{"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":"/method/pruning/papers/16","list_of":"/method/pruning","method":"Pruning","archive":{"snapshot":"2025-07-28"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"date (newest first), then slug","page":16,"pages_in_order":39,"rows_per_page":100,"rows":[1501,1600],"of":3874,"counts":{"archive_papers_tagged":3874,"with_a_code_link":1508,"where_syntology_ran_a_sample":478,"not_listed_spam_title":0,"listed":3874,"listed_where_code_ran":478,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":395,"every_run_a_failure_of_syntologys_instrument":83,"listed_with_a_run_with_no_instrument_failure":395,"listed_every_run_a_failure_of_syntologys_instrument":83,"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":"/method/pruning","prev":"/method/pruning/papers/15","next":"/method/pruning/papers/17","papers":[{"paper":null,"slug":"ecoflap-efficient-coarse-to-fine-layer-wise","title":"ECoFLaP: Efficient Coarse-to-Fine Layer-Wise Pruning for Vision-Language Models","date":"2023-10-04","arxiv_id":"2310.02998","n_code_links":0,"syntology":null},{"paper":null,"slug":"enhancing-accuracy-in-deep-learning-using","title":"Enhancing Accuracy in Deep Learning Using Random Matrix Theory","date":"2023-10-04","arxiv_id":"2310.03165","n_code_links":0,"syntology":null},{"paper":"/paper/deepzero-scaling-up-zeroth-order-optimization","slug":"deepzero-scaling-up-zeroth-order-optimization","title":"DeepZero: Scaling up Zeroth-Order Optimization for Deep Model Training","date":"2023-10-03","arxiv_id":"2310.02025","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["OPTML-Group/DeepZero"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/feather-an-elegant-solution-to-effective-dnn","slug":"feather-an-elegant-solution-to-effective-dnn","title":"Feather: An Elegant Solution to Effective DNN Sparsification","date":"2023-10-03","arxiv_id":"2310.02448","n_code_links":1,"syntology":null},{"paper":"/paper/ppt-token-pruning-and-pooling-for-efficient","slug":"ppt-token-pruning-and-pooling-for-efficient","title":"PPT: Token Pruning and Pooling for Efficient Vision Transformers","date":"2023-10-03","arxiv_id":"2310.01812","n_code_links":2,"syntology":{"ran":6,"of":7,"n_ran_checked":4,"n_instrument":2,"unverified":1,"pointer_only":2,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["xjwu1024/PPT","mindspore-lab/models"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/sieve-multimodal-dataset-pruning-using-image","slug":"sieve-multimodal-dataset-pruning-using-image","title":"Sieve: Multimodal Dataset Pruning Using Image Captioning Models","date":"2023-10-03","arxiv_id":"2310.02110","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["facebookresearch/sieve"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/venom-a-vectorized-n-m-format-for-unleashing","slug":"venom-a-vectorized-n-m-format-for-unleashing","title":"VENOM: A Vectorized N:M Format for Unleashing the Power of Sparse Tensor Cores","date":"2023-10-03","arxiv_id":"2310.02065","n_code_links":1,"syntology":{"ran":3,"of":4,"n_ran_checked":3,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"3 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; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["udc-gac/venom"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"artemis-he-aware-training-for-efficient","title":"Artemis: HE-Aware Training for Efficient Privacy-Preserving Machine Learning","date":"2023-10-02","arxiv_id":"2310.01664","n_code_links":0,"syntology":null},{"paper":"/paper/compressing-llms-the-truth-is-rarely-pure-and","slug":"compressing-llms-the-truth-is-rarely-pure-and","title":"Compressing LLMs: The Truth is Rarely Pure and Never Simple","date":"2023-10-02","arxiv_id":"2310.01382","n_code_links":1,"syntology":{"ran":2,"of":8,"n_ran_checked":1,"n_instrument":1,"unverified":6,"pointer_only":8,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 6 unverified","official":{"repos":["vita-group/llm-kick"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":6,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"faster-and-accurate-neural-networks-with","title":"Faster and Accurate Neural Networks with Semantic