{"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/31","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":31,"pages_in_order":50,"rows_per_page":100,"rows":[3001,3100],"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/30","next":"/task/quantization/papers/32","papers":[{"url":null,"slug":"augmenting-hessians-with-inter-layer","title":"Augmenting Hessians with Inter-Layer Dependencies for Mixed-Precision Post-Training Quantization","date":"2023-06-08","arxiv_id":"2306.04879","repositories_listed":0,"syntology":null},{"url":null,"slug":"iterative-signal-processing-for-integrated","title":"Iterative Signal Processing for Integrated Sensing and Communication Systems","date":"2023-06-08","arxiv_id":"2306.05235","repositories_listed":0,"syntology":null},{"url":null,"slug":"sensitivity-aware-finetuning-for-accuracy","title":"Sensitivity-Aware Finetuning for Accuracy Recovery on Deep Learning Hardware","date":"2023-06-05","arxiv_id":"2306.03076","repositories_listed":0,"syntology":null},{"url":null,"slug":"modular-transformers-compressing-transformers","title":"Modular Transformers: Compressing Transformers into Modularized Layers for Flexible Efficient Inference","date":"2023-06-04","arxiv_id":"2306.02379","repositories_listed":0,"syntology":null},{"url":null,"slug":"temporal-dynamic-quantization-for-diffusion","title":"Temporal Dynamic Quantization for Diffusion Models","date":"2023-06-04","arxiv_id":"2306.02316","repositories_listed":0,"syntology":null},{"url":null,"slug":"dynamic-quantized-consensus-under-dos-attacks","title":"Dynamic quantized consensus under DoS attacks: Towards a tight zooming-out factor","date":"2023-06-01","arxiv_id":"2306.00279","repositories_listed":0,"syntology":null},{"url":null,"slug":"flexround-learnable-rounding-based-on-element","title":"FlexRound: Learnable Rounding based on Element-wise Division for Post-Training Quantization","date":"2023-06-01","arxiv_id":"2306.00317","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-the-effectiveness-of-hybrid-mutual","title":"On the Effectiveness of Hybrid Mutual Information Estimation","date":"2023-06-01","arxiv_id":"2306.00608","repositories_listed":0,"syntology":null},{"url":null,"slug":"quantization-aware-and-tensor-compressed","title":"Quantization-Aware and Tensor-Compressed Training of Transformers for Natural Language Understanding","date":"2023-06-01","arxiv_id":"2306.01076","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-learning-discrete-representations-via","title":"Towards Learning Discrete Representations via Self-Supervision for Wearables-Based Human Activity Recognition","date":"2023-06-01","arxiv_id":"2306.01108","repositories_listed":0,"syntology":null},{"url":null,"slug":"asymptotic-performance-analysis-of-large","title":"Asymptotic Performance Analysis of Large-Scale Active IRS-Aided Wireless Network","date":"2023-05-31","arxiv_id":"2305.19931","repositories_listed":0,"syntology":null},{"url":null,"slug":"implementation-of-a-framework-for-deploying","title":"Implementation of a framework for deploying AI inference engines in FPGAs","date":"2023-05-30","arxiv_id":"2305.19455","repositories_listed":0,"syntology":null},{"url":null,"slug":"intriguing-properties-of-quantization-at","title":"Intriguing Properties of Quantization at Scale","date":"2023-05-30","arxiv_id":"2305.19268","repositories_listed":0,"syntology":null},{"url":null,"slug":"low-precision-quantization-aware-training-in","title":"Low Precision Quantization-aware Training in Spiking Neural Networks with Differentiable Quantization Function","date":"2023-05-30","arxiv_id":"2305.19295","repositories_listed":0,"syntology":null},{"url":null,"slug":"prequant-a-task-agnostic-quantization","title":"PreQuant: A Task-agnostic Quantization Approach for Pre-trained Language Models","date":"2023-05-30","arxiv_id":"2306.00014","repositories_listed":0,"syntology":null},{"url":null,"slug":"stochastic-gradient-langevin-dynamics-based","title":"Stochastic Gradient Langevin Dynamics Based on Quantization