{"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/26","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":26,"pages_in_order":50,"rows_per_page":100,"rows":[2501,2600],"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/25","next":"/task/quantization/papers/27","papers":[{"url":null,"slug":"outliers-and-calibration-sets-have","title":"Outliers and Calibration Sets have Diminishing Effect on Quantization of Modern LLMs","date":"2024-05-31","arxiv_id":"2405.20835","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-efficient-network-with-novel-quantization","title":"An Efficient Network with Novel Quantization Designed for Massive MIMO CSI Feedback","date":"2024-05-30","arxiv_id":"2405.20068","repositories_listed":0,"syntology":null},{"url":null,"slug":"hq-dit-efficient-diffusion-transformer-with","title":"HQ-DiT: Efficient Diffusion Transformer with FP4 Hybrid Quantization","date":"2024-05-30","arxiv_id":"2405.19751","repositories_listed":0,"syntology":null},{"url":null,"slug":"one-quantllm-for-all-fine-tuning-quantized","title":"One QuantLLM for ALL: Fine-tuning Quantized LLMs Once for Efficient Deployments","date":"2024-05-30","arxiv_id":"2405.20202","repositories_listed":0,"syntology":null},{"url":null,"slug":"s3d-a-simple-and-cost-effective-self","title":"S3D: A Simple and Cost-Effective Self-Speculative Decoding Scheme for Low-Memory GPUs","date":"2024-05-30","arxiv_id":"2405.20314","repositories_listed":0,"syntology":null},{"url":null,"slug":"pillarhist-a-quantization-aware-pillar","title":"Information Entropy Guided Height-aware Histogram for Quantization-friendly Pillar Feature Encoder","date":"2024-05-29","arxiv_id":"2405.18734","repositories_listed":0,"syntology":null},{"url":null,"slug":"i-llm-efficient-integer-only-inference-for","title":"I-LLM: Efficient Integer-Only Inference for Fully-Quantized Low-Bit Large Language Models","date":"2024-05-28","arxiv_id":"2405.17849","repositories_listed":0,"syntology":null},{"url":null,"slug":"llama-nas-efficient-neural-architecture","title":"LLaMA-NAS: Efficient Neural Architecture Search for Large Language Models","date":"2024-05-28","arxiv_id":"2405.18377","repositories_listed":0,"syntology":null},{"url":null,"slug":"mixdq-memory-efficient-few-step-text-to-image","title":"MixDQ: Memory-Efficient Few-Step Text-to-Image Diffusion Models with Metric-Decoupled Mixed Precision Quantization","date":"2024-05-28","arxiv_id":"2405.17873","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-binary-quantized-neural-network-for-dense","title":"The Binary Quantized Neural Network for Dense Prediction via Specially Designed Upsampling and Attention","date":"2024-05-28","arxiv_id":"2405.17776","repositories_listed":0,"syntology":null},{"url":null,"slug":"beamvq-aligning-space-time-forecasting-model","title":"BeamVQ: Aligning Space-Time Forecasting Model via Self-training on Physics-aware Metrics","date":"2024-05-27","arxiv_id":"2405.17051","repositories_listed":0,"syntology":null},{"url":null,"slug":"claq-pushing-the-limits-of-low-bit-post","title":"CLAQ: Pushing the Limits of Low-Bit Post-Training Quantization for LLMs","date":"2024-05-27","arxiv_id":"2405.17233","repositories_listed":0,"syntology":null},{"url":null,"slug":"text-di-2-text-pose-discrete-diffusion-model","title":"$\\text{Di}^2\\text{Pose}$: Discrete Diffusion Model for Occluded 3D Human Pose Estimation","date":"2024-05-27","arxiv_id":"2405.17016","repositories_listed":0,"syntology":null},{"url":null,"slug":"unicompress-enhancing-multi-data-medical","title":"UniCompress: Enhancing Multi-Data Medical Image Compression with Knowledge Distillation","date":"2024-05-27","arxiv_id":"2405.16850","repositories_listed":0,"syntology":null},{"url":null,"slug":"fastquery-communication-efficient-embedding","title":"FastQuery: Communication-efficient Embedding Table Query for Private LLM Inference","date":"2024-05-25","arxiv_id":"2405.16241","repositories_listed":0,"syntology":null},{"url":null,"slug":"athena-efficient-block-wise-post-training","title":"Athena: