{"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/13","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":13,"pages_in_order":39,"rows_per_page":100,"rows":[1201,1300],"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/12","next":"/method/pruning/papers/14","papers":[{"paper":"/paper/multi-criteria-token-fusion-with-one-step","slug":"multi-criteria-token-fusion-with-one-step","title":"Multi-criteria Token Fusion with One-step-ahead Attention for Efficient Vision Transformers","date":"2024-03-15","arxiv_id":"2403.10030","n_code_links":1,"syntology":{"ran":3,"of":5,"n_ran_checked":0,"n_instrument":3,"unverified":2,"pointer_only":0,"phrase":"3 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; 3 where Syntology's instrument failed) · 2 unverified","official":{"repos":["mlvlab/mctf"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/adversarial-fine-tuning-of-compressed-neural","slug":"adversarial-fine-tuning-of-compressed-neural","title":"Adversarial Fine-tuning of Compressed Neural Networks for Joint Improvement of Robustness and Efficiency","date":"2024-03-14","arxiv_id":"2403.09441","n_code_links":2,"syntology":null},{"paper":null,"slug":"autodfp-automatic-data-free-pruning-via","title":"AutoDFP: Automatic Data-Free Pruning via Channel Similarity Reconstruction","date":"2024-03-13","arxiv_id":"2403.08204","n_code_links":0,"syntology":null},{"paper":null,"slug":"coronetgan-controlled-pruning-of-gans-via","title":"CoroNetGAN: Controlled Pruning of GANs via Hypernetworks","date":"2024-03-13","arxiv_id":"2403.08261","n_code_links":0,"syntology":null},{"paper":"/paper/smart-submodular-data-mixture-strategy-for","slug":"smart-submodular-data-mixture-strategy-for","title":"SMART: Submodular Data Mixture Strategy for Instruction Tuning","date":"2024-03-13","arxiv_id":"2403.08370","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":1,"n_instrument":3,"unverified":0,"pointer_only":1,"phrase":"4 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; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["kowndinya-renduchintala/smart"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"paper":null,"slug":"distilling-the-knowledge-in-data-pruning","title":"Distilling the Knowledge in Data Pruning","date":"2024-03-12","arxiv_id":"2403.07854","n_code_links":0,"syntology":null},{"paper":null,"slug":"efficient-knowledge-deletion-from-trained","title":"Efficient Knowledge Deletion from Trained Models through Layer-wise Partial Machine Unlearning","date":"2024-03-12","arxiv_id":"2403.07611","n_code_links":0,"syntology":null},{"paper":null,"slug":"maxwell-s-demon-at-work-efficient-pruning-by","title":"Maxwell's Demon at Work: Efficient Pruning by Leveraging Saturation of Neurons","date":"2024-03-12","arxiv_id":"2403.07688","n_code_links":0,"syntology":null},{"paper":null,"slug":"mope-clip-structured-pruning-for-efficient","title":"MoPE-CLIP: Structured Pruning for Efficient Vision-Language Models with Module-wise Pruning Error Metric","date":"2024-03-12","arxiv_id":"2403.07839","n_code_links":0,"syntology":null},{"paper":"/paper/an-image-is-worth-1-2-tokens-after-layer-2","slug":"an-image-is-worth-1-2-tokens-after-layer-2","title":"An Image is Worth 1/2 Tokens After Layer 2: Plug-and-Play Inference Acceleration for Large Vision-Language Models","date":"2024-03-11","arxiv_id":"2403.06764","n_code_links":1,"syntology":{"ran":2,"of":4,"n_ran_checked":0,"n_instrument":2,"unverified":2,"pointer_only":4,"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) · 2 unverified","official":{"repos":["pkunlp-icler/fastv"],"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","unlocated"]}}},{"paper":null,"slug":"enhanced-sparsification-via-stimulative","title":"Enhanced Sparsification via Stimulative