{"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/15","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":15,"pages_in_order":39,"rows_per_page":100,"rows":[1401,1500],"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/14","next":"/method/pruning/papers/16","papers":[{"paper":"/paper/faster-minimum-bayes-risk-decoding-with","slug":"faster-minimum-bayes-risk-decoding-with","title":"Faster Minimum Bayes Risk Decoding with Confidence-based Pruning","date":"2023-11-25","arxiv_id":"2311.14919","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":["juliusc/pruning_mbr"],"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":null,"slug":"analysing-the-impact-of-removing-infrequent","title":"Analysing the Impact of Removing Infrequent Words on Topic Quality in LDA Models","date":"2023-11-24","arxiv_id":"2311.14505","n_code_links":0,"syntology":null},{"paper":"/paper/crisp-hybrid-structured-sparsity-for-class","slug":"crisp-hybrid-structured-sparsity-for-class","title":"CRISP: Hybrid Structured Sparsity for Class-aware Model Pruning","date":"2023-11-24","arxiv_id":"2311.14272","n_code_links":1,"syntology":null},{"paper":null,"slug":"you-only-explain-once","title":"You Only Explain Once","date":"2023-11-23","arxiv_id":"2311.14081","n_code_links":0,"syntology":null},{"paper":null,"slug":"adaptivefl-adaptive-heterogeneous-federated","title":"AdaptiveFL: Adaptive Heterogeneous Federated Learning for Resource-Constrained AIoT Systems","date":"2023-11-22","arxiv_id":"2311.13166","n_code_links":0,"syntology":null},{"paper":null,"slug":"deriving-comprehensible-theories-from","title":"Pruning-Based Extraction of Descriptions from Probabilistic Circuits","date":"2023-11-22","arxiv_id":"2311.13379","n_code_links":0,"syntology":null},{"paper":"/paper/input-compression-with-positional-consistency","slug":"input-compression-with-positional-consistency","title":"Input Compression with Positional Consistency for Efficient Training and Inference of Transformer Neural Networks","date":"2023-11-22","arxiv_id":"2312.12385","n_code_links":1,"syntology":null},{"paper":"/paper/spanning-training-progress-temporal-dual","slug":"spanning-training-progress-temporal-dual","title":"Spanning Training Progress: Temporal Dual-Depth Scoring (TDDS) for Enhanced Dataset Pruning","date":"2023-11-22","arxiv_id":"2311.13613","n_code_links":1,"syntology":{"ran":6,"of":11,"n_ran_checked":4,"n_instrument":2,"unverified":5,"pointer_only":1,"phrase":"6 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; 2 where Syntology's instrument failed) · 5 unverified","official":{"repos":["zhangxin-xd/Dataset-Pruning-TDDS"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"mechanistically-analyzing-the-effects-of-fine","title":"Mechanistically analyzing the effects of fine-tuning on procedurally defined tasks","date":"2023-11-21","arxiv_id":"2311.12786","n_code_links":0,"syntology":null},{"paper":"/paper/neural-network-pruning-by-gradient-descent","slug":"neural-network-pruning-by-gradient-descent","title":"Neural Network Pruning by Gradient Descent","date":"2023-11-21","arxiv_id":"2311.12526","n_code_links":1,"syntology":null},{"paper":"/paper/hourglass-tokenizer-for-efficient-transformer","slug":"hourglass-tokenizer-for-efficient-transformer","title":"Hourglass Tokenizer for Efficient Transformer-Based 3D Human Pose Estimation","date":"2023-11-20","arxiv_id":"2311.12028","n_code_links":1,"syntology":null},{"paper":"/paper/optimal-locally-private-nonparametric","slug":"optimal-locally-private-nonparametric","title":"Optimal Locally Private Nonparametric Classification with Public Data","date":"2023-11-19","arxiv_id":"2311.11369","n_code_links":1,"syntology":null},{"paper":null,"slug":"physics-enhanced-tinyml-for-real-time","title":"Physics-Enhanced TinyML for Real-Time Detection of Ground Magnetic Anomalies","date":"2023-11-19","arxiv_id":"2311.11452","n_code_links":0,"syntology":null},{"paper":null,"slug":"energizing-federated-learning-via-filter","title":"Energizing