Inference","date":"2023-10-02","arxiv_id":"2310.01259","n_code_links":0,"syntology":null},{"paper":"/paper/scaling-for-training-time-and-post-hoc-out-of","slug":"scaling-for-training-time-and-post-hoc-out-of","title":"Scaling for Training Time and Post-hoc Out-of-distribution Detection Enhancement","date":"2023-09-30","arxiv_id":"2310.00227","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["kai422/scale"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"instant-complexity-reduction-in-cnns-using","title":"Instant Complexity Reduction in CNNs using Locality-Sensitive Hashing","date":"2023-09-29","arxiv_id":"2309.17211","n_code_links":0,"syntology":null},{"paper":"/paper/junk-dna-hypothesis-a-task-centric-angle-of","slug":"junk-dna-hypothesis-a-task-centric-angle-of","title":"Pruning Small Pre-Trained Weights Irreversibly and Monotonically Impairs \"Difficult\" Downstream Tasks in LLMs","date":"2023-09-29","arxiv_id":"2310.02277","n_code_links":1,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":1,"phrase":"0 ran · 1 unverified","official":{"repos":["vita-group/junk_dna_hypothesis"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"paper":"/paper/discovering-utility-driven-interval-rules","slug":"discovering-utility-driven-interval-rules","title":"Discovering Utility-driven Interval Rules","date":"2023-09-28","arxiv_id":"2309.16102","n_code_links":1,"syntology":null},{"paper":"/paper/dreamgaussian-generative-gaussian-splatting","slug":"dreamgaussian-generative-gaussian-splatting","title":"DreamGaussian: Generative Gaussian Splatting for Efficient 3D Content Creation","date":"2023-09-28","arxiv_id":"2309.16653","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["dreamgaussian/dreamgaussian"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/elip-efficient-language-image-pre-training","slug":"elip-efficient-language-image-pre-training","title":"ELIP: Efficient Language-Image Pre-training with Fewer Vision Tokens","date":"2023-09-28","arxiv_id":"2309.16738","n_code_links":1,"syntology":null},{"paper":null,"slug":"cait-triple-win-compression-towards-high","title":"CAIT: Triple-Win Compression towards High Accuracy, Fast Inference, and Favorable Transferability For ViTs","date":"2023-09-27","arxiv_id":"2309.15755","n_code_links":0,"syntology":null},{"paper":null,"slug":"lapp-layer-adaptive-progressive-pruning-for","title":"LAPP: Layer Adaptive Progressive Pruning for Compressing CNNs from Scratch","date":"2023-09-25","arxiv_id":"2309.14157","n_code_links":0,"syntology":null},{"paper":null,"slug":"on-the-impact-of-quantization-and-pruning-of","title":"On the Impact of Quantization and Pruning of Self-Supervised Speech Models for Downstream Speech Recognition Tasks \"In-the-Wild''","date":"2023-09-25","arxiv_id":"2309.14462","n_code_links":0,"syntology":null},{"paper":null,"slug":"dynamic-asr-pathways-an-adaptive-masking","title":"Dynamic ASR Pathways: An Adaptive Masking Approach Towards Efficient Pruning of A Multilingual ASR Model","date":"2023-09-22","arxiv_id":"2309.13018","n_code_links":0,"syntology":null},{"paper":null,"slug":"efficient-n-m-sparse-dnn-training-using","title":"Efficient N:M Sparse DNN Training Using Algorithm, Architecture, and Dataflow Co-Design","date":"2023-09-22","arxiv_id":"2309.13015","n_code_links":0,"syntology":null},{"paper":"/paper/thinresnet-a-new-baseline-for-structured","slug":"thinresnet-a-new-baseline-for-structured","title":"ThinResNet: A New Baseline for Structured Convolutional Networks Pruning","date":"2023-09-22","arxiv_id":"2309.12854","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-differentiable-framework-for-end-to-end","title":"A Differentiable Framework for End-to-End Learning of Hybrid Structured Compression","date":"2023-09-21","arxiv_id":"2309.13077","n_code_links":0,"syntology":null},{"paper":null,"slug":"an-efficient-and-robust-framework-for","title":"An Efficient and Robust Framework for Approximate Nearest Neighbor Search with Attribute Constraint","date":"2023-09-21","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/bayesian-sparsification-for-deep-neural","slug":"bayesian-sparsification-for-deep-neural","title":"Bayesian sparsification for deep neural networks