Training","date":"2024-03-11","arxiv_id":"2403.06417","n_code_links":0,"syntology":null},{"paper":"/paper/falcon-flop-aware-combinatorial-optimization","slug":"falcon-flop-aware-combinatorial-optimization","title":"FALCON: FLOP-Aware Combinatorial Optimization for Neural Network Pruning","date":"2024-03-11","arxiv_id":"2403.07094","n_code_links":2,"syntology":null},{"paper":null,"slug":"identifying-and-interpreting-non-aligned","title":"Identifying and interpreting non-aligned human conceptual representations using language modeling","date":"2024-03-10","arxiv_id":"2403.06204","n_code_links":0,"syntology":null},{"paper":null,"slug":"optimal-policy-sparsification-and-low-rank","title":"Optimal Policy Sparsification and Low Rank Decomposition for Deep Reinforcement Learning","date":"2024-03-10","arxiv_id":"2403.06313","n_code_links":0,"syntology":null},{"paper":null,"slug":"can-large-language-models-play-games-a-case","title":"Can Large Language Models Play Games? A Case Study of A Self-Play Approach","date":"2024-03-08","arxiv_id":"2403.05632","n_code_links":0,"syntology":null},{"paper":"/paper/map-mask-pruning-for-source-free-model","slug":"map-mask-pruning-for-source-free-model","title":"MAP: MAsk-Pruning for Source-Free Model Intellectual Property Protection","date":"2024-03-07","arxiv_id":"2403.04149","n_code_links":1,"syntology":null},{"paper":"/paper/shortgpt-layers-in-large-language-models-are","slug":"shortgpt-layers-in-large-language-models-are","title":"ShortGPT: Layers in Large Language Models are More Redundant Than You Expect","date":"2024-03-06","arxiv_id":"2403.03853","n_code_links":1,"syntology":null},{"paper":null,"slug":"sparse-spiking-neural-network-exploiting","title":"Sparse Spiking Neural Network: Exploiting Heterogeneity in Timescales for Pruning Recurrent SNN","date":"2024-03-06","arxiv_id":"2403.03409","n_code_links":0,"syntology":null},{"paper":"/paper/a-general-approach-to-enhance-the","slug":"a-general-approach-to-enhance-the","title":"A general approach to enhance the survivability of backdoor attacks by decision path coupling","date":"2024-03-05","arxiv_id":"2403.02950","n_code_links":1,"syntology":null},{"paper":"/paper/dppa-pruning-method-for-large-language-model","slug":"dppa-pruning-method-for-large-language-model","title":"DPPA: Pruning Method for Large Language Model to Model Merging","date":"2024-03-05","arxiv_id":"2403.02799","n_code_links":1,"syntology":null},{"paper":null,"slug":"dynst-dynamic-sparse-training-for-resource","title":"DynST: Dynamic Sparse Training for Resource-Constrained Spatio-Temporal Forecasting","date":"2024-03-05","arxiv_id":"2403.02914","n_code_links":0,"syntology":null},{"paper":null,"slug":"g-evonas-evolutionary-neural-architecture","title":"G-EvoNAS: Evolutionary Neural Architecture Search Based on Network Growth","date":"2024-03-05","arxiv_id":"2403.02667","n_code_links":0,"syntology":null},{"paper":"/paper/madtp-multimodal-alignment-guided-dynamic","slug":"madtp-multimodal-alignment-guided-dynamic","title":"MADTP: Multimodal Alignment-Guided Dynamic Token Pruning for Accelerating Vision-Language Transformer","date":"2024-03-05","arxiv_id":"2403.02991","n_code_links":1,"syntology":{"ran":3,"of":7,"n_ran_checked":2,"n_instrument":1,"unverified":4,"pointer_only":1,"phrase":"3 ran (of which 2 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":["double125/madtp"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/not-all-tickets-are-equal-and-we-know-it","slug":"not-all-tickets-are-equal-and-we-know-it","title":"Pruning neural network models for gene regulatory dynamics using data and domain knowledge","date":"2024-03-05","arxiv_id":"2403.04805","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"pointer_only":2,"phrase":"3 