Federated Learning via Filter-Aware Attention","date":"2023-11-18","arxiv_id":"2311.12049","n_code_links":0,"syntology":null},{"paper":null,"slug":"pursing-the-sparse-limitation-of-spiking-deep","title":"Pursing the Sparse Limitation of Spiking Deep Learning Structures","date":"2023-11-18","arxiv_id":"2311.12060","n_code_links":0,"syntology":null},{"paper":null,"slug":"archtree-on-the-fly-tree-structured","title":"Archtree: on-the-fly tree-structured exploration for latency-aware pruning of deep neural networks","date":"2023-11-17","arxiv_id":"2311.10549","n_code_links":0,"syntology":null},{"paper":"/paper/hierarchical-pruning-of-deep-ensembles-with","slug":"hierarchical-pruning-of-deep-ensembles-with","title":"Hierarchical Pruning of Deep Ensembles with Focal Diversity","date":"2023-11-17","arxiv_id":"2311.10293","n_code_links":1,"syntology":null},{"paper":null,"slug":"using-cooperative-game-theory-to-prune-neural","title":"Using Cooperative Game Theory to Prune Neural Networks","date":"2023-11-17","arxiv_id":"2311.10468","n_code_links":0,"syntology":null},{"paper":null,"slug":"crispr-eliminating-bias-neurons-from-an","title":"Mitigating Biases for Instruction-following Language Models via Bias Neurons Elimination","date":"2023-11-16","arxiv_id":"2311.09627","n_code_links":0,"syntology":null},{"paper":null,"slug":"how-does-calibration-data-affect-the-post","title":"On the Impact of Calibration Data in Post-training Quantization and Pruning","date":"2023-11-16","arxiv_id":"2311.09755","n_code_links":0,"syntology":null},{"paper":null,"slug":"investigating-the-impact-of-weight-sharing","title":"Investigating the Impact of Weight Sharing Decisions on Knowledge Transfer in Continual Learning","date":"2023-11-16","arxiv_id":"2311.09506","n_code_links":0,"syntology":null},{"paper":null,"slug":"polynomially-over-parameterized-convolutional","title":"Polynomially Over-Parameterized Convolutional Neural Networks Contain Structured Strong Winning Lottery Tickets","date":"2023-11-16","arxiv_id":"2311.09858","n_code_links":0,"syntology":null},{"paper":null,"slug":"data-augmentations-in-deep-weight-spaces","title":"Data Augmentations in Deep Weight Spaces","date":"2023-11-15","arxiv_id":"2311.08851","n_code_links":0,"syntology":null},{"paper":"/paper/do-localization-methods-actually-localize","slug":"do-localization-methods-actually-localize","title":"Do Localization Methods Actually Localize Memorized Data in LLMs? A Tale of Two Benchmarks","date":"2023-11-15","arxiv_id":"2311.09060","n_code_links":2,"syntology":{"ran":6,"of":15,"n_ran_checked":6,"n_instrument":0,"unverified":9,"pointer_only":0,"phrase":"6 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; 0 where Syntology's instrument failed) · 9 unverified","official":{"repos":["terarachang/memdata","terarachang/mempi"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":9,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"fedcode-communication-efficient-federated","title":"FedCode: Communication-Efficient Federated Learning via Transferring Codebooks","date":"2023-11-15","arxiv_id":"2311.09270","n_code_links":0,"syntology":null},{"paper":"/paper/lighter-yet-more-faithful-investigating","slug":"lighter-yet-more-faithful-investigating","title":"Investigating Hallucinations in Pruned Large Language Models for Abstractive Summarization","date":"2023-11-15","arxiv_id":"2311.09335","n_code_links":1,"syntology":null},{"paper":null,"slug":"sparsespikformer-a-co-design-framework-for","title":"SparseSpikformer: A Co-Design Framework for Token and Weight Pruning in Spiking Transformer","date":"2023-11-15","arxiv_id":"2311.08806","n_code_links":0,"syntology":null},{"paper":null,"slug":"core-cog-conversational-recommendation-of","title":"CoRE-CoG: Conversational Recommendation of Entities using Constrained Generation","date":"2023-11-14","arxiv_id":"2311.08511","n_code_links":0,"syntology":null},{"paper":null,"slug":"lite-it-fly-an-all-deformable-butterfly","title":"Lite