with Increasing Resolution","date":"2023-05-30","arxiv_id":"2305.18864","repositories_listed":0,"syntology":null},{"url":null,"slug":"bright-bi-level-feature-representation-of","title":"BRICS: Bi-level feature Representation of Image CollectionS","date":"2023-05-29","arxiv_id":"2305.18601","repositories_listed":0,"syntology":null},{"url":null,"slug":"decor-defy-knowledge-forgetting-by-predicting","title":"DeCoR: Defy Knowledge Forgetting by Predicting Earlier Audio Codes","date":"2023-05-29","arxiv_id":"2305.18441","repositories_listed":0,"syntology":null},{"url":null,"slug":"global-qsgd-practical-floatless-quantization","title":"Global-QSGD: Practical Floatless Quantization for Distributed Learning with Theoretical Guarantees","date":"2023-05-29","arxiv_id":"2305.18627","repositories_listed":0,"syntology":null},{"url":null,"slug":"reducing-communication-for-split-learning-by","title":"Reducing Communication for Split Learning by Randomized Top-k Sparsification","date":"2023-05-29","arxiv_id":"2305.18469","repositories_listed":0,"syntology":null},{"url":null,"slug":"reversible-deep-neural-network-watermarking","title":"Reversible Quantization Index Modulation for Static Deep Neural Network Watermarking","date":"2023-05-29","arxiv_id":"2305.17879","repositories_listed":0,"syntology":null},{"url":null,"slug":"slimfit-memory-efficient-fine-tuning-of","title":"SlimFit: Memory-Efficient Fine-Tuning of Transformer-based Models Using Training Dynamics","date":"2023-05-29","arxiv_id":"2305.18513","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-storage-of-fine-tuned-models-via","title":"Efficient Storage of Fine-Tuned Models via Low-Rank Approximation of Weight Residuals","date":"2023-05-28","arxiv_id":"2305.18425","repositories_listed":0,"syntology":null},{"url":null,"slug":"examining-the-role-and-limits-of-batchnorm","title":"Examining the Role and Limits of Batchnorm Optimization to Mitigate Diverse Hardware-noise in In-memory Computing","date":"2023-05-28","arxiv_id":"2305.18416","repositories_listed":0,"syntology":null},{"url":null,"slug":"2-bit-conformer-quantization-for-automatic","title":"2-bit Conformer quantization for automatic speech recognition","date":"2023-05-26","arxiv_id":"2305.16619","repositories_listed":0,"syntology":null},{"url":null,"slug":"binaryvit-towards-efficient-and-accurate","title":"BinaryViT: Towards Efficient and Accurate Binary Vision Transformers","date":"2023-05-24","arxiv_id":"2305.14730","repositories_listed":0,"syntology":null},{"url":null,"slug":"large-language-model-distillation-doesn-t","title":"Just CHOP: Embarrassingly Simple LLM Compression","date":"2023-05-24","arxiv_id":"2305.14864","repositories_listed":0,"syntology":null},{"url":null,"slug":"rand-robustness-aware-norm-decay-for","title":"RAND: Robustness Aware Norm Decay For Quantized Seq2seq Models","date":"2023-05-24","arxiv_id":"2305.15536","repositories_listed":0,"syntology":null},{"url":null,"slug":"adversarial-defenses-via-vector-quantization","title":"Adversarial Defenses via Vector Quantization","date":"2023-05-23","arxiv_id":"2305.13651","repositories_listed":0,"syntology":null},{"url":null,"slug":"augmented-random-search-for-multi-objective","title":"Combining Multi-Objective Bayesian Optimization with Reinforcement Learning for TinyML","date":"2023-05-23","arxiv_id":"2305.14109","repositories_listed":0,"syntology":null},{"url":null,"slug":"downlink-clustering-based-scheduling-of-irs","title":"Downlink Clustering-Based Scheduling of IRS-Assisted Communications With Reconfiguration Constraints","date":"2023-05-23","arxiv_id":"2305.14051","repositories_listed":0,"syntology":null},{"url":null,"slug":"memory-efficient-fine-tuning-of-compressed","title":"Memory-Efficient Fine-Tuning of Compressed Large Language Models via sub-4-bit Integer Quantization","date":"2023-05-23","arxiv_id":"2305.14152","repositories_listed":0,"syntology":null},{"url":null,"slug":"differential-privacy-with-random-projections","title":"Differential Privacy with Random Projections