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["quackenbushlab/dash"],"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":["found_in_text","official"]}}},{"paper":"/paper/dyce-dynamic-configurable-exiting-for-deep","slug":"dyce-dynamic-configurable-exiting-for-deep","title":"DyCE: Dynamically Configurable Exiting for Deep Learning Compression and Real-time Scaling","date":"2024-03-04","arxiv_id":"2403.01695","n_code_links":1,"syntology":null},{"paper":null,"slug":"not-all-layers-of-llms-are-necessary-during","title":"Not All Layers of LLMs Are Necessary During Inference","date":"2024-03-04","arxiv_id":"2403.02181","n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-efficient-deep-autoencoders-for","title":"Towards efficient deep autoencoders for multivariate time series anomaly detection","date":"2024-03-04","arxiv_id":"2403.02429","n_code_links":0,"syntology":null},{"paper":null,"slug":"representation-learning-on-heterophilic-graph","title":"Representation Learning on Heterophilic Graph with Directional Neighborhood Attention","date":"2024-03-03","arxiv_id":"2403.01475","n_code_links":0,"syntology":null},{"paper":null,"slug":"structurally-prune-anything-any-architecture","title":"Structurally Prune Anything: Any Architecture, Any Framework, Any Time","date":"2024-03-03","arxiv_id":"2403.18955","n_code_links":0,"syntology":null},{"paper":"/paper/dissecting-language-models-machine-unlearning","slug":"dissecting-language-models-machine-unlearning","title":"Dissecting Language Models: Machine Unlearning via Selective Pruning","date":"2024-03-02","arxiv_id":"2403.01267","n_code_links":1,"syntology":{"ran":3,"of":4,"n_ran_checked":2,"n_instrument":1,"unverified":1,"pointer_only":4,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["nickypro/selective-pruning"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"motif-distribution-and-function-of-sparse","title":"Motif distribution and function of sparse deep neural networks","date":"2024-03-01","arxiv_id":"2403.00974","n_code_links":0,"syntology":null},{"paper":null,"slug":"masks-signs-and-learning-rate-rewinding","title":"Masks, Signs, And Learning Rate Rewinding","date":"2024-02-29","arxiv_id":"2402.19262","n_code_links":0,"syntology":null},{"paper":null,"slug":"prsa-prompt-reverse-stealing-attacks-against","title":"PRSA: Prompt Stealing Attacks against Real-World Prompt Services","date":"2024-02-29","arxiv_id":"2402.19200","n_code_links":0,"syntology":null},{"paper":null,"slug":"t3dnet-compressing-point-cloud-models-for","title":"T3DNet: Compressing Point Cloud Models for Lightweight 3D Recognition","date":"2024-02-29","arxiv_id":"2402.19264","n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-explaining-deep-neural-network","title":"Towards Explaining Deep Neural Network Compression Through a Probabilistic Latent Space","date":"2024-02-29","arxiv_id":"2403.00155","n_code_links":0,"syntology":null},{"paper":"/paper/verification-of-neural-networks-global","slug":"verification-of-neural-networks-global","title":"Verification of Neural Networks' Global Robustness","date":"2024-02-29","arxiv_id":"2402.19322","n_code_links":1,"syntology":null},{"paper":null,"slug":"cutting-off-the-head-ends-the-conflict-a","title":"Cutting Off the Head Ends the Conflict: A Mechanism for Interpreting and Mitigating Knowledge Conflicts in Language Models","date":"2024-02-28","arxiv_id":"2402.18154","n_code_links":0,"syntology":null},{"paper":"/paper/gradient-free-adaptive-global-pruning-for-pre","slug":"gradient-free-adaptive-global-pruning-for-pre","title":"SparseLLM: Towards Global Pruning for Pre-trained Language Models","date":"2024-02-28","arxiv_id":"2402.17946","n_code_links":2,"syntology":{"ran":3,"of":9,"n_ran_checked":2,"n_instrument":1,"unverified":6,"pointer_only":3,"phrase":"3 ran (of which 1 