{"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/23","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":23,"pages_in_order":50,"rows_per_page":100,"rows":[2201,2300],"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/22","next":"/task/quantization/papers/24","papers":[{"url":null,"slug":"can-general-purpose-large-language-models","title":"Can General-Purpose Large Language Models Generalize to English-Thai Machine Translation ?","date":"2024-10-22","arxiv_id":"2410.17145","repositories_listed":0,"syntology":null},{"url":null,"slug":"pyramid-vector-quantization-for-llms","title":"Pyramid Vector Quantization for LLMs","date":"2024-10-22","arxiv_id":"2410.16926","repositories_listed":0,"syntology":null},{"url":null,"slug":"self-calibration-for-language-model","title":"Self-calibration for Language Model Quantization and Pruning","date":"2024-10-22","arxiv_id":"2410.17170","repositories_listed":0,"syntology":null},{"url":null,"slug":"continuous-speech-synthesis-using-per-token","title":"Continuous Speech Synthesis using per-token Latent Diffusion","date":"2024-10-21","arxiv_id":"2410.16048","repositories_listed":0,"syntology":null},{"url":null,"slug":"large-deviations-and-improved-mean-squared","title":"Large Deviation Upper Bounds and Improved MSE Rates of Nonlinear SGD: Heavy-tailed Noise and Power of Symmetry","date":"2024-10-21","arxiv_id":"2410.15637","repositories_listed":0,"syntology":null},{"url":null,"slug":"lscodec-low-bitrate-and-speaker-decoupled","title":"LSCodec: Low-Bitrate and Speaker-Decoupled Discrete Speech Codec","date":"2024-10-21","arxiv_id":"2410.15764","repositories_listed":0,"syntology":null},{"url":null,"slug":"solving-continual-offline-rl-through","title":"Solving Continual Offline RL through Selective Weights Activation on Aligned Spaces","date":"2024-10-21","arxiv_id":"2410.15698","repositories_listed":0,"syntology":null},{"url":null,"slug":"lossless-kv-cache-compression-to-2","title":"Lossless KV Cache Compression to 2%","date":"2024-10-20","arxiv_id":"2410.15252","repositories_listed":0,"syntology":null},{"url":null,"slug":"sdp4bit-toward-4-bit-communication","title":"SDP4Bit: Toward 4-bit Communication Quantization in Sharded Data Parallelism for LLM Training","date":"2024-10-20","arxiv_id":"2410.15526","repositories_listed":0,"syntology":null},{"url":null,"slug":"understanding-the-difficulty-of-low-precision","title":"Understanding the Difficulty of Low-Precision Post-Training Quantization for LLMs","date":"2024-10-18","arxiv_id":"2410.14570","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-unified-view-of-delta-parameter-editing-in","title":"A Unified View of Delta Parameter Editing in Post-Trained Large-Scale Models","date":"2024-10-17","arxiv_id":"2410.13841","repositories_listed":0,"syntology":null},{"url":null,"slug":"asymkv-enabling-1-bit-quantization-of-kv","title":"AsymKV: Enabling 1-Bit Quantization of KV Cache with Layer-Wise Asymmetric Quantization Configurations","date":"2024-10-17","arxiv_id":"2410.13212","repositories_listed":0,"syntology":null},{"url":null,"slug":"dart-disentanglement-of-accent-and-speaker","title":"DART: Disentanglement of Accent and Speaker Representation in Multispeaker Text-to-Speech","date":"2024-10-17","arxiv_id":"2410.13342","repositories_listed":0,"syntology":null},{"url":null,"slug":"harnessing-your-dram-and-ssd-for-sustainable","title":"Harnessing Your DRAM and SSD for Sustainable and Accessible LLM Inference with Mixed-Precision and Multi-level Caching","date":"2024-10-17","arxiv_id":"2410.14740","repositories_listed":0,"syntology":null},{"url":null,"slug":"nonlinear-stochastic-gradient-descent-and","title":"Nonlinear Stochastic Gradient Descent and Heavy-tailed Noise: A Unified Framework and High-probability Guarantees","date":"2024-10-17","arxiv_id":"2410.13954","repositories_listed":0,"syntology":null},{"url":null,"slug":"progressive-mixed-precision-decoding-for","title":"Progressive Mixed-Precision Decoding for Efficient LLM