and Sign Random Projections","date":"2023-05-22","arxiv_id":"2306.01751","repositories_listed":0,"syntology":null},{"url":null,"slug":"joint-device-edge-digital-semantic","title":"Digital-SC: Digital Semantic Communication with Adaptive Network Split and Learned Non-Linear Quantization","date":"2023-05-22","arxiv_id":"2305.13553","repositories_listed":0,"syntology":null},{"url":null,"slug":"revisiting-data-augmentation-in-model","title":"Revisiting Data Augmentation in Model Compression: An Empirical and Comprehensive Study","date":"2023-05-22","arxiv_id":"2305.13232","repositories_listed":0,"syntology":null},{"url":null,"slug":"tinyissimoyolo-a-quantized-low-memory","title":"TinyissimoYOLO: A Quantized, Low-Memory Footprint, TinyML Object Detection Network for Low Power Microcontrollers","date":"2023-05-22","arxiv_id":"2306.00001","repositories_listed":0,"syntology":null},{"url":null,"slug":"tsptq-vit-two-scaled-post-training","title":"TSPTQ-ViT: Two-scaled post-training quantization for vision transformer","date":"2023-05-22","arxiv_id":"2305.12901","repositories_listed":0,"syntology":null},{"url":null,"slug":"atomic-anatomy-of-low-inertia-power-systems","title":"Atomic Anatomy of Low-Inertia Power Systems","date":"2023-05-21","arxiv_id":"2305.12574","repositories_listed":0,"syntology":null},{"url":null,"slug":"bi-vit-pushing-the-limit-of-vision","title":"Bi-ViT: Pushing the Limit of Vision Transformer Quantization","date":"2023-05-21","arxiv_id":"2305.12354","repositories_listed":0,"syntology":null},{"url":null,"slug":"faq-mitigating-the-impact-of-faults-in-the","title":"FAQ: Mitigating the Impact of Faults in the Weight Memory of DNN Accelerators through Fault-Aware Quantization","date":"2023-05-21","arxiv_id":"2305.12590","repositories_listed":0,"syntology":null},{"url":null,"slug":"integer-or-floating-point-new-outlooks-for","title":"Integer or Floating Point? New Outlooks for Low-Bit Quantization on Large Language Models","date":"2023-05-21","arxiv_id":"2305.12356","repositories_listed":0,"syntology":null},{"url":null,"slug":"stoat-structured-data-to-analytical-text-with","title":"ReTAG: Reasoning Aware Table to Analytic Text Generation","date":"2023-05-19","arxiv_id":"2305.11826","repositories_listed":0,"syntology":null},{"url":null,"slug":"two-bit-ris-aided-communications-at-3-5ghz","title":"Two-Bit RIS-Aided Communications at 3.5GHz: Some Insights from the Measurement Results Under Multiple Practical Scenes","date":"2023-05-19","arxiv_id":"2305.11614","repositories_listed":0,"syntology":null},{"url":null,"slug":"boost-vision-transformer-with-gpu-friendly-1","title":"Boost Vision Transformer with GPU-Friendly Sparsity and Quantization","date":"2023-05-18","arxiv_id":"2305.10727","repositories_listed":0,"syntology":null},{"url":null,"slug":"q-shed-distributed-optimization-at-the-edge","title":"Q-SHED: Distributed Optimization at the Edge via Hessian Eigenvectors Quantization","date":"2023-05-18","arxiv_id":"2305.10852","repositories_listed":0,"syntology":null},{"url":null,"slug":"whisper-kdq-a-lightweight-whisper-via-guided","title":"DQ-Whisper: Joint Distillation and Quantization for Efficient Multilingual Speech Recognition","date":"2023-05-18","arxiv_id":"2305.10788","repositories_listed":0,"syntology":null},{"url":null,"slug":"compress-then-prompt-improving-accuracy","title":"Compress, Then Prompt: Improving Accuracy-Efficiency Trade-off of LLM Inference with Transferable Prompt","date":"2023-05-17","arxiv_id":"2305.11186","repositories_listed":0,"syntology":null},{"url":null,"slug":"component-training-of-turbo-autoencoders","title":"Component Training of Turbo Autoencoders","date":"2023-05-16","arxiv_id":"2305.09216","repositories_listed":0,"syntology":null},{"url":null,"slug":"designing-discontinuities","title":"Designing Discontinuities","date":"2023-05-15","arxiv_id":"2305.08559","repositories_listed":0,"syntology":null},{"url":null,"slug":"fast-inference-of-tree-ensembles-on-arm","title":"Fast Inference of Tree Ensembles on ARM