with Bayesian model reduction","date":"2023-09-21","arxiv_id":"2309.12095","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["dimarkov/bmr4pml"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/cluster-based-pruning-techniques-for-audio","slug":"cluster-based-pruning-techniques-for-audio","title":"Cluster-based pruning techniques for audio data","date":"2023-09-21","arxiv_id":"2309.11922","n_code_links":1,"syntology":null},{"paper":"/paper/comflp-correlation-measure-based-fast-search","slug":"comflp-correlation-measure-based-fast-search","title":"CoMFLP: Correlation Measure based Fast Search on ASR Layer Pruning","date":"2023-09-21","arxiv_id":"2309.11768","n_code_links":1,"syntology":{"ran":11,"of":12,"n_ran_checked":9,"n_instrument":2,"unverified":1,"pointer_only":12,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["louislau1129/comflp"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/dont-just-prune-by-magnitude-your-mask","slug":"dont-just-prune-by-magnitude-your-mask","title":"Don’t just prune by magnitude! Your mask topology is a secret weapon","date":"2023-09-21","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/exact-verification-of-relu-neural-control","slug":"exact-verification-of-relu-neural-control","title":"Exact Verification of ReLU Neural Control Barrier Functions","date":"2023-09-21","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/lockdown-backdoor-defense-for-federated","slug":"lockdown-backdoor-defense-for-federated","title":"Lockdown: Backdoor Defense for Federated Learning with Isolated Subspace Training","date":"2023-09-21","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/lockdown-backdoor-defense-for-federated-1","slug":"lockdown-backdoor-defense-for-federated-1","title":"Lockdown: Backdoor Defense for Federated Learning with Isolated Subspace Training","date":"2023-09-21","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/making-scalable-meta-learning-practical","slug":"making-scalable-meta-learning-practical","title":"Making Scalable Meta Learning Practical","date":"2023-09-21","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/one-less-reason-for-filter-pruning-gaining","slug":"one-less-reason-for-filter-pruning-gaining","title":"One Less Reason for Filter Pruning: Gaining Free Adversarial Robustness with Structured Grouped Kernel Pruning","date":"2023-09-21","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"rewiring-neurons-in-non-stationary","title":"Rewiring Neurons in Non-Stationary Environments","date":"2023-09-21","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/selectivity-drives-productivity-efficient","slug":"selectivity-drives-productivity-efficient","title":"Selectivity Drives Productivity: Efficient Dataset Pruning for Enhanced Transfer Learning","date":"2023-09-21","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/subp-soft-uniform-block-pruning-for-1-times-n","slug":"subp-soft-uniform-block-pruning-for-1-times-n","title":"SUBP: Soft Uniform Block Pruning for 1$\\times$N Sparse CNNs Multithreading Acceleration","date":"2023-09-21","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/towards-data-agnostic-pruning-at","slug":"towards-data-agnostic-pruning-at","title":"Towards Data-Agnostic Pruning At Initialization: What Makes a Good Sparse Mask?","date":"2023-09-21","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"unveiling-optimal-sdg-pathways-an-innovative","title":"Unveiling Optimal SDG Pathways: An Innovative Approach Leveraging Graph Pruning and Intent Graph for Effective Recommendations","date":"2023-09-21","arxiv_id":"2309.11741","n_code_links":0,"syntology":null},{"paper":"/paper/flash-llm-enabling-cost-effective-and-highly","slug":"flash-llm-enabling-cost-effective-and-highly","title":"Flash-LLM: Enabling Cost-Effective and Highly-Efficient Large Generative Model Inference with Unstructured Sparsity","date":"2023-09-19","arxiv_id":"2309.10285","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["alibabaresearch/flash-llm"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"heuristic-search-for-path-finding-with","title":"Heuristic Search for Path Finding with