Inference","date":"2024-10-17","arxiv_id":"2410.13461","repositories_listed":0,"syntology":null},{"url":null,"slug":"channel-wise-mixed-precision-quantization-for","title":"Channel-Wise Mixed-Precision Quantization for Large Language Models","date":"2024-10-16","arxiv_id":"2410.13056","repositories_listed":0,"syntology":null},{"url":null,"slug":"comet-towards-partical-w4a4kv4-llms-serving","title":"COMET: Towards Partical W4A4KV4 LLMs Serving","date":"2024-10-16","arxiv_id":"2410.12168","repositories_listed":0,"syntology":null},{"url":null,"slug":"ervq-enhanced-residual-vector-quantization","title":"ERVQ: Enhanced Residual Vector Quantization with Intra-and-Inter-Codebook Optimization for Neural Audio Codecs","date":"2024-10-16","arxiv_id":"2410.12359","repositories_listed":0,"syntology":null},{"url":null,"slug":"qspec-speculative-decoding-with-complementary","title":"QSpec: Speculative Decoding with Complementary Quantization Schemes","date":"2024-10-15","arxiv_id":"2410.11305","repositories_listed":0,"syntology":null},{"url":null,"slug":"scaling-laws-for-post-training-quantized","title":"Scaling Laws for Post Training Quantized Large Language Models","date":"2024-10-15","arxiv_id":"2410.12119","repositories_listed":0,"syntology":null},{"url":null,"slug":"gaussian-mixture-vector-quantization-with","title":"Gaussian Mixture Vector Quantization with Aggregated Categorical Posterior","date":"2024-10-14","arxiv_id":"2410.10180","repositories_listed":0,"syntology":null},{"url":null,"slug":"real-time-stress-detection-via","title":"Real-Time Stress Detection via Photoplethysmogram Signals: Implementation of a Combined Continuous Wavelet Transform and Convolutional Neural Network on Resource-Constrained Microcontrollers","date":"2024-10-14","arxiv_id":"2410.19776","repositories_listed":0,"syntology":null},{"url":null,"slug":"slanc-static-layernorm-calibration","title":"SLaNC: Static LayerNorm Calibration","date":"2024-10-14","arxiv_id":"2410.10553","repositories_listed":0,"syntology":null},{"url":null,"slug":"gala-geometry-aware-local-adaptive-grids-for","title":"GALA: Geometry-Aware Local Adaptive Grids for Detailed 3D Generation","date":"2024-10-13","arxiv_id":"2410.10037","repositories_listed":0,"syntology":null},{"url":null,"slug":"gradient-free-neural-network-training-on-the","title":"Gradient-Free Neural Network Training on the Edge","date":"2024-10-13","arxiv_id":"2410.09734","repositories_listed":0,"syntology":null},{"url":null,"slug":"privquant-communication-efficient-private","title":"PrivQuant: Communication-Efficient Private Inference with Quantized Network/Protocol Co-Optimization","date":"2024-10-12","arxiv_id":"2410.09531","repositories_listed":0,"syntology":null},{"url":null,"slug":"deltadq-ultra-high-delta-compression-for-fine","title":"DeltaDQ: Ultra-High Delta Compression for Fine-Tuned LLMs via Group-wise Dropout and Separate Quantization","date":"2024-10-11","arxiv_id":"2410.08666","repositories_listed":0,"syntology":null},{"url":null,"slug":"zipvl-efficient-large-vision-language-models","title":"ZipVL: Efficient Large Vision-Language Models with Dynamic Token Sparsification","date":"2024-10-11","arxiv_id":"2410.08584","repositories_listed":0,"syntology":null},{"url":null,"slug":"crossquant-a-post-training-quantization","title":"CrossQuant: A Post-Training Quantization Method with Smaller Quantization Kernel for Precise Large Language Model Compression","date":"2024-10-10","arxiv_id":"2410.07505","repositories_listed":0,"syntology":null},{"url":null,"slug":"dart-denoising-autoregressive-transformer-for","title":"DART: Denoising Autoregressive Transformer for Scalable Text-to-Image Generation","date":"2024-10-10","arxiv_id":"2410.08159","repositories_listed":0,"syntology":null},{"url":null,"slug":"m-2-vit-accelerating-hybrid-vision","title":"M$^2$-ViT: Accelerating Hybrid Vision Transformers with Two-Level Mixed Quantization","date":"2024-10-10","arxiv_id":"2410.09113","repositories_listed":0,"syntology":null},{"url":null,"slug":"scalable-representation-learning-for","title":"Scalable Representation Learning