Efficient Block-Wise Post-Training Quantization for Large Language Models Using Second-Order Matrix Derivative Information","date":"2024-05-24","arxiv_id":"2405.17470","repositories_listed":0,"syntology":null},{"url":null,"slug":"bisup-bidirectional-quantization-error","title":"BiSup: Bidirectional Quantization Error Suppression for Large Language Models","date":"2024-05-24","arxiv_id":"2405.15346","repositories_listed":0,"syntology":null},{"url":null,"slug":"massive-mimo-isac-system-with-1-bit-adcs-dacs","title":"Massive MIMO-ISAC System With 1-Bit ADCs/DACs","date":"2024-05-24","arxiv_id":"2405.15553","repositories_listed":0,"syntology":null},{"url":null,"slug":"asi-towards-distributionally-balanced-end-to","title":"ASI++: Towards Distributionally Balanced End-to-End Generative Retrieval","date":"2024-05-23","arxiv_id":"2405.14280","repositories_listed":0,"syntology":null},{"url":null,"slug":"distilling-vision-language-pretraining-for","title":"Distilling Vision-Language Pretraining for Efficient Cross-Modal Retrieval","date":"2024-05-23","arxiv_id":"2405.14726","repositories_listed":0,"syntology":null},{"url":null,"slug":"embedding-compression-for-efficient-re","title":"Embedding Compression for Efficient Re-Identification","date":"2024-05-23","arxiv_id":"2405.14730","repositories_listed":0,"syntology":null},{"url":null,"slug":"exposure-diffusion-hdr-image-generation-by","title":"Bracket Diffusion: HDR Image Generation by Consistent LDR Denoising","date":"2024-05-23","arxiv_id":"2405.14304","repositories_listed":0,"syntology":null},{"url":null,"slug":"integer-scale-a-free-lunch-for-faster-fine","title":"Integer Scale: A Free Lunch for Faster Fine-grained Quantization of LLMs","date":"2024-05-23","arxiv_id":"2405.14597","repositories_listed":0,"syntology":null},{"url":null,"slug":"lg-vq-language-guided-codebook-learning","title":"LG-VQ: Language-Guided Codebook Learning","date":"2024-05-23","arxiv_id":"2405.14206","repositories_listed":0,"syntology":null},{"url":null,"slug":"minicache-kv-cache-compression-in-depth","title":"MiniCache: KV Cache Compression in Depth Dimension for Large Language Models","date":"2024-05-23","arxiv_id":"2405.14366","repositories_listed":0,"syntology":null},{"url":null,"slug":"multicast-zero-shot-multivariate-time-series","title":"MultiCast: Zero-Shot Multivariate Time Series Forecasting Using LLMs","date":"2024-05-23","arxiv_id":"2405.14748","repositories_listed":0,"syntology":null},{"url":null,"slug":"oac-output-adaptive-calibration-for-accurate","title":"OAC: Output-adaptive Calibration for Accurate Post-training Quantization","date":"2024-05-23","arxiv_id":"2405.15025","repositories_listed":0,"syntology":null},{"url":null,"slug":"path-metrics-pruning-and-generalization","title":"A rescaling-invariant Lipschitz bound based on path-metrics for modern ReLU network parameterizations","date":"2024-05-23","arxiv_id":"2405.15006","repositories_listed":0,"syntology":null},{"url":null,"slug":"adaptive-wireless-image-semantic-transmission","title":"Adaptive Wireless Image Semantic Transmission and Over-The-Air Testing","date":"2024-05-22","arxiv_id":"2405.13403","repositories_listed":0,"syntology":null},{"url":null,"slug":"adpq-a-zero-shot-calibration-free-adaptive","title":"AdpQ: A Zero-shot Calibration Free Adaptive Post Training Quantization Method for LLMs","date":"2024-05-22","arxiv_id":"2405.13358","repositories_listed":0,"syntology":null},{"url":null,"slug":"dct-based-decorrelated-attention-for-vision","title":"Discrete Cosine Transform Based Decorrelated Attention for Vision Transformers","date":"2024-05-22","arxiv_id":"2405.13901","repositories_listed":0,"syntology":null},{"url":null,"slug":"exmy-a-data-type-and-technique-for-arbitrary","title":"eXmY: A Data Type and Technique for Arbitrary Bit Precision Quantization","date":"2024-05-22","arxiv_id":"2405.13938","repositories_listed":0,"syntology":null},{"url":null,"slug":"qgait-toward-accurate-quantization-for-gait","title":"QGait: Toward Accurate Quantization for Gait Recognition with Binarized Input","date":"2024-05-22","arxiv_id":"2405.13859","repositories_listed":0,"syntology":null},{"url":null,"slug":"two-heads-are-better-than-one-neural-networks","title":"Two Heads are Better Than One: Neural Networks Quantization with 2D Hilbert Curve-based Output Representation","date":"2024-05-22","arxiv_id":"2405.14024","repositories_listed":0,"syntology":null},{"url":null,"slug":"generative-ai-and-large-language-models-for","title":"Generative AI in Cybersecurity: A Comprehensive Review of LLM Applications and Vulnerabilities","date":"2024-05-21","arxiv_id":"2405.12750","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-image-registration-and-subpixel-estimation","title":"On Image Registration and Subpixel Estimation","date":"2024-05-21","arxiv_id":"2405.12927","repositories_listed":0,"syntology":null},{"url":null,"slug":"online-signature-recognition-a-biologically","title":"Online Signature Recognition: A Biologically Inspired Feature Vector Splitting Approach","date":"2024-05-21","arxiv_id":"2405.12556","repositories_listed":0,"syntology":null},{"url":null,"slug":"reallm-a-general-framework-for-llm","title":"ReALLM: A general framework for LLM compression and fine-tuning","date":"2024-05-21","arxiv_id":"2405.13155","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":"enhancing-perception-quality-in-remote","title":"Enhancing Perception Quality in Remote Sensing Image Compression via Invertible Neural Network","date":"2024-05-17","arxiv_id":"2405.10518","repositories_listed":0,"syntology":null},{"url":null,"slug":"flattened-one-bit-stochastic-gradient-descent","title":"Flattened one-bit stochastic gradient descent: compressed distributed optimization with controlled variance","date":"2024-05-17","arxiv_id":"2405.11095","repositories_listed":0,"syntology":null},{"url":null,"slug":"universal-joint-source-channel-coding-for","title":"Universal Joint Source-Channel Coding for Modulation-Agnostic Semantic Communication","date":"2024-05-17","arxiv_id":"2405.10749","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-effect-of-quantization-in-federated","title":"The Effect of Quantization in Federated Learning: A Rényi Differential Privacy Perspective","date":"2024-05-16","arxiv_id":"2405.10096","repositories_listed":0,"syntology":null},{"url":null,"slug":"fdd-massive-mimo-how-to-optimally-combine-ul","title":"FDD Massive MIMO: How to Optimally Combine UL Pilot and Limited DL CSI Feedback?","date":"2024-05-14","arxiv_id":"2405.08614","repositories_listed":0,"syntology":null},{"url":null,"slug":"simple-and-efficient-quantization-techniques","title":"Neural Speech Coding for Real-time Communications using Constant Bitrate Scalar Quantization","date":"2024-05-14","arxiv_id":"2405.08417","repositories_listed":0,"syntology":null},{"url":null,"slug":"goal-oriented-compression-for-l-p-norm-type","title":"Goal-oriented compression for $L_p$-norm-type goal functions: Application to power consumption scheduling","date":"2024-05-13","arxiv_id":"2405.07808","repositories_listed":0,"syntology":null},{"url":null,"slug":"vqdna-unleashing-the-power-of-vector","title":"VQDNA: Unleashing the Power of Vector Quantization for Multi-Species Genomic Sequence Modeling","date":"2024-05-13","arxiv_id":"2405.10812","repositories_listed":0,"syntology":null},{"url":null,"slug":"combining-multiple-post-training-techniques","title":"Post Training Quantization of Large Language Models with Microscaling Formats","date":"2024-05-12","arxiv_id":"2405.07135","repositories_listed":0,"syntology":null},{"url":null,"slug":"edge-intelligence-optimization-for-large","title":"Edge Intelligence Optimization for Large Language Model Inference with Batching and Quantization","date":"2024-05-12","arxiv_id":"2405.07140","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":"compression-realized-deep-structural-network","title":"Compression-Realized