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) · 6 unverified","official":{"repos":["baithebest/adagp","baithebest/sparsellm"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":6,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"reprune-channel-pruning-via-kernel","title":"REPrune: Channel Pruning via Kernel Representative Selection","date":"2024-02-27","arxiv_id":"2402.17862","n_code_links":0,"syntology":null},{"paper":null,"slug":"sequentialattention-for-block-sparsification","title":"SequentialAttention++ for Block Sparsification: Differentiable Pruning Meets Combinatorial Optimization","date":"2024-02-27","arxiv_id":"2402.17902","n_code_links":0,"syntology":null},{"paper":null,"slug":"data-freeweight-compress-and-denoise-for","title":"Data-freeWeight Compress and Denoise for Large Language Models","date":"2024-02-26","arxiv_id":"2402.16319","n_code_links":0,"syntology":null},{"paper":null,"slug":"personalized-federated-instruction-tuning-via","title":"Personalized Federated Instruction Tuning via Neural Architecture Search","date":"2024-02-26","arxiv_id":"2402.16919","n_code_links":0,"syntology":null},{"paper":null,"slug":"skill-similarity-aware-knowledge-distillation","title":"SKILL: Similarity-aware Knowledge distILLation for Speech Self-Supervised Learning","date":"2024-02-26","arxiv_id":"2402.16830","n_code_links":0,"syntology":null},{"paper":null,"slug":"spc-nerf-spatial-predictive-compression-for","title":"SPC-NeRF: Spatial Predictive Compression for Voxel Based Radiance Field","date":"2024-02-26","arxiv_id":"2402.16366","n_code_links":0,"syntology":null},{"paper":null,"slug":"unraveling-babel-exploring-multilingual","title":"Unraveling Babel: Exploring Multilingual Activation Patterns of LLMs and Their Applications","date":"2024-02-26","arxiv_id":"2402.16367","n_code_links":0,"syntology":null},{"paper":"/paper/shaving-weights-with-occam-s-razor-bayesian","slug":"shaving-weights-with-occam-s-razor-bayesian","title":"Shaving Weights with Occam's Razor: Bayesian Sparsification for Neural Networks Using the Marginal Likelihood","date":"2024-02-25","arxiv_id":"2402.15978","n_code_links":1,"syntology":{"ran":6,"of":7,"n_ran_checked":3,"n_instrument":3,"unverified":1,"pointer_only":7,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 3 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","official":{"repos":["fortuinlab/spam-pruning"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"hd-eval-aligning-large-language-model","title":"HD-Eval: Aligning Large Language Model Evaluators Through Hierarchical Criteria Decomposition","date":"2024-02-24","arxiv_id":"2402.15754","n_code_links":0,"syntology":null},{"paper":null,"slug":"training-nonlinear-transformers-for-efficient","title":"How Do Nonlinear Transformers Learn and Generalize in In-Context Learning?","date":"2024-02-23","arxiv_id":"2402.15607","n_code_links":0,"syntology":null},{"paper":"/paper/not-all-experts-are-equal-efficient-expert","slug":"not-all-experts-are-equal-efficient-expert","title":"Not All Experts are Equal: Efficient Expert Pruning and Skipping for Mixture-of-Experts Large Language Models","date":"2024-02-22","arxiv_id":"2402.14800","n_code_links":1,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"0 ran · 1 unverified","official":{"repos":["lucky-lance/expert_sparsity"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"paper":null,"slug":"propd-dynamic-token-tree-pruning-and","title":"ProPD: Dynamic Token Tree Pruning and Generation for LLM Parallel Decoding","date":"2024-02-21","arxiv_id":"2402.13485","n_code_links":0,"syntology":null},{"paper":null,"slug":"partial-search-in-a-frozen-network-is-enough","title":"Partial Search in a Frozen Network is Enough to Find a Strong Lottery