for Multimodal Tabular Transactions","date":"2024-10-10","arxiv_id":"2410.07851","repositories_listed":0,"syntology":null},{"url":null,"slug":"quailora-quantization-aware-initialization","title":"QuAILoRA: Quantization-Aware Initialization for LoRA","date":"2024-10-09","arxiv_id":"2410.14713","repositories_listed":0,"syntology":null},{"url":null,"slug":"scaling-laws-for-mixed-quantization-in-large","title":"Scaling Laws for Mixed quantization in Large Language Models","date":"2024-10-09","arxiv_id":"2410.06722","repositories_listed":0,"syntology":null},{"url":null,"slug":"covering-numbers-for-deep-relu-networks-with","title":"Covering Numbers for Deep ReLU Networks with Applications to Function Approximation and Nonparametric Regression","date":"2024-10-08","arxiv_id":"2410.06378","repositories_listed":0,"syntology":null},{"url":null,"slug":"gesture2text-a-generalizable-decoder-for-word","title":"Gesture2Text: A Generalizable Decoder for Word-Gesture Keyboards in XR Through Trajectory Coarse Discretization and Pre-training","date":"2024-10-08","arxiv_id":"2410.18099","repositories_listed":0,"syntology":null},{"url":null,"slug":"qera-an-analytical-framework-for-quantization","title":"QERA: an Analytical Framework for Quantization Error Reconstruction","date":"2024-10-08","arxiv_id":"2410.06040","repositories_listed":0,"syntology":null},{"url":null,"slug":"variable-bitrate-residual-vector-quantization","title":"Variable Bitrate Residual Vector Quantization for Audio Coding","date":"2024-10-08","arxiv_id":"2410.06016","repositories_listed":0,"syntology":null},{"url":null,"slug":"designing-a-classifier-for-active-fire","title":"Designing a Classifier for Active Fire Detection from Multispectral Satellite Imagery Using Neural Architecture Search","date":"2024-10-07","arxiv_id":"2410.05425","repositories_listed":0,"syntology":null},{"url":null,"slug":"variable-resolution-pixel-quantization-for","title":"Variable Resolution Pixel Quantization for Low Power Machine Vision Application on Edge","date":"2024-10-07","arxiv_id":"2410.05189","repositories_listed":0,"syntology":null},{"url":null,"slug":"continuous-approximations-for-improving","title":"Continuous Approximations for Improving Quantization Aware Training of LLMs","date":"2024-10-06","arxiv_id":"2410.10849","repositories_listed":0,"syntology":null},{"url":null,"slug":"hall-e-hierarchical-neural-codec-language","title":"HALL-E: Hierarchical Neural Codec Language Model for Minute-Long Zero-Shot Text-to-Speech Synthesis","date":"2024-10-06","arxiv_id":"2410.04380","repositories_listed":0,"syntology":null},{"url":null,"slug":"palmbench-a-comprehensive-benchmark-of","title":"PalmBench: A Comprehensive Benchmark of Compressed Large Language Models on Mobile Platforms","date":"2024-10-05","arxiv_id":"2410.05315","repositories_listed":0,"syntology":null},{"url":null,"slug":"generative-semantic-communication-for-text-to","title":"Generative Semantic Communication for Text-to-Speech Synthesis","date":"2024-10-04","arxiv_id":"2410.03459","repositories_listed":0,"syntology":null},{"url":null,"slug":"mimo-detection-with-spatial-sigma-delta-adcs","title":"MIMO Detection with Spatial Sigma-Delta ADCs: A Variational Bayesian Approach","date":"2024-10-04","arxiv_id":"2410.03891","repositories_listed":0,"syntology":null},{"url":null,"slug":"resource-aware-mixed-precision-quantization","title":"Resource-aware Mixed-precision Quantization for Enhancing Deployability of Transformers for Time-series Forecasting on Embedded FPGAs","date":"2024-10-04","arxiv_id":"2410.03294","repositories_listed":0,"syntology":null},{"url":null,"slug":"overcoming-representation-bias-in-fairness","title":"Overcoming Representation Bias in Fairness-Aware data Repair using Optimal Transport","date":"2024-10-03","arxiv_id":"2410.02840","repositories_listed":0,"syntology":null},{"url":null,"slug":"remember-and-recall-associative-memory-based","title":"Remember and Recall: Associative-Memory-based Trajectory