Deep Structural Network for Video Quality Enhancement","date":"2024-05-10","arxiv_id":"2405.06342","repositories_listed":0,"syntology":null},{"url":"/paper/selective-focus-investigating-semantics","slug":"selective-focus-investigating-semantics","title":"Selective Focus: Investigating Semantics Sensitivity in Post-training Quantization for Lane Detection","date":"2024-05-10","arxiv_id":"2405.06264","repositories_listed":0,"syntology":{"n":14,"n_ran":6,"n_constructed":0,"n_ran_checked":3,"n_instrument":3,"n_unverified":8,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":14,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/selective-focus-investigating-semantics#ran","syntology_url":"https://syntology.ai/paper/2405.06264","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.06264"}},"official":null}},{"url":null,"slug":"skvq-sliding-window-key-and-value-cache","title":"SKVQ: Sliding-window Key and Value Cache Quantization for Large Language Models","date":"2024-05-10","arxiv_id":"2405.06219","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":"custom-gradient-estimators-are-straight","title":"Custom Gradient Estimators are Straight-Through Estimators in Disguise","date":"2024-05-08","arxiv_id":"2405.05171","repositories_listed":0,"syntology":null},{"url":null,"slug":"kv-cache-is-1-bit-per-channel-efficient-large","title":"KV Cache is 1 Bit Per Channel: Efficient Large Language Model Inference with Coupled Quantization","date":"2024-05-07","arxiv_id":"2405.03917","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-65nm-36nj-decision-bio-inspired-temporal","title":"DeltaKWS: A 65nm 36nJ/Decision Bio-inspired Temporal-Sparsity-Aware Digital Keyword Spotting IC with 0.6V Near-Threshold SRAM","date":"2024-05-06","arxiv_id":"2405.03905","repositories_listed":0,"syntology":null},{"url":null,"slug":"compression-based-privacy-preservation-for","title":"Compression-based Privacy Preservation for Distributed Nash Equilibrium Seeking in Aggregative Games","date":"2024-05-06","arxiv_id":"2405.03106","repositories_listed":0,"syntology":null},{"url":null,"slug":"enabling-high-sparsity-foundational-llama","title":"Enabling High-Sparsity Foundational Llama Models with Efficient Pretraining and Deployment","date":"2024-05-06","arxiv_id":"2405.03594","repositories_listed":0,"syntology":null},{"url":null,"slug":"quantifying-the-capabilities-of-llms-across","title":"Quantifying the Capabilities of LLMs across Scale and Precision","date":"2024-05-06","arxiv_id":"2405.03146","repositories_listed":0,"syntology":null},{"url":null,"slug":"joint-discrete-precoding-and-ris-optimization","title":"Joint Discrete Precoding and RIS Optimization for RIS-Assisted MU-MIMO Communication Systems","date":"2024-05-05","arxiv_id":"2405.03022","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-extreme-quantization-in-spiking","title":"Exploring Extreme Quantization in Spiking Language Models","date":"2024-05-04","arxiv_id":"2405.02543","repositories_listed":0,"syntology":null},{"url":null,"slug":"lightweight-change-detection-in-heterogeneous","title":"Lightweight Change Detection in Heterogeneous Remote Sensing Images with Online All-Integer Pruning Training","date":"2024-05-03","arxiv_id":"2405.01920","repositories_listed":0,"syntology":null},{"url":null,"slug":"three-quantization-regimes-for-relu-networks","title":"Three Quantization Regimes for ReLU Networks","date":"2024-05-03","arxiv_id":"2405.01952","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-learning-models-in-speech-recognition","title":"Deep Learning Models in Speech Recognition: Measuring GPU Energy Consumption, Impact of Noise and Model Quantization for Edge Deployment","date":"2024-05-02","arxiv_id":"2405.01004","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-compression-of-multitask","title":"Efficient Compression of Multitask Multilingual Speech