it fly: An All-Deformable-Butterfly Network","date":"2023-11-14","arxiv_id":"2311.08125","n_code_links":0,"syntology":null},{"paper":null,"slug":"activity-sparsity-complements-weight-sparsity","title":"Activity Sparsity Complements Weight Sparsity for Efficient RNN Inference","date":"2023-11-13","arxiv_id":"2311.07625","n_code_links":0,"syntology":null},{"paper":"/paper/metasymnet-a-dynamic-symbolic-regression","slug":"metasymnet-a-dynamic-symbolic-regression","title":"MetaSymNet: A Tree-like Symbol Network with Adaptive Architecture and Activation Functions","date":"2023-11-13","arxiv_id":"2311.07326","n_code_links":1,"syntology":null},{"paper":null,"slug":"pruning-random-resistive-memory-for","title":"Pruning random resistive memory for optimizing analogue AI","date":"2023-11-13","arxiv_id":"2311.07164","n_code_links":0,"syntology":null},{"paper":null,"slug":"epim-efficient-processing-in-memory","title":"EPIM: Efficient Processing-In-Memory Accelerators based on Epitome","date":"2023-11-12","arxiv_id":"2311.07620","n_code_links":0,"syntology":null},{"paper":null,"slug":"inference-and-interference-the-role-of","title":"Inference and Interference: The Role of Clipping, Pruning and Loss Landscapes in Differentially Private Stochastic Gradient Descent","date":"2023-11-12","arxiv_id":"2311.06839","n_code_links":0,"syntology":null},{"paper":null,"slug":"transfer-learning-for-structured-pruning","title":"Transfer Learning for Structured Pruning under Limited Task Data","date":"2023-11-10","arxiv_id":"2311.06382","n_code_links":0,"syntology":null},{"paper":"/paper/beyond-size-how-gradients-shape-pruning","slug":"beyond-size-how-gradients-shape-pruning","title":"Beyond Size: How Gradients Shape Pruning Decisions in Large Language Models","date":"2023-11-08","arxiv_id":"2311.04902","n_code_links":2,"syntology":{"ran":3,"of":7,"n_ran_checked":2,"n_instrument":1,"unverified":4,"pointer_only":1,"phrase":"3 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; 1 where Syntology's instrument failed) · 4 unverified","official":{"repos":["rocktimjyotidas/gblm-pruner","vila-lab/gblm-pruner"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/cup-curriculum-curriculum-learning-on-model","slug":"cup-curriculum-curriculum-learning-on-model","title":"Cup Curriculum: Curriculum Learning on Model Capacity","date":"2023-11-07","arxiv_id":"2311.03956","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"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) · 0 unverified","official":{"repos":["luca-scharr/cupcurriculum"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/gtp-vit-efficient-vision-transformers-via","slug":"gtp-vit-efficient-vision-transformers-via","title":"GTP-ViT: Efficient Vision Transformers via Graph-based Token Propagation","date":"2023-11-06","arxiv_id":"2311.03035","n_code_links":1,"syntology":{"ran":1,"of":2,"n_ran_checked":0,"n_instrument":1,"unverified":1,"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) · 1 unverified","official":{"repos":["ackesnal/gtp-vit"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"brain-inspired-efficient-pruning-exploiting","title":"Brain-Inspired Efficient Pruning: Exploiting Criticality in Spiking Neural Networks","date":"2023-11-05","arxiv_id":"2311.16141","n_code_links":0,"syntology":null},{"paper":"/paper/a-structured-pruning-algorithm-for-model","slug":"a-structured-pruning-algorithm-for-model","title":"Efficient Model-Based Deep Learning via Network Pruning and Fine-Tuning","date":"2023-11-03","arxiv_id":"2311.02003","n_code_links":1,"syntology":null},{"paper":null,"slug":"revisiting-the-knowledge-injection-frameworks","title":"Revisiting the Knowledge Injection Frameworks","date":"2023-11-02","arxiv_id":"2311.01150","n_code_links":0,"syntology":null},{"paper":"/paper/robust-data-pruning-under-label-noise-via","slug":"robust-data-pruning-under-label-noise-via","title":"Robust