Prediction","date":"2024-10-03","arxiv_id":"2410.02201","repositories_listed":0,"syntology":null},{"url":null,"slug":"seal-semantic-augmented-imitation-learning","title":"SEAL: SEmantic-Augmented Imitation Learning via Language Model","date":"2024-10-03","arxiv_id":"2410.02231","repositories_listed":0,"syntology":null},{"url":null,"slug":"getting-free-bits-back-from-rotational","title":"Getting Free Bits Back from Rotational Symmetries in LLMs","date":"2024-10-02","arxiv_id":"2410.01309","repositories_listed":0,"syntology":null},{"url":null,"slug":"restorative-speech-enhancement-a-progressive","title":"Restorative Speech Enhancement: A Progressive Approach Using SE and Codec Modules","date":"2024-10-02","arxiv_id":"2410.01150","repositories_listed":0,"syntology":null},{"url":null,"slug":"compressing-recurrent-neural-networks-for","title":"Compressing Recurrent Neural Networks for FPGA-accelerated Implementation in Fluorescence Lifetime Imaging","date":"2024-10-01","arxiv_id":"2410.00948","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-activity-propagation-via-weight","title":"Deep activity propagation via weight initialization in spiking neural networks","date":"2024-10-01","arxiv_id":"2410.00580","repositories_listed":0,"syntology":null},{"url":null,"slug":"stanh-parametric-quantization-for-variable","title":"STanH : Parametric Quantization for Variable Rate Learned Image Compression","date":"2024-10-01","arxiv_id":"2410.00557","repositories_listed":0,"syntology":null},{"url":null,"slug":"aggressive-post-training-compression-on","title":"Aggressive Post-Training Compression on Extremely Large Language Models","date":"2024-09-30","arxiv_id":"2409.20094","repositories_listed":0,"syntology":null},{"url":null,"slug":"constraint-guided-model-quantization-of","title":"Constraint Guided Model Quantization of Neural Networks","date":"2024-09-30","arxiv_id":"2409.20138","repositories_listed":0,"syntology":null},{"url":null,"slug":"mixed-precision-embeddings-for-large-scale","title":"Mixed-Precision Embeddings for Large-Scale Recommendation Models","date":"2024-09-30","arxiv_id":"2409.20305","repositories_listed":0,"syntology":null},{"url":null,"slug":"quantized-and-asynchronous-federated-learning","title":"Quantized and Asynchronous Federated Learning","date":"2024-09-30","arxiv_id":"2410.00242","repositories_listed":0,"syntology":null},{"url":null,"slug":"rotated-runtime-smooth-training-free","title":"Rotated Runtime Smooth: Training-Free Activation Smoother for accurate INT4 inference","date":"2024-09-30","arxiv_id":"2409.20361","repositories_listed":0,"syntology":null},{"url":null,"slug":"infantcrynet-a-data-driven-framework-for","title":"InfantCryNet: A Data-driven Framework for Intelligent Analysis of Infant Cries","date":"2024-09-29","arxiv_id":"2409.19689","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-method-of-using-rsvd-in-residual","title":"A method of using RSVD in residual calculation of LowBit GEMM","date":"2024-09-27","arxiv_id":"2409.18772","repositories_listed":0,"syntology":null},{"url":null,"slug":"asymptotic-tracking-control-of-dynamic","title":"Asymptotic tracking control of dynamic reference over homomorphically encrypted data with finite modulus","date":"2024-09-27","arxiv_id":"2409.18787","repositories_listed":0,"syntology":null},{"url":null,"slug":"heterogeneous-quantization-regularizes","title":"Heterogeneous quantization regularizes spiking neural network activity","date":"2024-09-27","arxiv_id":"2409.18396","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-arbitrary-precision-acceleration","title":"Efficient Arbitrary Precision Acceleration for Large Language Models on GPU Tensor Cores","date":"2024-09-26","arxiv_id":"2409.17870","repositories_listed":0,"syntology":null},{"url":null,"slug":"fronthaul-constrained-distributed-radar","title":"Fronthaul-Constrained Distributed Radar Sensing","date":"2024-09-26","arxiv_id":"2409.17753","repositories_listed":0,"syntology":null},{"url":null,"slug":"mogents-motion-generation-based-on-spatial","title":"MoGenTS: Motion Generation based on Spatial-Temporal