Refuelling","date":"2023-09-19","arxiv_id":"2309.10796","n_code_links":0,"syntology":null},{"paper":null,"slug":"efficient-low-rank-gnn-defense-against","title":"Efficient Low-Rank GNN Defense Against Structural Attacks","date":"2023-09-18","arxiv_id":"2309.10136","n_code_links":0,"syntology":null},{"paper":null,"slug":"pruning-large-language-models-via-accuracy","title":"Pruning Large Language Models via Accuracy Predictor","date":"2023-09-18","arxiv_id":"2309.09507","n_code_links":0,"syntology":null},{"paper":"/paper/litetrack-layer-pruning-with-asynchronous","slug":"litetrack-layer-pruning-with-asynchronous","title":"LiteTrack: Layer Pruning with Asynchronous Feature Extraction for Lightweight and Efficient Visual Tracking","date":"2023-09-17","arxiv_id":"2309.09249","n_code_links":1,"syntology":null},{"paper":null,"slug":"accelerating-in-browser-deep-learning","title":"Empowering In-Browser Deep Learning Inference on Edge Devices with Just-in-Time Kernel Optimizations","date":"2023-09-16","arxiv_id":"2309.08978","n_code_links":0,"syntology":null},{"paper":null,"slug":"bridging-dense-and-sparse-maximum-inner","title":"Bridging Dense and Sparse Maximum Inner Product Search","date":"2023-09-16","arxiv_id":"2309.09013","n_code_links":0,"syntology":null},{"paper":"/paper/frustratingly-simple-memory-efficiency-for","slug":"frustratingly-simple-memory-efficiency-for","title":"Vocabulary-level Memory Efficiency for Language Model Fine-tuning","date":"2023-09-15","arxiv_id":"2309.08708","n_code_links":2,"syntology":null},{"paper":"/paper/p-rocket-pruning-random-convolution-kernels","slug":"p-rocket-pruning-random-convolution-kernels","title":"POCKET: Pruning Random Convolution Kernels for Time Series Classification from a Feature Selection Perspective","date":"2023-09-15","arxiv_id":"2309.08499","n_code_links":2,"syntology":null},{"paper":"/paper/uncovering-neural-scaling-laws-in-molecular-1","slug":"uncovering-neural-scaling-laws-in-molecular-1","title":"Uncovering Neural Scaling Laws in Molecular Representation Learning","date":"2023-09-15","arxiv_id":"2309.15123","n_code_links":2,"syntology":{"ran":6,"of":10,"n_ran_checked":6,"n_instrument":0,"unverified":4,"pointer_only":1,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 2 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","official":{"repos":["data-reindeer/nsl_mrl","Data-reindeer/MolScaling"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/dnnshifter-an-efficient-dnn-pruning-system","slug":"dnnshifter-an-efficient-dnn-pruning-system","title":"DNNShifter: An Efficient DNN Pruning System for Edge Computing","date":"2023-09-13","arxiv_id":"2309.06973","n_code_links":1,"syntology":null},{"paper":"/paper/feddip-federated-learning-with-extreme","slug":"feddip-federated-learning-with-extreme","title":"FedDIP: Federated Learning with Extreme Dynamic Pruning and Incremental Regularization","date":"2023-09-13","arxiv_id":"2309.06805","n_code_links":1,"syntology":null},{"paper":null,"slug":"mcns-mining-causal-natural-structures-inside","title":"MCNS: Mining Causal Natural Structures Inside Time Series via A Novel Internal Causality Scheme","date":"2023-09-13","arxiv_id":"2309.06739","n_code_links":0,"syntology":null},{"paper":null,"slug":"accelerating-deep-neural-networks-via-semi","title":"Accelerating Deep Neural Networks via Semi-Structured Activation Sparsity","date":"2023-09-12","arxiv_id":"2309.06626","n_code_links":0,"syntology":null},{"paper":null,"slug":"ensemble-mask-networks","title":"Ensemble Mask Networks","date":"2023-09-12","arxiv_id":"2309.06382","n_code_links":0,"syntology":null},{"paper":"/paper/edac-efficient-deployment-of-audio","slug":"edac-efficient-deployment-of-audio","title":"EDAC: Efficient Deployment of Audio Classification Models For COVID-19 Detection","date":"2023-09-11","arxiv_id":"2309.05357","n_code_links":1,"syntology":null},{"paper":null,"slug":"sculpting-efficiency-pruning-medical-imaging","title":"Sculpting Efficiency: Pruning Medical Imaging Models for On-Device Inference","date":"2023-09-10","arxiv_id":"2309.05090","n_code_links":0,"syntology":null},{"paper":null,"slug":"recall-driven-precision-refinement-unveiling","title":"Recall-driven Precision Refinement: Unveiling Accurate Fall Detection