Ticket","date":"2024-02-20","arxiv_id":"2402.14029","n_code_links":0,"syntology":null},{"paper":"/paper/tiny-reinforcement-learning-for-quadruped","slug":"tiny-reinforcement-learning-for-quadruped","title":"Tiny Reinforcement Learning for Quadruped Locomotion using Decision Transformers","date":"2024-02-20","arxiv_id":"2402.13201","n_code_links":1,"syntology":null},{"paper":null,"slug":"in-deep-reinforcement-learning-a-pruned","title":"In value-based deep reinforcement learning, a pruned network is a good network","date":"2024-02-19","arxiv_id":"2402.12479","n_code_links":0,"syntology":null},{"paper":"/paper/interpretable-embedding-for-ad-hoc-video","slug":"interpretable-embedding-for-ad-hoc-video","title":"Interpretable Embedding for Ad-hoc Video Search","date":"2024-02-19","arxiv_id":"2402.11812","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-fisher-information-based-receding-horizon","title":"A Fisher Information based Receding Horizon Control Method for Signal Strength Model Estimation","date":"2024-02-18","arxiv_id":"2402.11483","n_code_links":0,"syntology":null},{"paper":"/paper/besa-pruning-large-language-models-with","slug":"besa-pruning-large-language-models-with","title":"BESA: Pruning Large Language Models with Blockwise Parameter-Efficient Sparsity Allocation","date":"2024-02-18","arxiv_id":"2402.16880","n_code_links":2,"syntology":{"ran":4,"of":10,"n_ran_checked":2,"n_instrument":2,"unverified":6,"pointer_only":10,"phrase":"4 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; 2 where Syntology's instrument failed) · 6 unverified","official":{"repos":["linkanonymous/besa","opengvlab/llmprune-besa"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":6,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"extraction-of-nonlinearity-in-neural-networks","title":"Extraction of nonlinearity in neural networks with Koopman operator","date":"2024-02-18","arxiv_id":"2402.11740","n_code_links":0,"syntology":null},{"paper":null,"slug":"self-evolving-autoencoder-embedded-q-network","title":"Self-evolving Autoencoder Embedded Q-Network","date":"2024-02-18","arxiv_id":"2402.11604","n_code_links":0,"syntology":null},{"paper":null,"slug":"why-lift-so-heavy-slimming-large-language","title":"Why Lift so Heavy? Slimming Large Language Models by Cutting Off the Layers","date":"2024-02-18","arxiv_id":"2402.11700","n_code_links":0,"syntology":null},{"paper":"/paper/laco-large-language-model-pruning-via-layer","slug":"laco-large-language-model-pruning-via-layer","title":"LaCo: Large Language Model Pruning via Layer Collapse","date":"2024-02-17","arxiv_id":"2402.11187","n_code_links":2,"syntology":null},{"paper":"/paper/distilled-gradual-pruning-with-pruned-fine","slug":"distilled-gradual-pruning-with-pruned-fine","title":"Distilled Gradual Pruning with Pruned Fine-tuning","date":"2024-02-15","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/nuteprune-efficient-progressive-pruning-with","slug":"nuteprune-efficient-progressive-pruning-with","title":"NutePrune: Efficient Progressive Pruning with Numerous Teachers for Large Language Models","date":"2024-02-15","arxiv_id":"2402.09773","n_code_links":1,"syntology":{"ran":9,"of":16,"n_ran_checked":5,"n_instrument":4,"unverified":7,"pointer_only":16,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 4 where Syntology's instrument failed) · 7 unverified","official":{"repos":["lucius-lsr/nuteprune"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":7,"ran_from_kinds":["official"]}}},{"paper":"/paper/what-to-do-when-your-discrete-optimization-is","slug":"what-to-do-when-your-discrete-optimization-is","title":"What to Do When Your Discrete Optimization Is the Size of a Neural Network?","date":"2024-02-15","arxiv_id":"2402.10339","n_code_links":1,"syntology":null},{"paper":null,"slug":"fgeo-tp-a-language-model-enhanced-solver-for","title":"FGeo-TP: A Language Model-Enhanced Solver for Geometry Problems","date":"2024-02-14","arxiv_id":"2402.09047","n_code_links":0,"syntology":null},{"paper":"/paper/get-more-with-less-synthesizing-recurrence","slug":"get-more-with-less-synthesizing-recurrence","title":"Get More with LESS: Synthesizing Recurrence with KV Cache Compression for Efficient LLM Inference","date":"2024-02-14","arxiv_id":"2402.09398","n_code_links":1,"syntology":{"ran":12,"of":17,"n_ran_checked":10,"n_instrument":2,"unverified":5,"pointer_only":17,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 1 violated, 9 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified","official":{"repos":["hdong920/less"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":"/paper/lightweight-deep-learning-based-channel","slug":"lightweight-deep-learning-based-channel","title":"Lightweight Deep Learning Based Channel Estimation for Extremely Large-Scale Massive MIMO Systems","date":"2024-02-14","arxiv_id":"2402.08916","n_code_links":1,"syntology":null},{"paper":"/paper/sleb-streamlining-llms-through-redundancy","slug":"sleb-streamlining-llms-through-redundancy","title":"SLEB: Streamlining LLMs through Redundancy Verification and Elimination of Transformer Blocks","date":"2024-02-14","arxiv_id":"2402.09025","n_code_links":1,"syntology":{"ran":6,"of":12,"n_ran_checked":3,"n_instrument":3,"unverified":6,"pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 3 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 6 unverified","official":{"repos":["jiwonsong-dev/sleb"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":6,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"data-reconstruction-attacks-and-defenses-a","title":"Data Reconstruction Attacks and Defenses: A Systematic Evaluation","date":"2024-02-13","arxiv_id":"2402.09478","n_code_links":0,"syntology":null},{"paper":"/paper/fedlps-heterogeneous-federated-learning-for","slug":"fedlps-heterogeneous-federated-learning-for","title":"FedLPS: Heterogeneous Federated Learning for Multiple Tasks with Local Parameter Sharing","date":"2024-02-13","arxiv_id":"2402.08578","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 2 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; every one of the 2 samples that ran constructed an object rather than computing a result","official":{"repos":["jyzgh/fedlps"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"differentially-private-zeroth-order-methods","title":"Differentially Private Zeroth-Order Methods for Scalable Large Language Model Finetuning","date":"2024-02-12","arxiv_id":"2402.07818","n_code_links":0,"syntology":null},{"paper":null,"slug":"generalising-planning-environment-redesign","title":"Generalising Planning Environment Redesign","date":"2024-02-12","arxiv_id":"2402.07799","n_code_links":0,"syntology":null},{"paper":null,"slug":"lora-drop-efficient-lora-parameter-pruning","title":"LoRA-drop: Efficient LoRA Parameter Pruning based on Output Evaluation","date":"2024-02-12","arxiv_id":"2402.07721","n_code_links":0,"syntology":null},{"paper":"/paper/towards-meta-pruning-via-optimal-transport","slug":"towards-meta-pruning-via-optimal-transport","title":"Towards Meta-Pruning via Optimal Transport","date":"2024-02-12","arxiv_id":"2402.07839","n_code_links":1,"syntology":{"ran":5,"of":5,"n_ran_checked":5,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["alexandertheus/intra-fusion"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/on-the-effectiveness-of-machine-learning","slug":"on-the-effectiveness-of-machine-learning","title":"On the Effectiveness of Machine Learning-based Call Graph Pruning: An Empirical Study","date":"2024-02-11","arxiv_id":"2402.07294","n_code_links":1,"syntology":null},{"paper":null,"slug":"discriminative-adversarial-unlearning","title":"Discriminative