Devices","date":"2023-05-15","arxiv_id":"2305.08579","repositories_listed":0,"syntology":null},{"url":null,"slug":"straightening-out-the-straight-through","title":"Straightening Out the Straight-Through Estimator: Overcoming Optimization Challenges in Vector Quantized Networks","date":"2023-05-15","arxiv_id":"2305.08842","repositories_listed":0,"syntology":null},{"url":null,"slug":"task-oriented-communication-design-at-scale","title":"Task-Oriented Communication Design at Scale","date":"2023-05-15","arxiv_id":"2305.08481","repositories_listed":0,"syntology":null},{"url":null,"slug":"analyzing-compression-techniques-for-computer","title":"Analyzing Compression Techniques for Computer Vision","date":"2023-05-14","arxiv_id":"2305.08075","repositories_listed":0,"syntology":null},{"url":null,"slug":"federated-td-learning-over-finite-rate","title":"Federated TD Learning over Finite-Rate Erasure Channels: Linear Speedup under Markovian Sampling","date":"2023-05-14","arxiv_id":"2305.08104","repositories_listed":0,"syntology":null},{"url":null,"slug":"accelerator-aware-training-for-transducer","title":"Accelerator-Aware Training for Transducer-Based Speech Recognition","date":"2023-05-12","arxiv_id":"2305.07778","repositories_listed":0,"syntology":null},{"url":null,"slug":"patch-wise-mixed-precision-quantization-of","title":"Patch-wise Mixed-Precision Quantization of Vision Transformer","date":"2023-05-11","arxiv_id":"2305.06559","repositories_listed":0,"syntology":null},{"url":null,"slug":"speaker-diaphragm-excursion-prediction-deep","title":"Speaker Diaphragm Excursion Prediction: deep attention and online adaptation","date":"2023-05-11","arxiv_id":"2305.06640","repositories_listed":0,"syntology":null},{"url":null,"slug":"mobile-image-restoration-via-prior","title":"Mobile Image Restoration via Prior Quantization","date":"2023-05-10","arxiv_id":"2305.05899","repositories_listed":0,"syntology":null},{"url":null,"slug":"multiscale-augmented-normalizing-flows-for","title":"Multiscale Augmented Normalizing Flows for Image Compression","date":"2023-05-09","arxiv_id":"2305.05451","repositories_listed":0,"syntology":null},{"url":null,"slug":"snt-sharpness-minimizing-network","title":"CrAFT: Compression-Aware Fine-Tuning for Efficient Visual Task Adaptation","date":"2023-05-08","arxiv_id":"2305.04526","repositories_listed":0,"syntology":null},{"url":null,"slug":"structural-and-statistical-texture-knowledge-1","title":"Structural and Statistical Texture Knowledge Distillation for Semantic Segmentation","date":"2023-05-06","arxiv_id":"2305.03944","repositories_listed":0,"syntology":null},{"url":null,"slug":"emulation-learning-for-neuromimetic-systems","title":"Emulation Learning for Neuromimetic Systems","date":"2023-05-04","arxiv_id":"2305.03196","repositories_listed":0,"syntology":null},{"url":null,"slug":"vertical-federated-learning-over-cloud-ran","title":"Vertical Federated Learning over Cloud-RAN: Convergence Analysis and System Optimization","date":"2023-05-04","arxiv_id":"2305.06279","repositories_listed":0,"syntology":null},{"url":null,"slug":"hybrid-model-for-single-stage-multi-person","title":"Hybrid model for Single-Stage Multi-Person Pose Estimation","date":"2023-05-02","arxiv_id":"2305.01167","repositories_listed":0,"syntology":null},{"url":null,"slug":"icq-a-quantization-scheme-for-best-arm","title":"ICQ: A Quantization Scheme for Best-Arm Identification Over Bit-Constrained Channels","date":"2023-04-30","arxiv_id":"2305.00528","repositories_listed":0,"syntology":null},{"url":null,"slug":"guaranteed-quantization-error-computation-for","title":"Guaranteed Quantization Error Computation for Neural Network Model Compression","date":"2023-04-26","arxiv_id":"2304.13812","repositories_listed":0,"syntology":null},{"url":null,"slug":"killing-two-birds-with-one-stone-quantization","title":"Killing Two Birds with One Stone: Quantization Achieves Privacy in Distributed Learning","date":"2023-04-26","arxiv_id":"2304.13545","repositories_listed":0,"syntology":null},{"url":null,"slug":"membrane-potential-distribution-adjustment","title":"Membrane