using LSTM","date":"2023-09-09","arxiv_id":"2309.07154","n_code_links":0,"syntology":null},{"paper":null,"slug":"decreasing-the-computing-time-of-bayesian","title":"Decreasing the Computing Time of Bayesian Optimization using Generalizable Memory Pruning","date":"2023-09-08","arxiv_id":"2309.04510","n_code_links":0,"syntology":null},{"paper":"/paper/learning-compact-compositional-embeddings-via","slug":"learning-compact-compositional-embeddings-via","title":"Learning Compact Compositional Embeddings via Regularized Pruning for Recommendation","date":"2023-09-07","arxiv_id":"2309.03518","n_code_links":1,"syntology":null},{"paper":null,"slug":"an-fpga-smart-camera-implementation-of","title":"An FPGA smart camera implementation of segmentation models for drone wildfire imagery","date":"2023-09-04","arxiv_id":"2309.01318","n_code_links":0,"syntology":null},{"paper":null,"slug":"computation-and-communication-efficient","title":"Adaptive Model Pruning and Personalization for Federated Learning over Wireless Networks","date":"2023-09-04","arxiv_id":"2309.01816","n_code_links":0,"syntology":null},{"paper":"/paper/transformer-compression-via-subspace","slug":"transformer-compression-via-subspace","title":"$\\rm SP^3$: Enhancing Structured Pruning via PCA Projection","date":"2023-08-31","arxiv_id":"2308.16475","n_code_links":1,"syntology":{"ran":12,"of":14,"n_ran_checked":11,"n_instrument":1,"unverified":2,"pointer_only":14,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 1 violated, 9 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","official":{"repos":["hyx1999/sp3"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/learning-diverse-features-in-vision","slug":"learning-diverse-features-in-vision","title":"Learning Diverse Features in Vision Transformers for Improved Generalization","date":"2023-08-30","arxiv_id":"2308.16274","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["armandnm/diverse-vit"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"serving-moe-models-on-resource-constrained","title":"SwapMoE: Serving Off-the-shelf MoE-based Large Language Models with Tunable Memory Budget","date":"2023-08-29","arxiv_id":"2308.15030","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-generalization-of-continuous-relaxation-in","title":"A Generalization of Continuous Relaxation in Structured Pruning","date":"2023-08-28","arxiv_id":"2308.14605","n_code_links":0,"syntology":null},{"paper":null,"slug":"pruning-self-attention-for-zero-shot-multi","title":"Pruning Self-Attention for Zero-Shot Multi-Speaker Text-to-Speech","date":"2023-08-28","arxiv_id":"2308.14909","n_code_links":0,"syntology":null},{"paper":"/paper/fixating-on-attention-integrating-human-eye","slug":"fixating-on-attention-integrating-human-eye","title":"Gaze-Informed Vision Transformers: Predicting Driving Decisions Under Uncertainty","date":"2023-08-26","arxiv_id":"2308.13969","n_code_links":1,"syntology":null},{"paper":null,"slug":"memory-aware-scheduling-for-complex-wired","title":"Memory-aware Scheduling for Complex Wired Networks with Iterative Graph Optimization","date":"2023-08-26","arxiv_id":"2308.13898","n_code_links":0,"syntology":null},{"paper":null,"slug":"resource-efficient-federated-learning-for","title":"REFT: Resource-Efficient Federated Training Framework for Heterogeneous and Resource-Constrained Environments","date":"2023-08-25","arxiv_id":"2308.13662","n_code_links":0,"syntology":null},{"paper":"/paper/increlora-incremental-parameter-allocation","slug":"increlora-incremental-parameter-allocation","title":"IncreLoRA: Incremental Parameter Allocation Method for Parameter-Efficient Fine-tuning","date":"2023-08-23","arxiv_id":"2308.12043","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":1,"n_instrument":1,"unverified":0,"pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["feiyuzhang98/increlora"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/efficient-joint-optimization-of-layer","slug":"efficient-joint-optimization-of-layer","title":"Efficient Joint Optimization of Layer-Adaptive Weight Pruning in Deep Neural