Joint Modeling","date":"2024-09-26","arxiv_id":"2409.17686","repositories_listed":0,"syntology":null},{"url":null,"slug":"p4q-learning-to-prompt-for-quantization-in","title":"P4Q: Learning to Prompt for Quantization in Visual-language Models","date":"2024-09-26","arxiv_id":"2409.17634","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-survey-of-low-bit-large-language-models","title":"A Survey of Low-bit Large Language Models: Basics, Systems, and Algorithms","date":"2024-09-25","arxiv_id":"2409.16694","repositories_listed":0,"syntology":null},{"url":null,"slug":"accumulator-aware-post-training-quantization","title":"Accumulator-Aware Post-Training Quantization","date":"2024-09-25","arxiv_id":"2409.17092","repositories_listed":0,"syntology":null},{"url":null,"slug":"llama-sciq-an-educational-chatbot-for","title":"LLaMa-SciQ: An Educational Chatbot for Answering Science MCQ","date":"2024-09-25","arxiv_id":"2409.16779","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-for-finite-space-mean","title":"Reinforcement Learning for Finite Space Mean-Field Type Games","date":"2024-09-25","arxiv_id":"2409.18152","repositories_listed":0,"syntology":null},{"url":null,"slug":"using-random-codebooks-for-audio-neural","title":"Using Random Codebooks for Audio Neural AutoEncoders","date":"2024-09-25","arxiv_id":"2409.16677","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-formalization-of-image-vectorization-by","title":"A Formalization of Image Vectorization by Region Merging","date":"2024-09-24","arxiv_id":"2409.15940","repositories_listed":0,"syntology":null},{"url":null,"slug":"communication-and-energy-efficient-federated","title":"Communication and Energy Efficient Federated Learning using Zero-Order Optimization Technique","date":"2024-09-24","arxiv_id":"2409.16456","repositories_listed":0,"syntology":null},{"url":null,"slug":"twin-network-augmentation-a-novel-training","title":"Twin Network Augmentation: A Novel Training Strategy for Improved Spiking Neural Networks and Efficient Weight Quantization","date":"2024-09-24","arxiv_id":"2409.15849","repositories_listed":0,"syntology":null},{"url":null,"slug":"ultra-low-latency-quantum-inspired-machine","title":"Ultra-low latency quantum-inspired machine learning predictors implemented on FPGA","date":"2024-09-24","arxiv_id":"2409.16075","repositories_listed":0,"syntology":null},{"url":null,"slug":"dilatequant-accurate-and-efficient-diffusion","title":"DilateQuant: Accurate and Efficient Diffusion Quantization via Weight Dilation","date":"2024-09-22","arxiv_id":"2409.14307","repositories_listed":0,"syntology":null},{"url":null,"slug":"spaq-dl-slam-towards-optimizing-deep-learning","title":"SPAQ-DL-SLAM: Towards Optimizing Deep Learning-based SLAM for Resource-Constrained Embedded Platforms","date":"2024-09-22","arxiv_id":"2409.14515","repositories_listed":0,"syntology":null},{"url":null,"slug":"corbin-fl-a-differentially-private-federated","title":"CorBin-FL: A Differentially Private Federated Learning Mechanism using Common Randomness","date":"2024-09-20","arxiv_id":"2409.13133","repositories_listed":0,"syntology":null},{"url":null,"slug":"ptq4adm-post-training-quantization-for","title":"PTQ4ADM: Post-Training Quantization for Efficient Text Conditional Audio Diffusion Models","date":"2024-09-20","arxiv_id":"2409.13894","repositories_listed":0,"syntology":null},{"url":null,"slug":"reduced-bit-median-quantization-a-middle","title":"Reduced bit median quantization: A middle process for Efficient Image Compression","date":"2024-09-20","arxiv_id":"2409.13789","repositories_listed":0,"syntology":null},{"url":null,"slug":"talkmosaic-interactive-photomosaic-with-multi","title":"TalkMosaic: Interactive PhotoMosaic with Multi-modal LLM Q&A Interactions","date":"2024-09-20","arxiv_id":"2409.13941","repositories_listed":0,"syntology":null},{"url":null,"slug":"impact-of-ml-optimization-tactics-on-greener","title":"Impact of ML Optimization Tactics on Greener Pre-Trained ML