Data Pruning under Label Noise via Maximizing Re-labeling Accuracy","date":"2023-11-02","arxiv_id":"2311.01002","n_code_links":1,"syntology":{"ran":14,"of":16,"n_ran_checked":10,"n_instrument":4,"unverified":2,"pointer_only":5,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 4 where Syntology's instrument failed) · 2 unverified","official":{"repos":["kaist-dmlab/Prune4Rel"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"federated-topic-model-and-model-pruning-based","title":"Federated Topic Model and Model Pruning Based on Variational Autoencoder","date":"2023-11-01","arxiv_id":"2311.00314","n_code_links":0,"syntology":null},{"paper":"/paper/llmrec-large-language-models-with-graph","slug":"llmrec-large-language-models-with-graph","title":"LLMRec: Large Language Models with Graph Augmentation for Recommendation","date":"2023-11-01","arxiv_id":"2311.00423","n_code_links":1,"syntology":{"ran":15,"of":16,"n_ran_checked":14,"n_instrument":1,"unverified":1,"pointer_only":6,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 1 honoured, 1 violated, 12 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["hkuds/llmrec"],"state":"official (archive's flag): 15 ran","n_ran":15,"n_constructed":0,"n_ran_no_instrument_failure":14,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/balancing-act-constraining-disparate-impact","slug":"balancing-act-constraining-disparate-impact","title":"Balancing Act: Constraining Disparate Impact in Sparse Models","date":"2023-10-31","arxiv_id":"2310.20673","n_code_links":3,"syntology":{"ran":2,"of":4,"n_ran_checked":2,"n_instrument":0,"unverified":2,"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) · 2 unverified","official":{"repos":["cooper-org/cooper","merajhashemi/balancing-act","merajhashemi/balancing_act"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"adapter-pruning-using-tropical","title":"Adapter Pruning using Tropical Characterization","date":"2023-10-30","arxiv_id":"2310.19232","n_code_links":0,"syntology":null},{"paper":"/paper/grokking-tickets-lottery-tickets-accelerate","slug":"grokking-tickets-lottery-tickets-accelerate","title":"Bridging Lottery Ticket and Grokking: Understanding Grokking from Inner Structure of Networks","date":"2023-10-30","arxiv_id":"2310.19470","n_code_links":1,"syntology":{"ran":3,"of":5,"n_ran_checked":2,"n_instrument":1,"unverified":2,"pointer_only":5,"phrase":"3 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; 1 where Syntology's instrument failed) · 2 unverified","official":{"repos":["gouki510/grokking-tickets"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"priprune-quantifying-and-preserving-privacy","title":"PriPrune: Quantifying and Preserving Privacy in Pruned Federated Learning","date":"2023-10-30","arxiv_id":"2310.19958","n_code_links":0,"syntology":null},{"paper":"/paper/resource-constrained-semantic-segmentation","slug":"resource-constrained-semantic-segmentation","title":"Resource Constrained Semantic Segmentation for Waste Sorting","date":"2023-10-30","arxiv_id":"2310.19407","n_code_links":1,"syntology":null},{"paper":null,"slug":"sparsebytenn-a-novel-mobile-inference","title":"SparseByteNN: A Novel Mobile Inference Acceleration Framework Based on Fine-Grained Group Sparsity","date":"2023-10-30","arxiv_id":"2310.19509","n_code_links":0,"syntology":null},{"paper":null,"slug":"linear-mode-connectivity-in-sparse-neural","title":"Linear Mode Connectivity in Sparse Neural Networks","date":"2023-10-28","arxiv_id":"2310.18769","n_code_links":0,"syntology":null},{"paper":null,"slug":"bridging-the-gaps-between-token-pruning-and","title":"Bridging The Gaps Between Token Pruning and Full Pre-training via Masked Fine-tuning","date":"2023-10-26","arxiv_id":"2310.17177","n_code_links":0,"syntology":null},{"paper":null,"slug":"pac-tuning-fine-tuning-pretrained-language","title":"PAC-tuning:Fine-tuning Pretrained Language Models with PAC-driven Perturbed Gradient