Networks","date":"2023-08-21","arxiv_id":"2308.10438","n_code_links":2,"syntology":null},{"paper":"/paper/privacy-preserving-face-recognition-using","slug":"privacy-preserving-face-recognition-using","title":"Privacy-Preserving Face Recognition Using Random Frequency Components","date":"2023-08-21","arxiv_id":"2308.10461","n_code_links":1,"syntology":null},{"paper":null,"slug":"vision-transformer-pruning-via-matrix","title":"Vision Transformer Pruning Via Matrix Decomposition","date":"2023-08-21","arxiv_id":"2308.10839","n_code_links":0,"syntology":null},{"paper":null,"slug":"controlretriever-harnessing-the-power-of","title":"I3: Intent-Introspective Retrieval Conditioned on Instructions","date":"2023-08-19","arxiv_id":"2308.10025","n_code_links":0,"syntology":null},{"paper":"/paper/on-the-robustness-of-open-world-test-time","slug":"on-the-robustness-of-open-world-test-time","title":"On the Robustness of Open-World Test-Time Training: Self-Training with Dynamic Prototype Expansion","date":"2023-08-19","arxiv_id":"2308.09942","n_code_links":1,"syntology":{"ran":9,"of":11,"n_ran_checked":9,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["yushu-li/owttt"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"to-prune-or-not-to-prune-a-chaos-causality","title":"To prune or not to prune : A chaos-causality approach to principled pruning of dense neural networks","date":"2023-08-19","arxiv_id":"2308.09955","n_code_links":0,"syntology":null},{"paper":"/paper/how-does-pruning-impact-long-tailed-multi","slug":"how-does-pruning-impact-long-tailed-multi","title":"How Does Pruning Impact Long-Tailed Multi-Label Medical Image Classifiers?","date":"2023-08-17","arxiv_id":"2308.09180","n_code_links":1,"syntology":null},{"paper":null,"slug":"benchmarking-adversarial-robustness-of","title":"Benchmarking Adversarial Robustness of Compressed Deep Learning Models","date":"2023-08-16","arxiv_id":"2308.08160","n_code_links":0,"syntology":null},{"paper":null,"slug":"reproducing-kernel-hilbert-space-pruning-for","title":"Reproducing Kernel Hilbert Space Pruning for Sparse Hyperspectral Abundance Prediction","date":"2023-08-16","arxiv_id":"2308.08653","n_code_links":0,"syntology":null},{"paper":null,"slug":"ada-qpacknet-adaptive-pruning-with-bit-width","title":"Ada-QPacknet -- adaptive pruning with bit width reduction as an efficient continual learning method without forgetting","date":"2023-08-14","arxiv_id":"2308.07939","n_code_links":0,"syntology":null},{"paper":null,"slug":"unified-data-free-compression-pruning-and","title":"Unified Data-Free Compression: Pruning and Quantization without Fine-Tuning","date":"2023-08-14","arxiv_id":"2308.07209","n_code_links":0,"syntology":null},{"paper":"/paper/a-survey-on-deep-neural-network-pruning","slug":"a-survey-on-deep-neural-network-pruning","title":"A Survey on Deep Neural Network Pruning-Taxonomy, Comparison, Analysis, and Recommendations","date":"2023-08-13","arxiv_id":"2308.06767","n_code_links":1,"syntology":null},{"paper":"/paper/influence-function-based-second-order-channel","slug":"influence-function-based-second-order-channel","title":"Influence Function Based Second-Order Channel Pruning-Evaluating True Loss Changes For Pruning Is Possible Without Retraining","date":"2023-08-13","arxiv_id":"2308.06755","n_code_links":1,"syntology":null},{"paper":null,"slug":"neural-networks-at-a-fraction-with-pruned","title":"Neural Networks at a Fraction with Pruned Quaternions","date":"2023-08-13","arxiv_id":"2308.06780","n_code_links":0,"syntology":null},{"paper":"/paper/can-unstructured-pruning-reduce-the-depth-in","slug":"can-unstructured-pruning-reduce-the-depth-in","title":"Can Unstructured Pruning Reduce the Depth in Deep Neural Networks?","date":"2023-08-12","arxiv_id":"2308.06619","n_code_links":1,"syntology":null},{"paper":null,"slug":"revisiting-vision-transformer-from-the-view","title":"Revisiting Vision Transformer from the View of Path Ensemble","date":"2023-08-12","arxiv_id":"2308.06548","n_code_links":0,"syntology":null},{"paper":null,"slug":"automated-sizing-and-training-of-efficient","title":"Automated Sizing and Training of Efficient Deep Autoencoders using Second Order Algorithms","date":"2023-08-11","arxiv_id":"2308.06221","n_code_links":0,"syntology":null},{"paper":null,"slug":"fpga-resource-aware-structured-pruning-for","title":"FPGA