT","date":"2024-12-18","arxiv_id":"2412.13737","repositories_listed":0,"syntology":null},{"url":null,"slug":"self-control-a-better-conditional-mechanism","title":"Self-control: A Better Conditional Mechanism for Masked Autoregressive Model","date":"2024-12-18","arxiv_id":"2412.13635","repositories_listed":0,"syntology":null},{"url":null,"slug":"more-tokens-lower-precision-towards-the","title":"More Tokens, Lower Precision: Towards the Optimal Token-Precision Trade-off in KV Cache Compression","date":"2024-12-17","arxiv_id":"2412.12706","repositories_listed":0,"syntology":null},{"url":null,"slug":"apollo-forecast-overcoming-aliasing-and","title":"Apollo-Forecast: Overcoming Aliasing and Inference Speed Challenges in Language Models for Time Series Forecasting","date":"2024-12-16","arxiv_id":"2412.12226","repositories_listed":0,"syntology":null},{"url":null,"slug":"csr-achieving-1-bit-key-value-cache-via","title":"CSR:Achieving 1 Bit Key-Value Cache via Sparse Representation","date":"2024-12-16","arxiv_id":"2412.11741","repositories_listed":0,"syntology":null},{"url":null,"slug":"finlora-finetuning-quantized-financial-large","title":"FinLoRA: Finetuning Quantized Financial Large Language Models Using Low-Rank Adaptation","date":"2024-12-16","arxiv_id":"2412.11378","repositories_listed":0,"syntology":null},{"url":null,"slug":"qpruner-probabilistic-decision-quantization","title":"QPruner: Probabilistic Decision Quantization for Structured Pruning in Large Language Models","date":"2024-12-16","arxiv_id":"2412.11629","repositories_listed":0,"syntology":null},{"url":null,"slug":"quantization-of-climate-change-impacts-on","title":"Quantifying Climate Change Impacts on Renewable Energy Generation: A Super-Resolution Recurrent Diffusion Model","date":"2024-12-16","arxiv_id":"2412.11399","repositories_listed":0,"syntology":null},{"url":null,"slug":"vrvvc-variable-rate-nerf-based-volumetric","title":"VRVVC: Variable-Rate NeRF-Based Volumetric Video Compression","date":"2024-12-16","arxiv_id":"2412.11362","repositories_listed":0,"syntology":null},{"url":null,"slug":"nanoscaling-floating-point-nxfp-nanomantissa","title":"Nanoscaling Floating-Point (NxFP): NanoMantissa, Adaptive Microexponents, and Code Recycling for Direct-Cast Compression of Large Language Models","date":"2024-12-15","arxiv_id":"2412.19821","repositories_listed":0,"syntology":null},{"url":null,"slug":"profe-communication-efficient-decentralized","title":"ProFe: Communication-Efficient Decentralized Federated Learning via Distillation and Prototypes","date":"2024-12-15","arxiv_id":"2412.11207","repositories_listed":0,"syntology":null},{"url":null,"slug":"trimllm-progressive-layer-dropping-for-domain","title":"TrimLLM: Progressive Layer Dropping for Domain-Specific LLMs","date":"2024-12-15","arxiv_id":"2412.11242","repositories_listed":0,"syntology":null},{"url":null,"slug":"adaptive-quantization-resolution-and-power","title":"Adaptive Quantization Resolution and Power Control for Federated Learning over Cell-free Networks","date":"2024-12-14","arxiv_id":"2412.10878","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-off-grid-one-bit-doa-estimation","title":"Enhancing Off-Grid One-Bit DOA Estimation with Learning-Based Sparse Bayesian Approach for Non-Uniform Sparse Array","date":"2024-12-14","arxiv_id":"2412.10976","repositories_listed":0,"syntology":null},{"url":null,"slug":"memory-efficient-4-bit-preconditioned","title":"Memory-Efficient 4-bit Preconditioned Stochastic Optimization","date":"2024-12-14","arxiv_id":"2412.10663","repositories_listed":0,"syntology":null},{"url":null,"slug":"progressive-compression-with-universally","title":"Progressive Compression with Universally Quantized Diffusion Models","date":"2024-12-14","arxiv_id":"2412.10935","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-generative-modeling-with-residual","title":"Efficient Generative Modeling with Residual Vector Quantization-Based Tokens","date":"2024-12-13","arxiv_id":"2412.10208","repositories_listed":0,"syntology":null},{"url":null,"slug":"mvq-towards-efficient-dnn-compression-and","title":"MVQ:Towards Efficient DNN Compression and Acceleration with Masked Vector Quantization","date":"2024-12-13","arxiv_id":"2412.10261","repositories_listed":0,"syntology":null},{"url":null,"slug":"panacea-novel-dnn-accelerator-using-accuracy","title":"Panacea: Novel DNN Accelerator using Accuracy-Preserving Asymmetric Quantization and Energy-Saving Bit-Slice Sparsity","date":"2024-12-13","arxiv_id":"2412.10059","repositories_listed":0,"syntology":null},{"url":null,"slug":"ttaq-towards-stable-post-training","title":"TTAQ: Towards Stable Post-training Quantization in Continuous Domain Adaptation","date":"2024-12-13","arxiv_id":"2412.09899","repositories_listed":0,"syntology":null},{"url":null,"slug":"vqtalker-towards-multilingual-talking-avatars","title":"VQTalker: Towards Multilingual Talking Avatars through Facial Motion Tokenization","date":"2024-12-13","arxiv_id":"2412.09892","repositories_listed":0,"syntology":null},{"url":null,"slug":"crvq-channel-relaxed-vector-quantization-for","title":"CRVQ: Channel-relaxed Vector Quantization for Extreme Compression of LLMs","date":"2024-12-12","arxiv_id":"2412.09282","repositories_listed":0,"syntology":null},{"url":null,"slug":"dqa-an-efficient-method-for-deep-quantization","title":"DQA: An Efficient Method for Deep Quantization of Deep Neural Network Activations","date":"2024-12-12","arxiv_id":"2412.09687","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-round-off-errors-and-gaussian-blur-in","title":"On Round-Off Errors and Gaussian Blur in Superresolution and in Image Registration","date":"2024-12-12","arxiv_id":"2412.09741","repositories_listed":0,"syntology":null},{"url":null,"slug":"optimising-tinyml-with-quantization-and","title":"Optimising TinyML with Quantization and Distillation of Transformer and Mamba Models for Indoor Localisation on Edge Devices","date":"2024-12-12","arxiv_id":"2412.09289","repositories_listed":0,"syntology":null},{"url":null,"slug":"breaking-the-bias-recalibrating-the-attention","title":"Breaking the Bias: Recalibrating the Attention of Industrial Anomaly Detection","date":"2024-12-11","arxiv_id":"2412.08189","repositories_listed":0,"syntology":null},{"url":null,"slug":"turboattention-efficient-attention","title":"TurboAttention: Efficient Attention Approximation For High Throughputs LLMs","date":"2024-12-11","arxiv_id":"2412.08585","repositories_listed":0,"syntology":null},{"url":null,"slug":"ai-driven-conservative-to-primitive","title":"Machine learning-driven conservative-to-primitive conversion in hybrid piecewise polytropic and tabulated equations of state","date":"2024-12-10","arxiv_id":"2412.07836","repositories_listed":0,"syntology":null},{"url":null,"slug":"low-rank-correction-for-quantized-llms","title":"Low-Rank Correction for Quantized LLMs","date":"2024-12-10","arxiv_id":"2412.07902","repositories_listed":0,"syntology":null},{"url":null,"slug":"post-training-non-uniform-quantization-for","title":"Post-Training Non-Uniform Quantization for Convolutional Neural Networks","date":"2024-12-10","arxiv_id":"2412.07391","repositories_listed":0,"syntology":null},{"url":null,"slug":"quantformer-learning-to-quantize-for-neural","title":"QuantFormer: Learning to Quantize for Neural Activity Forecasting in Mouse Visual Cortex","date":"2024-12-10","arxiv_id":"2412.07264","repositories_listed":0,"syntology":null},{"url":null,"slug":"compression-for-better-a-general-and-stable","title":"Compression for Better: A General and Stable Lossless Compression Framework","date":"2024-12-09","arxiv_id":"2412.06868","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficiency-meets-fidelity-a-novel","title":"Efficiency Meets Fidelity: A Novel Quantization Framework for Stable Diffusion","date":"2024-12-09","arxiv_id":"2412.06661","repositories_listed":0,"syntology":null},{"url":null,"slug":"federated-split-learning-with-model-pruning","title":"Federated Split Learning with Model Pruning and Gradient Quantization in Wireless Networks","date":"2024-12-09","arxiv_id":"2412.06414","repositories_listed":0,"syntology":null},{"url":null,"slug":"fp-xint-a-low-bit-series-expansion-algorithm","title":"FP=xINT:A Low-Bit Series Expansion Algorithm for Post-Training Quantization","date":"2024-12-09","arxiv_id":"2412.06865","repositories_listed":0,"syntology":null},{"url":null,"slug":"fuzzy-norm-explicit-product-quantization-for","title":"Fuzzy Norm-Explicit Product Quantization for Recommender Systems","date":"2024-12-08","arxiv_id":"2412.06069","repositories_listed":0,"syntology":null},{"url":null,"slug":"sizegs-size-aware-compression-of-3d-gaussians","title":"SizeGS: Size-aware Compression of 3D Gaussians with Hierarchical Mixed Precision Quantization","date":"2024-12-08","arxiv_id":"2412.05808","repositories_listed":0,"syntology":null},{"url":null,"slug":"taming-sensitive-weights-noise-perturbation","title":"Taming Sensitive Weights : Noise Perturbation Fine-tuning for Robust LLM Quantization","date":"2024-12-08","arxiv_id":"2412.06858","repositories_listed":0,"syntology":null},{"url":null,"slug":"vision-transformer-based-semantic","title":"Vision Transformer-based Semantic Communications With Importance-Aware Quantization","date":"2024-12-08","arxiv_id":"2412.06038","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-distributed-training-through","title":"Efficient Distributed Training through Gradient Compression with Sparsification and Quantization Techniques","date":"2024-12-07","arxiv_id":"2502.07634","repositories_listed":0,"syntology":null},{"url":null,"slug":"error-feedback-approach-for-quantization","title":"Error Feedback Approach for Quantization Noise Reduction of Distributed Graph Filters","date":"2024-12-07","arxiv_id":"2412.05651","repositories_listed":0,"syntology":null},{"url":null,"slug":"gaqat-gradient-adaptive-quantization-aware","title":"GAQAT: gradient-adaptive quantization-aware training for domain generalization","date":"2024-12-07","arxiv_id":"2412.05551","repositories_listed":0,"syntology":null}],"record_sha256":"50f3d727080e01dba767bf375b2c64cc25fe5d3ab7aad7c091c9474c83cc572d","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}