Descent","date":"2023-10-26","arxiv_id":"2310.17588","n_code_links":0,"syntology":null},{"paper":null,"slug":"graft-gradual-fusion-transformer-for","title":"GraFT: Gradual Fusion Transformer for Multimodal Re-Identification","date":"2023-10-25","arxiv_id":"2310.16856","n_code_links":0,"syntology":null},{"paper":null,"slug":"e-sparse-boosting-the-large-language-model","title":"E-Sparse: Boosting the Large Language Model Inference through Entropy-based N:M Sparsity","date":"2023-10-24","arxiv_id":"2310.15929","n_code_links":0,"syntology":null},{"paper":"/paper/lorashear-efficient-large-language-model","slug":"lorashear-efficient-large-language-model","title":"LoRAShear: Efficient Large Language Model Structured Pruning and Knowledge Recovery","date":"2023-10-24","arxiv_id":"2310.18356","n_code_links":2,"syntology":{"ran":1,"of":3,"n_ran_checked":1,"n_instrument":0,"unverified":2,"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) · 2 unverified","official":null}},{"paper":null,"slug":"mixture-of-linguistic-experts-adapters-for","title":"Mixture-of-Linguistic-Experts Adapters for Improving and Interpreting Pre-trained Language Models","date":"2023-10-24","arxiv_id":"2310.16240","n_code_links":0,"syntology":null},{"paper":null,"slug":"data-pruning-via-moving-one-sample-out","title":"Data Pruning via Moving-one-Sample-out","date":"2023-10-23","arxiv_id":"2310.14664","n_code_links":0,"syntology":null},{"paper":"/paper/federated-learning-compression-designed-for","slug":"federated-learning-compression-designed-for","title":"Federated learning compression designed for lightweight communications","date":"2023-10-23","arxiv_id":"2310.14693","n_code_links":1,"syntology":null},{"paper":"/paper/lxmert-model-compression-for-visual-question","slug":"lxmert-model-compression-for-visual-question","title":"LXMERT Model Compression for Visual Question Answering","date":"2023-10-23","arxiv_id":"2310.15325","n_code_links":2,"syntology":null},{"paper":null,"slug":"mgas-multi-granularity-architecture-search","title":"MGAS: Multi-Granularity Architecture Search for Trade-Off Between Model Effectiveness and Efficiency","date":"2023-10-23","arxiv_id":"2310.15074","n_code_links":0,"syntology":null},{"paper":"/paper/you-only-condense-once-two-rules-for-pruning-1","slug":"you-only-condense-once-two-rules-for-pruning-1","title":"You Only Condense Once: Two Rules for Pruning Condensed Datasets","date":"2023-10-21","arxiv_id":"2310.14019","n_code_links":1,"syntology":{"ran":13,"of":16,"n_ran_checked":11,"n_instrument":2,"unverified":3,"pointer_only":16,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","official":{"repos":["he-y/you-only-condense-once"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/cnn-based-prediction-of-partition-path-for","slug":"cnn-based-prediction-of-partition-path-for","title":"CNN-based Prediction of Partition Path for VVC Fast Inter Partitioning Using Motion Fields","date":"2023-10-20","arxiv_id":"2310.13838","n_code_links":2,"syntology":null},{"paper":null,"slug":"breaking-through-deterministic-barriers","title":"Breaking through Deterministic Barriers: Randomized Pruning Mask Generation and Selection","date":"2023-10-19","arxiv_id":"2310.13183","n_code_links":0,"syntology":null},{"paper":"/paper/how-a-student-becomes-a-teacher-learning-and","slug":"how-a-student-becomes-a-teacher-learning-and","title":"How a student becomes a teacher: learning and forgetting through Spectral methods","date":"2023-10-19","arxiv_id":"2310.12612","n_code_links":1,"syntology":{"ran":3,"of":4,"n_ran_checked":3,"n_instrument":0,"unverified":1,"pointer_only":4,"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":["jamba15/spectral-regularization-teacher-student"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["found_in_text","official"]}}},{"paper":null,"slug":"robust-multimodal-models-have-outlier","title":"Interpreting CLIP: Insights on the Robustness to ImageNet Distribution