Models","date":"2024-05-02","arxiv_id":"2405.00966","repositories_listed":0,"syntology":null},{"url":null,"slug":"joint-sequential-fronthaul-quantization-and","title":"Joint Sequential Fronthaul Quantization and Hardware Complexity Reduction in Uplink Cell-Free Massive MIMO Networks","date":"2024-05-02","arxiv_id":"2405.01303","repositories_listed":0,"syntology":null},{"url":null,"slug":"investigating-automatic-scoring-and-feedback","title":"Investigating Automatic Scoring and Feedback using Large Language Models","date":"2024-05-01","arxiv_id":"2405.00602","repositories_listed":0,"syntology":null},{"url":null,"slug":"wake-vision-a-large-scale-diverse-dataset-and","title":"Wake Vision: A Tailored Dataset and Benchmark Suite for TinyML Computer Vision Applications","date":"2024-05-01","arxiv_id":"2405.00892","repositories_listed":0,"syntology":null},{"url":null,"slug":"transition-rate-scheduling-for-quantization","title":"Transition Rate Scheduling for Quantization-Aware Training","date":"2024-04-30","arxiv_id":"2404.19248","repositories_listed":0,"syntology":null},{"url":null,"slug":"quantized-context-based-lif-neurons-for","title":"Quantized Context Based LIF Neurons for Recurrent Spiking Neural Networks in 45nm","date":"2024-04-28","arxiv_id":"2404.18066","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-channel-estimation-in-quantized","title":"Enhancing Channel Estimation in Quantized Systems with a Generative Prior","date":"2024-04-26","arxiv_id":"2405.03542","repositories_listed":0,"syntology":null},{"url":null,"slug":"sdac-semantic-digital-analog-converter-for","title":"sDAC -- Semantic Digital Analog Converter for Semantic Communications","date":"2024-04-26","arxiv_id":"2405.02335","repositories_listed":0,"syntology":null},{"url":null,"slug":"how-to-parameterize-asymmetric-quantization","title":"How to Parameterize Asymmetric Quantization Ranges for Quantization-Aware Training","date":"2024-04-25","arxiv_id":"2404.16898","repositories_listed":0,"syntology":null},{"url":null,"slug":"mmgrec-multimodal-generative-recommendation","title":"MMGRec: Multimodal Generative Recommendation with Transformer Model","date":"2024-04-25","arxiv_id":"2404.16555","repositories_listed":0,"syntology":null},{"url":null,"slug":"contrastive-quantization-based-semantic-code","title":"CoST: Contrastive Quantization based Semantic Tokenization for Generative Recommendation","date":"2024-04-23","arxiv_id":"2404.14774","repositories_listed":0,"syntology":null},{"url":null,"slug":"adaqat-adaptive-bit-width-quantization-aware","title":"AdaQAT: Adaptive Bit-Width Quantization-Aware Training","date":"2024-04-22","arxiv_id":"2404.16876","repositories_listed":0,"syntology":null},{"url":null,"slug":"cnn-based-equalization-for-communications","title":"CNN-Based Equalization for Communications: Achieving Gigabit Throughput with a Flexible FPGA Hardware Architecture","date":"2024-04-22","arxiv_id":"2405.02323","repositories_listed":0,"syntology":null},{"url":null,"slug":"latency-distortion-tradeoffs-in-communicating","title":"Latency-Distortion Tradeoffs in Communicating Classification Results over Noisy Channels","date":"2024-04-22","arxiv_id":"2404.14586","repositories_listed":0,"syntology":null},{"url":null,"slug":"fedmpq-secure-and-communication-efficient","title":"FedMPQ: Secure and Communication-Efficient Federated Learning with Multi-codebook Product Quantization","date":"2024-04-21","arxiv_id":"2404.13575","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-ser-based-device-selection-mechanism-in","title":"A SER-based Device Selection Mechanism in Multi-bits Quantization Federated Learning","date":"2024-04-20","arxiv_id":"2405.02320","repositories_listed":0,"syntology":null},{"url":null,"slug":"hybridflow-infusing-continuity-into-masked","title":"HybridFlow: Infusing Continuity into Masked Codebook for Extreme Low-Bitrate Image Compression","date":"2024-04-20","arxiv_id":"2404.13372","repositories_listed":0,"syntology":null},{"url":null,"slug":"edgefusion-on-device-text-to-image-generation","title":"EdgeFusion: On-Device Text-to-Image Generation","date":"2024-04-18","arxiv_id":"2404.11925","repositories_listed":0,"syntology":null},{"url":null,"slug":"privacy-preserving-ucb-decision-process","title":"Privacy-Preserving UCB Decision Process Verification via zk-SNARKs","date":"2024-04-18","arxiv_id":"2404.12186","repositories_listed":0,"syntology":null},{"url":null,"slug":"longvq-long-sequence-modeling-with-vector","title":"LongVQ: Long Sequence Modeling with Vector Quantization on Structured Memory","date":"2024-04-17","arxiv_id":"2404.11163","repositories_listed":0,"syntology":null},{"url":null,"slug":"neural-network-approach-for-non-markovian","title":"Neural Network Approach for Non-Markovian Dissipative Dynamics of Many-Body Open Quantum Systems","date":"2024-04-17","arxiv_id":"2404.11093","repositories_listed":0,"syntology":null},{"url":null,"slug":"qgen-on-the-ability-to-generalize-in","title":"QGen: On the Ability to Generalize in Quantization Aware Training","date":"2024-04-17","arxiv_id":"2404.11769","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":"efficient-and-accurate-neural-field","title":"Efficient and accurate neural field reconstruction using resistive memory","date":"2024-04-15","arxiv_id":"2404.09613","repositories_listed":0,"syntology":null},{"url":null,"slug":"quantization-of-large-language-models-with-an","title":"Quantization of Large Language Models with an Overdetermined Basis","date":"2024-04-15","arxiv_id":"2404.09737","repositories_listed":0,"syntology":null},{"url":null,"slug":"tmpq-dm-joint-timestep-reduction-and","title":"TMPQ-DM: Joint Timestep Reduction and Quantization Precision Selection for Efficient Diffusion Models","date":"2024-04-15","arxiv_id":"2404.09532","repositories_listed":0,"syntology":null},{"url":null,"slug":"bullion-a-column-store-for-machine-learning","title":"Bullion: A Column Store for Machine Learning","date":"2024-04-13","arxiv_id":"2404.08901","repositories_listed":0,"syntology":null},{"url":null,"slug":"full-duplex-beyond-self-interference-the","title":"Full-Duplex Beyond Self-Interference: The Unlimited Sensing Way","date":"2024-04-12","arxiv_id":"2404.08610","repositories_listed":0,"syntology":null},{"url":null,"slug":"lossy-image-compression-with-foundation","title":"Lossy Image Compression with Foundation Diffusion Models","date":"2024-04-12","arxiv_id":"2404.08580","repositories_listed":0,"syntology":null},{"url":null,"slug":"1-bit-quantized-on-chip-hybrid-diffraction","title":"1-bit Quantized On-chip Hybrid Diffraction Neural Network Enabled by Authentic All-optical Fully-connected Architecture","date":"2024-04-11","arxiv_id":"2404.07443","repositories_listed":0,"syntology":null},{"url":null,"slug":"edge-efficient-deep-learning-models-for","title":"Edge-Efficient Deep Learning Models for Automatic Modulation Classification: A Performance Analysis","date":"2024-04-11","arxiv_id":"2404.15343","repositories_listed":0,"syntology":null},{"url":null,"slug":"frame-quantization-of-neural-networks","title":"Frame Quantization of Neural Networks","date":"2024-04-11","arxiv_id":"2404.08131","repositories_listed":0,"syntology":null},{"url":null,"slug":"differentiable-search-for-finding-optimal","title":"Differentiable Search for Finding Optimal Quantization Strategy","date":"2024-04-10","arxiv_id":"2404.08010","repositories_listed":0,"syntology":null},{"url":null,"slug":"collaborative-edge-ai-inference-over-cloud","title":"Collaborative Edge AI Inference over Cloud-RAN","date":"2024-04-09","arxiv_id":"2404.06007","repositories_listed":0,"syntology":null},{"url":null,"slug":"encoder-quantization-motion-based-video","title":"Encoder-Quantization-Motion-based Video Quality Metrics","date":"2024-04-09","arxiv_id":"2404.06620","repositories_listed":0,"syntology":null}],"record_sha256":"68a2968c0e88a329130cf7b13c6fcca0425f8705aaa37c91520ebfe1b67728c0","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}