Potential Distribution Adjustment and Parametric Surrogate Gradient in Spiking Neural Networks","date":"2023-04-26","arxiv_id":"2304.13289","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-robustness-against-adversarial","title":"Improving Robustness Against Adversarial Attacks with Deeply Quantized Neural Networks","date":"2023-04-25","arxiv_id":"2304.12829","repositories_listed":0,"syntology":null},{"url":null,"slug":"speed-is-all-you-need-on-device-acceleration","title":"Speed Is All You Need: On-Device Acceleration of Large Diffusion Models via GPU-Aware Optimizations","date":"2023-04-21","arxiv_id":"2304.11267","repositories_listed":0,"syntology":null},{"url":null,"slug":"transformer-based-models-and-hardware","title":"Transformer-based models and hardware acceleration analysis in autonomous driving: A survey","date":"2023-04-21","arxiv_id":"2304.10891","repositories_listed":0,"syntology":null},{"url":null,"slug":"post-training-quantization-for-object","title":"Improving Post-Training Quantization on Object Detection with Task Loss-Guided Lp Metric","date":"2023-04-19","arxiv_id":"2304.09785","repositories_listed":0,"syntology":null},{"url":null,"slug":"deepgemm-accelerated-ultra-low-precision","title":"DeepGEMM: Accelerated Ultra Low-Precision Inference on CPU Architectures using Lookup Tables","date":"2023-04-18","arxiv_id":"2304.09049","repositories_listed":0,"syntology":null},{"url":null,"slug":"atheena-a-toolflow-for-hardware-early-exit","title":"ATHEENA: A Toolflow for Hardware Early-Exit Network Automation","date":"2023-04-17","arxiv_id":"2304.08400","repositories_listed":0,"syntology":null},{"url":null,"slug":"soft-label-coding-for-end-to-end-sound-source","title":"Soft Label Coding for End-to-end Sound Source Localization With Ad-hoc Microphone Arrays","date":"2023-04-15","arxiv_id":"2304.07512","repositories_listed":0,"syntology":null},{"url":null,"slug":"convergence-rate-of-tsallis-entropic","title":"Convergence rate of Tsallis entropic regularized optimal transport","date":"2023-04-13","arxiv_id":"2304.06616","repositories_listed":0,"syntology":null},{"url":null,"slug":"d-svm-over-networked-systems-with-non-ideal","title":"D-SVM over Networked Systems with Non-Ideal Linking Conditions","date":"2023-04-13","arxiv_id":"2304.06667","repositories_listed":0,"syntology":null},{"url":null,"slug":"end-to-end-codesign-of-hessian-aware","title":"End-to-end codesign of Hessian-aware quantized neural networks for FPGAs and ASICs","date":"2023-04-13","arxiv_id":"2304.06745","repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-multi-criteria-adversarial","title":"Unsupervised Multi-Criteria Adversarial Detection in Deep Image Retrieval","date":"2023-04-09","arxiv_id":"2304.04228","repositories_listed":0,"syntology":null},{"url":null,"slug":"benchmarking-the-robustness-of-quantized","title":"Benchmarking the Robustness of Quantized Models","date":"2023-04-08","arxiv_id":"2304.03968","repositories_listed":0,"syntology":null},{"url":null,"slug":"autoqnn-an-end-to-end-framework-for","title":"AutoQNN: An End-to-End Framework for Automatically Quantizing Neural Networks","date":"2023-04-07","arxiv_id":"2304.03782","repositories_listed":0,"syntology":null},{"url":null,"slug":"feddisc-a-computation-efficient-federated","title":"FedDiSC: A Computation-efficient Federated Learning Framework for Power Systems Disturbance and Cyber Attack Discrimination","date":"2023-04-07","arxiv_id":"2304.03640","repositories_listed":0,"syntology":null},{"url":null,"slug":"blockwise-compression-of-transformer-based","title":"Blockwise Compression of Transformer-based Models without Retraining","date":"2023-04-04","arxiv_id":"2304.01483","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-unified-compression-framework-for-efficient","title":"A Unified Compression Framework for Efficient Speech-Driven Talking-Face Generation","date":"2023-04-02","arxiv_id":"2304.00471","repositories_listed":0,"syntology":null},{"url":null,"slug":"distributed-optimization-for-quadratic-cost","title":"Distributed