Shifts","date":"2023-10-19","arxiv_id":"2310.13040","n_code_links":0,"syntology":null},{"paper":"/paper/survival-of-the-most-influential-prompts","slug":"survival-of-the-most-influential-prompts","title":"Survival of the Most Influential Prompts: Efficient Black-Box Prompt Search via Clustering and Pruning","date":"2023-10-19","arxiv_id":"2310.12774","n_code_links":1,"syntology":{"ran":1,"of":3,"n_ran_checked":0,"n_instrument":1,"unverified":2,"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) · 2 unverified","official":{"repos":["cambridgeltl/claps"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"towards-robust-pruning-an-adaptive-knowledge","title":"Towards Robust Pruning: An Adaptive Knowledge-Retention Pruning Strategy for Language Models","date":"2023-10-19","arxiv_id":"2310.13191","n_code_links":0,"syntology":null},{"paper":null,"slug":"conservative-predictions-on-noisy-financial","title":"Conservative Predictions on Noisy Financial Data","date":"2023-10-18","arxiv_id":"2310.11815","n_code_links":0,"syntology":null},{"paper":null,"slug":"ki-pmf-knowledge-integrated-plausible-motion","title":"KI-PMF: Knowledge Integrated Plausible Motion Forecasting","date":"2023-10-18","arxiv_id":"2310.12007","n_code_links":0,"syntology":null},{"paper":null,"slug":"in-defense-of-parameter-sharing-for-model","title":"In defense of parameter sharing for model-compression","date":"2023-10-17","arxiv_id":"2310.11611","n_code_links":0,"syntology":null},{"paper":null,"slug":"iterative-shallow-fusion-of-backward-language","title":"Iterative Shallow Fusion of Backward Language Model for End-to-End Speech Recognition","date":"2023-10-17","arxiv_id":"2310.11010","n_code_links":0,"syntology":null},{"paper":null,"slug":"gevo-ml-optimizing-machine-learning-code-with","title":"GEVO-ML: Optimizing Machine Learning Code with Evolutionary Computation","date":"2023-10-16","arxiv_id":"2310.10211","n_code_links":0,"syntology":null},{"paper":"/paper/nash-a-simple-unified-framework-of-structured","slug":"nash-a-simple-unified-framework-of-structured","title":"NASH: A Simple Unified Framework of Structured Pruning for Accelerating Encoder-Decoder Language Models","date":"2023-10-16","arxiv_id":"2310.10054","n_code_links":1,"syntology":null},{"paper":null,"slug":"the-road-to-on-board-change-detection-a","title":"The Road to On-board Change Detection: A Lightweight Patch-Level Change Detection Network via Exploring the Potential of Pruning and Pooling","date":"2023-10-16","arxiv_id":"2310.10166","n_code_links":0,"syntology":null},{"paper":"/paper/does-clip-s-generalization-performance-mainly","slug":"does-clip-s-generalization-performance-mainly","title":"Does CLIP's Generalization Performance Mainly Stem from High Train-Test Similarity?","date":"2023-10-14","arxiv_id":"2310.09562","n_code_links":1,"syntology":{"ran":1,"of":3,"n_ran_checked":1,"n_instrument":0,"unverified":2,"pointer_only":1,"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) · 2 unverified","official":{"repos":["brendel-group/clip-ood"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["unlocated"]}}},{"paper":null,"slug":"edge-inversionnet-enabling-efficient","title":"Edge-InversionNet: Enabling Efficient Inference of InversionNet on Edge Devices","date":"2023-10-14","arxiv_id":"2310.09667","n_code_links":0,"syntology":null},{"paper":"/paper/one-shot-sensitivity-aware-mixed-sparsity","slug":"one-shot-sensitivity-aware-mixed-sparsity","title":"One-Shot Sensitivity-Aware Mixed Sparsity Pruning for Large Language Models","date":"2023-10-14","arxiv_id":"2310.09499","n_code_links":1,"syntology":{"ran":4,"of":11,"n_ran_checked":1,"n_instrument":3,"unverified":7,"pointer_only":11,"phrase":"4 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; 3 where Syntology's instrument failed) · 7 unverified","official":{"repos":["talkking/MixGPT"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":7,"ran_from_kinds":["official"]}}},{"paper":"/paper/dynamic-sparse-no-training-training-free-fine","slug":"dynamic-sparse-no-training-training-free-fine","title":"Dynamic