Resource-aware Structured Pruning for Real-Time Neural Networks","date":"2023-08-09","arxiv_id":"2308.05170","n_code_links":0,"syntology":null},{"paper":null,"slug":"safer-layer-level-sensitivity-assessment-for","title":"SAfER: Layer-Level Sensitivity Assessment for Efficient and Robust Neural Network Inference","date":"2023-08-09","arxiv_id":"2308.04753","n_code_links":0,"syntology":null},{"paper":"/paper/which-tokens-to-use-investigating-token","slug":"which-tokens-to-use-investigating-token","title":"Which Tokens to Use? Investigating Token Reduction in Vision Transformers","date":"2023-08-09","arxiv_id":"2308.04657","n_code_links":1,"syntology":{"ran":8,"of":8,"n_ran_checked":6,"n_instrument":2,"unverified":0,"pointer_only":3,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":null,"slug":"d-score-a-synapse-inspired-approach-for","title":"D-Score: A Synapse-Inspired Approach for Filter Pruning","date":"2023-08-08","arxiv_id":"2308.04470","n_code_links":0,"syntology":null},{"paper":"/paper/knowledge-preserving-pruning-for-pre-trained","slug":"knowledge-preserving-pruning-for-pre-trained","title":"Accurate Retraining-free Pruning for Pretrained Encoder-based Language Models","date":"2023-08-07","arxiv_id":"2308.03449","n_code_links":1,"syntology":{"ran":12,"of":16,"n_ran_checked":12,"n_instrument":0,"unverified":4,"pointer_only":16,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","official":{"repos":["snudm-starlab/k-prune"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"iterative-magnitude-pruning-as-a","title":"Iterative Magnitude Pruning as a Renormalisation Group: A Study in The Context of The Lottery Ticket Hypothesis","date":"2023-08-06","arxiv_id":"2308.03128","n_code_links":0,"syntology":null},{"paper":"/paper/adversarial-erasing-with-pruned-elements","slug":"adversarial-erasing-with-pruned-elements","title":"Adversarial Erasing with Pruned Elements: Towards Better Graph Lottery Ticket","date":"2023-08-05","arxiv_id":"2308.02916","n_code_links":1,"syntology":null},{"paper":null,"slug":"pruning-a-neural-network-using-bayesian","title":"Pruning a neural network using Bayesian inference","date":"2023-08-04","arxiv_id":"2308.02451","n_code_links":0,"syntology":null},{"paper":null,"slug":"scalable-computation-of-causal-bounds","title":"Scalable Computation of Causal Bounds","date":"2023-08-04","arxiv_id":"2308.02709","n_code_links":0,"syntology":null},{"paper":null,"slug":"solving-witness-type-triangle-puzzles-faster","title":"Solving Witness-type Triangle Puzzles Faster with an Automatically Learned Human-Explainable Predicate","date":"2023-08-04","arxiv_id":"2308.02666","n_code_links":0,"syntology":null},{"paper":null,"slug":"accurate-neural-network-pruning-requires","title":"Accurate Neural Network Pruning Requires Rethinking Sparse Optimization","date":"2023-08-03","arxiv_id":"2308.02060","n_code_links":0,"syntology":null},{"paper":null,"slug":"hierarchical-federated-learning-in-wireless","title":"Hierarchical Federated Learning in Wireless Networks: Pruning Tackles Bandwidth Scarcity and System Heterogeneity","date":"2023-08-03","arxiv_id":"2308.01562","n_code_links":0,"syntology":null},{"paper":"/paper/data-centric-diet-effective-multi-center","slug":"data-centric-diet-effective-multi-center","title":"Data-Centric Diet: Effective Multi-center Dataset Pruning for Medical Image Segmentation","date":"2023-08-02","arxiv_id":"2308.01189","n_code_links":0,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"pointer_only":3,"phrase":"3 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; 0 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":"/paper/dynamic-token-pruning-in-plain-vision","slug":"dynamic-token-pruning-in-plain-vision","title":"Dynamic Token Pruning in Plain Vision Transformers for Semantic Segmentation","date":"2023-08-02","arxiv_id":"2308.01045","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":4,"n_instrument":0,"unverified":0,"pointer_only":1,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":null}}],"record_sha256":"4e800d892efd1c42c45a0c8eef4678444f58ee3306d5159fee0c79085902d17d","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}