Models","date":"2024-09-19","arxiv_id":"2409.12878","repositories_listed":0,"syntology":null},{"url":null,"slug":"ndvq-robust-neural-audio-codec-with-normal","title":"NDVQ: Robust Neural Audio Codec with Normal Distribution-Based Vector Quantization","date":"2024-09-19","arxiv_id":"2409.12717","repositories_listed":0,"syntology":null},{"url":null,"slug":"scaling-fp8-training-to-trillion-token-llms","title":"Scaling FP8 training to trillion-token LLMs","date":"2024-09-19","arxiv_id":"2409.12517","repositories_listed":0,"syntology":null},{"url":null,"slug":"art-and-science-of-quantizing-large-scale","title":"Art and Science of Quantizing Large-Scale Models: A Comprehensive Overview","date":"2024-09-18","arxiv_id":"2409.11650","repositories_listed":0,"syntology":null},{"url":null,"slug":"low-frame-rate-speech-codec-a-codec-designed","title":"Low Frame-rate Speech Codec: a Codec Designed for Fast High-quality Speech LLM Training and Inference","date":"2024-09-18","arxiv_id":"2409.12117","repositories_listed":0,"syntology":null},{"url":null,"slug":"pareto-data-framework-steps-towards-resource","title":"Pareto Data Framework: Steps Towards Resource-Efficient Decision Making Using Minimum Viable Data (MVD)","date":"2024-09-18","arxiv_id":"2409.12112","repositories_listed":0,"syntology":null},{"url":null,"slug":"forearm-ultrasound-based-gesture-recognition","title":"Forearm Ultrasound based Gesture Recognition on Edge","date":"2024-09-16","arxiv_id":"2409.09915","repositories_listed":0,"syntology":null},{"url":null,"slug":"lasers-latent-space-encoding-for","title":"LASERS: LAtent Space Encoding for Representations with Sparsity for Generative Modeling","date":"2024-09-16","arxiv_id":"2409.11184","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-statistical-significance-in-human","title":"Improving Statistical Significance in Human Evaluation of Automatic Metrics via Soft Pairwise Accuracy","date":"2024-09-15","arxiv_id":"2409.09598","repositories_listed":0,"syntology":null},{"url":null,"slug":"language-models-and-retrieval-augmented","title":"Language Models and Retrieval Augmented Generation for Automated Structured Data Extraction from Diagnostic Reports","date":"2024-09-15","arxiv_id":"2409.10576","repositories_listed":0,"syntology":null},{"url":null,"slug":"mesongs-post-training-compression-of-3d","title":"MesonGS: Post-training Compression of 3D Gaussians via Efficient Attribute Transformation","date":"2024-09-15","arxiv_id":"2409.09756","repositories_listed":0,"syntology":null},{"url":null,"slug":"privacy-preserving-sam-quantization-for","title":"Privacy-Preserving SAM Quantization for Efficient Edge Intelligence in Healthcare","date":"2024-09-14","arxiv_id":"2410.01813","repositories_listed":0,"syntology":null},{"url":null,"slug":"robust-training-of-neural-networks-at","title":"Robust Training of Neural Networks at Arbitrary Precision and Sparsity","date":"2024-09-14","arxiv_id":"2409.09245","repositories_listed":0,"syntology":null},{"url":null,"slug":"investigating-disentanglement-in-a-phoneme","title":"Investigating Disentanglement in a Phoneme-level Speech Codec for Prosody Modeling","date":"2024-09-13","arxiv_id":"2409.08664","repositories_listed":0,"syntology":null},{"url":null,"slug":"dequantization-of-a-signal-from-two-parallel","title":"Dequantization of a signal from two parallel quantized observations","date":"2024-09-12","arxiv_id":"2409.08071","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-and-reliable-vector-similarity","title":"Efficient and Reliable Vector Similarity Search Using Asymmetric Encoding with NAND-Flash for Many-Class Few-Shot Learning","date":"2024-09-12","arxiv_id":"2409.07832","repositories_listed":0,"syntology":null},{"url":null,"slug":"distributed-convolutional-neural-network","title":"Distributed Convolutional Neural Network Training on Mobile and Edge Clusters","date":"2024-09-11","arxiv_id":"2409.09083","repositories_listed":0,"syntology":null}],"record_sha256":"6bb8099039417653a71f5a30274f47fbcd54039e778abbbd4317517a36e04d48","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}