Sparse No Training: Training-Free Fine-tuning for Sparse LLMs","date":"2023-10-13","arxiv_id":"2310.08915","n_code_links":1,"syntology":{"ran":8,"of":15,"n_ran_checked":6,"n_instrument":2,"unverified":7,"pointer_only":15,"phrase":"8 ran (of which 2 constructed an object rather than computing a result; 6 with no instrument failure: 2 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 7 unverified","official":{"repos":["zyxxmu/dsnot"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":2,"n_ran_no_instrument_failure":6,"n_unverified":7,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"exploring-sparse-spatial-relation-in-graph","title":"Exploring Sparse Spatial Relation in Graph Inference for Text-Based VQA","date":"2023-10-13","arxiv_id":"2310.09147","n_code_links":0,"syntology":null},{"paper":null,"slug":"samples-on-thin-ice-re-evaluating-adversarial","title":"Samples on Thin Ice: Re-Evaluating Adversarial Pruning of Neural Networks","date":"2023-10-12","arxiv_id":"2310.08073","n_code_links":0,"syntology":null},{"paper":"/paper/d2-pruning-message-passing-for-balancing","slug":"d2-pruning-message-passing-for-balancing","title":"D2 Pruning: Message Passing for Balancing Diversity and Difficulty in Data Pruning","date":"2023-10-11","arxiv_id":"2310.07931","n_code_links":1,"syntology":{"ran":7,"of":10,"n_ran_checked":7,"n_instrument":0,"unverified":3,"pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["adymaharana/d2pruning"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"leveraging-hierarchical-feature-sharing-for","title":"Leveraging Hierarchical Feature Sharing for Efficient Dataset Condensation","date":"2023-10-11","arxiv_id":"2310.07506","n_code_links":0,"syntology":null},{"paper":"/paper/filter-pruning-for-cnn-with-enhanced-linear","slug":"filter-pruning-for-cnn-with-enhanced-linear","title":"Filter Pruning For CNN With Enhanced Linear Representation Redundancy","date":"2023-10-10","arxiv_id":"2310.06344","n_code_links":1,"syntology":null},{"paper":null,"slug":"rule-mining-for-correcting-classification","title":"Rule Mining for Correcting Classification Models","date":"2023-10-10","arxiv_id":"2310.06446","n_code_links":0,"syntology":null},{"paper":"/paper/sheared-llama-accelerating-language-model-pre","slug":"sheared-llama-accelerating-language-model-pre","title":"Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning","date":"2023-10-10","arxiv_id":"2310.06694","n_code_links":2,"syntology":{"ran":3,"of":3,"n_ran_checked":1,"n_instrument":2,"unverified":0,"pointer_only":0,"phrase":"3 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; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["princeton-nlp/llm-shearing"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/skeleton-ground-truth-extraction-methodology","slug":"skeleton-ground-truth-extraction-methodology","title":"Skeleton Ground Truth Extraction: Methodology, Annotation Tool and Benchmarks","date":"2023-10-10","arxiv_id":"2310.06437","n_code_links":1,"syntology":null},{"paper":"/paper/subp-soft-uniform-block-pruning-for-1xn","slug":"subp-soft-uniform-block-pruning-for-1xn","title":"SUBP: Soft Uniform Block Pruning for 1xN Sparse CNNs Multithreading Acceleration","date":"2023-10-10","arxiv_id":"2310.06218","n_code_links":1,"syntology":{"ran":2,"of":3,"n_ran_checked":1,"n_instrument":1,"unverified":1,"pointer_only":3,"phrase":"2 ran (of which 1 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) · 1 unverified","official":{"repos":["JingyangXiang/SUBP"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/compressing-context-to-enhance-inference","slug":"compressing-context-to-enhance-inference","title":"Compressing Context to Enhance Inference Efficiency of Large Language Models","date":"2023-10-09","arxiv_id":"2310.06201","n_code_links":2,"syntology":{"ran":1,"of":2,"n_ran_checked":1,"n_instrument":0,"unverified":1,"pointer_only":2,"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) · 