Optimization for Quadratic Cost Functions over Large-Scale Networks with Quantized Communication and Finite-Time Convergence","date":"2023-04-02","arxiv_id":"2304.00596","repositories_listed":0,"syntology":null},{"url":null,"slug":"fp8-versus-int8-for-efficient-deep-learning","title":"FP8 versus INT8 for efficient deep learning inference","date":"2023-03-31","arxiv_id":"2303.17951","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-joint-model-and-data-driven-method-for","title":"A Joint Model and Data Driven Method for Distributed Estimation","date":"2023-03-30","arxiv_id":"2303.17241","repositories_listed":0,"syntology":null},{"url":null,"slug":"oberta-improving-sparse-transfer-learning-via","title":"oBERTa: Improving Sparse Transfer Learning via improved initialization, distillation, and pruning regimes","date":"2023-03-30","arxiv_id":"2303.17612","repositories_listed":0,"syntology":null},{"url":null,"slug":"low-dose-ct-image-reconstruction-using-vector","title":"Low-Dose CT Image Reconstruction using Vector Quantized Convolutional Autoencoder with Perceptual Loss","date":"2023-03-28","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"tetra-aml-automatic-machine-learning-via","title":"Tetra-AML: Automatic Machine Learning via Tensor Networks","date":"2023-03-28","arxiv_id":"2303.16214","repositories_listed":0,"syntology":null},{"url":null,"slug":"binarizing-sparse-convolutional-networks-for","title":"Binarizing Sparse Convolutional Networks for Efficient Point Cloud Analysis","date":"2023-03-27","arxiv_id":"2303.15493","repositories_listed":0,"syntology":null},{"url":null,"slug":"what-is-the-state-of-memory-saving-for-model","title":"An Evaluation of Memory Optimization Methods for Training Neural Networks","date":"2023-03-26","arxiv_id":"2303.14633","repositories_listed":0,"syntology":null},{"url":null,"slug":"lvqac-lattice-vector-quantization-coupled","title":"LVQAC: Lattice Vector Quantization Coupled with Spatially Adaptive Companding for Efficient Learned Image Compression","date":"2023-03-25","arxiv_id":"2304.12319","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-accurate-post-training-quantization","title":"Towards Accurate Post-Training Quantization for Vision Transformer","date":"2023-03-25","arxiv_id":"2303.14341","repositories_listed":0,"syntology":null},{"url":null,"slug":"benchmarking-the-reliability-of-post-training","title":"Benchmarking the Reliability of Post-training Quantization: a Particular Focus on Worst-case Performance","date":"2023-03-23","arxiv_id":"2303.13003","repositories_listed":0,"syntology":null},{"url":null,"slug":"scaled-quantization-for-the-vision","title":"Scaled Quantization for the Vision Transformer","date":"2023-03-23","arxiv_id":"2303.13601","repositories_listed":0,"syntology":null},{"url":null,"slug":"low-rank-optimization-for-efficient-deep","title":"Low Rank Optimization for Efficient Deep Learning: Making A Balance between Compact Architecture and Fast Training","date":"2023-03-22","arxiv_id":"2303.13635","repositories_listed":0,"syntology":null},{"url":null,"slug":"fighting-over-fitting-with-quantization-for","title":"Fighting over-fitting with quantization for learning deep neural networks on noisy labels","date":"2023-03-21","arxiv_id":"2303.11803","repositories_listed":0,"syntology":null},{"url":null,"slug":"quantized-zero-dynamics-attacks-against","title":"Quantized Zero Dynamics Attacks against Sampled-data Control Systems","date":"2023-03-21","arxiv_id":"2303.11982","repositories_listed":0,"syntology":null},{"url":"/paper/r-2-range-regularization-for-model","slug":"r-2-range-regularization-for-model","title":"R2 Loss: Range Restriction Loss for Model Compression and Quantization","date":"2023-03-14","arxiv_id":"2303.08253","repositories_listed":0,"syntology":null}],"record_sha256":"5c7dc6f0aaefd8b3cdb9ef325618fa88b5810c824f540230b9bfb4052e389e84","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}