1 unverified","official":{"repos":["liyucheng09/selective_context"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/no-token-left-behind-efficient-vision","slug":"no-token-left-behind-efficient-vision","title":"No Token Left Behind: Efficient Vision Transformer via Dynamic Token Idling","date":"2023-10-09","arxiv_id":"2310.05654","n_code_links":1,"syntology":null},{"paper":"/paper/compresso-structured-pruning-with","slug":"compresso-structured-pruning-with","title":"Compresso: Structured Pruning with Collaborative Prompting Learns Compact Large Language Models","date":"2023-10-08","arxiv_id":"2310.05015","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"pointer_only":1,"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":{"repos":["microsoft/moonlit"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/outlier-weighed-layerwise-sparsity-owl-a","slug":"outlier-weighed-layerwise-sparsity-owl-a","title":"Outlier Weighed Layerwise Sparsity (OWL): A Missing Secret Sauce for Pruning LLMs to High Sparsity","date":"2023-10-08","arxiv_id":"2310.05175","n_code_links":1,"syntology":{"ran":2,"of":6,"n_ran_checked":2,"n_instrument":0,"unverified":4,"pointer_only":0,"phrase":"2 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","official":{"repos":["luuyin/owl"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/robust-network-pruning-with-sparse-entropic","slug":"robust-network-pruning-with-sparse-entropic","title":"SWAP: Sparse Entropic Wasserstein Regression for Robust Network Pruning","date":"2023-10-07","arxiv_id":"2310.04918","n_code_links":1,"syntology":{"ran":5,"of":5,"n_ran_checked":4,"n_instrument":1,"unverified":0,"pointer_only":5,"phrase":"5 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; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["youlei202/entropic-wasserstein-pruning"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"the-cost-of-down-scaling-language-models-fact","title":"The Cost of Down-Scaling Language Models: Fact Recall Deteriorates before In-Context Learning","date":"2023-10-07","arxiv_id":"2310.04680","n_code_links":0,"syntology":null},{"paper":null,"slug":"can-pruning-make-large-language-models-more","title":"Can pruning make Large Language Models more efficient?","date":"2023-10-06","arxiv_id":"2310.04573","n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-stability-in-simultaneous-speech","title":"Improving Stability in Simultaneous Speech Translation: A Revision-Controllable Decoding Approach","date":"2023-10-06","arxiv_id":"2310.04399","n_code_links":0,"syntology":null},{"paper":null,"slug":"non-redundant-graph-neural-networks-with","title":"On the Two Sides of Redundancy in Graph Neural Networks","date":"2023-10-06","arxiv_id":"2310.04190","n_code_links":0,"syntology":null},{"paper":"/paper/spade-sparsity-guided-debugging-for-deep","slug":"spade-sparsity-guided-debugging-for-deep","title":"SPADE: Sparsity-Guided Debugging for Deep Neural Networks","date":"2023-10-06","arxiv_id":"2310.04519","n_code_links":1,"syntology":{"ran":5,"of":9,"n_ran_checked":3,"n_instrument":2,"unverified":4,"pointer_only":9,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified","official":{"repos":["ist-daslab/spade"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"neural-language-model-pruning-for-automatic","title":"Neural Language Model Pruning for Automatic Speech Recognition","date":"2023-10-05","arxiv_id":"2310.03424","n_code_links":0,"syntology":null},{"paper":null,"slug":"table-grape-inflorescence-detection-and","title":"Table grape inflorescence detection and clamping point localisation based on channel pruned YOLO V7-TP","date":"2023-10-05","arxiv_id":null,"n_code_links":0,"syntology":null}],"record_sha256":"9b68eb1fad30d0c06712c48358199d818f0dd2a6dd4eb32a96b35f53db8fde5b","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}