Adversarial Unlearning","date":"2024-02-10","arxiv_id":"2402.06864","n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-attributed-graphlets-predictive","title":"Learning Attributed Graphlets: Predictive Graph Mining by Graphlets with Trainable Attribute","date":"2024-02-10","arxiv_id":"2402.06932","n_code_links":0,"syntology":null},{"paper":"/paper/everybody-prune-now-structured-pruning-of","slug":"everybody-prune-now-structured-pruning-of","title":"Everybody Prune Now: Structured Pruning of LLMs with only Forward Passes","date":"2024-02-08","arxiv_id":"2402.05406","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":1,"n_instrument":2,"unverified":0,"pointer_only":2,"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":["ldery/bonsai"],"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","unlocated"]}}},{"paper":null,"slug":"exploring-learning-complexity-for-downstream","title":"Exploring Learning Complexity for Efficient Downstream Dataset Pruning","date":"2024-02-08","arxiv_id":"2402.05356","n_code_links":0,"syntology":null},{"paper":null,"slug":"assessing-the-brittleness-of-safety-alignment","title":"Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications","date":"2024-02-07","arxiv_id":"2402.05162","n_code_links":0,"syntology":null},{"paper":null,"slug":"compressing-deep-reinforcement-learning","title":"Compressing Deep Reinforcement Learning Networks with a Dynamic Structured Pruning Method for Autonomous Driving","date":"2024-02-07","arxiv_id":"2402.05146","n_code_links":0,"syntology":null},{"paper":"/paper/less-is-ken-a-universal-and-simple-non","slug":"less-is-ken-a-universal-and-simple-non","title":"Less is KEN: a Universal and Simple Non-Parametric Pruning Algorithm for Large Language Models","date":"2024-02-05","arxiv_id":"2402.03142","n_code_links":1,"syntology":null},{"paper":null,"slug":"mining-a-minimal-set-of-behavioral-patterns","title":"Mining a Minimal Set of Behavioral Patterns using Incremental Evaluation","date":"2024-02-05","arxiv_id":"2402.02921","n_code_links":0,"syntology":null},{"paper":"/paper/rethink-model-re-basin-and-the-linear-mode","slug":"rethink-model-re-basin-and-the-linear-mode","title":"Vanishing Feature: Diagnosing Model Merging and Beyond","date":"2024-02-05","arxiv_id":"2402.05966","n_code_links":2,"syntology":{"ran":2,"of":3,"n_ran_checked":2,"n_instrument":0,"unverified":1,"pointer_only":3,"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) · 1 unverified","official":{"repos":["xingyuqu/rethink-re-basin","xingyuqu/vf"],"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":["official"]}}},{"paper":"/paper/shortened-llama-a-simple-depth-pruning-for","slug":"shortened-llama-a-simple-depth-pruning-for","title":"Shortened LLaMA: Depth Pruning for Large Language Models with Comparison of Retraining Methods","date":"2024-02-05","arxiv_id":"2402.02834","n_code_links":1,"syntology":{"ran":3,"of":6,"n_ran_checked":3,"n_instrument":0,"unverified":3,"pointer_only":6,"phrase":"3 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; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["nota-netspresso/shortened-llm"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/skill-set-optimization-reinforcing-language","slug":"skill-set-optimization-reinforcing-language","title":"Skill Set Optimization: Reinforcing Language Model Behavior via Transferable Skills","date":"2024-02-05","arxiv_id":"2402.03244","n_code_links":1,"syntology":{"ran":2,"of":3,"n_ran_checked":2,"n_instrument":0,"unverified":1,"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) · 1 unverified","official":{"repos":["allenai/sso"],"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":["official"]}}},{"paper":"/paper/pruner-an-efficient-cross-platform-tensor","slug":"pruner-an-efficient-cross-platform-tensor","title":"Pruner: A Speculative Exploration Mechanism to Accelerate Tensor Program Tuning","date":"2024-02-04","arxiv_id":"2402.02361","n_code_links":1,"syntology":null},{"paper":null,"slug":"no-free-prune-information-theoretic-barriers","title":"No Free Prune: Information-Theoretic Barriers to Pruning at Initialization","date":"2024-02-02","arxiv_id":"2402.01089","n_code_links":0,"syntology":null},{"paper":null,"slug":"training-time-neuron-alignment-through","title":"Training-time Neuron Alignment through Permutation Subspace for Improving Linear Mode Connectivity and Model Fusion","date":"2024-02-02","arxiv_id":"2402.01342","n_code_links":0,"syntology":null},{"paper":null,"slug":"easrec-elastic-architecture-search-for","title":"DNS-Rec: Data-aware Neural Architecture Search for Recommender Systems","date":"2024-02-01","arxiv_id":"2402.00390","n_code_links":0,"syntology":null},{"paper":null,"slug":"effective-multi-stage-training-model-for-edge","title":"Effective Multi-Stage Training Model For Edge Computing Devices In Intrusion Detection","date":"2024-01-31","arxiv_id":"2401.17546","n_code_links":0,"syntology":null},{"paper":null,"slug":"epsd-early-pruning-with-self-distillation-for","title":"EPSD: Early Pruning with Self-Distillation for Efficient Model Compression","date":"2024-01-31","arxiv_id":"2402.00084","n_code_links":0,"syntology":null},{"paper":"/paper/pf-gnn-differentiable-particle-filtering-1","slug":"pf-gnn-differentiable-particle-filtering-1","title":"PF-GNN: Differentiable particle filtering based approximation of universal graph representations","date":"2024-01-31","arxiv_id":"2401.17752","n_code_links":1,"syntology":{"ran":0,"of":2,"n_ran_checked":0,"n_instrument":0,"unverified":2,"pointer_only":2,"phrase":"0 ran · 2 unverified","official":{"repos":["pfgnn/pf-gnn"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":[]}}},{"paper":"/paper/pipenet-question-answering-with-semantic","slug":"pipenet-question-answering-with-semantic","title":"PipeNet: Question Answering with Semantic Pruning over Knowledge Graphs","date":"2024-01-31","arxiv_id":"2401.17536","n_code_links":1,"syntology":null},{"paper":"/paper/data-efficient-fine-tuning-for-llm-based","slug":"data-efficient-fine-tuning-for-llm-based","title":"Data-efficient Fine-tuning for LLM-based Recommendation","date":"2024-01-30","arxiv_id":"2401.17197","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":1,"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":["linxyhaha/dealrec"],"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":"revisiting-gradient-pruning-a-dual","title":"Revisiting Gradient Pruning: A Dual Realization for Defending against Gradient Attacks","date":"2024-01-30","arxiv_id":"2401.16687","n_code_links":0,"syntology":null},{"paper":"/paper/scaling-sparse-fine-tuning-to-large-language","slug":"scaling-sparse-fine-tuning-to-large-language","title":"Scaling Sparse Fine-Tuning to Large Language Models","date":"2024-01-29","arxiv_id":"2401.16405","n_code_links":2,"syntology":{"ran":13,"of":15,"n_ran_checked":9,"n_instrument":4,"unverified":2,"pointer_only":5,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 2 honoured, 0 violated, 7 with no contract checked; 4 where Syntology's instrument failed) · 2 unverified","official":{"repos":["alanansell/peft","ducdauge/sft-llm"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":2,"ran_from_kinds":["official","unlocated"]}}},{"paper":null,"slug":"lite-snn-designing-lightweight-and-efficient","title":"LitE-SNN: Designing Lightweight and Efficient Spiking Neural Network through Spatial-Temporal Compressive Network Search and Joint Optimization","date":"2024-01-26","arxiv_id":"2401.14652","n_code_links":0,"syntology":null},{"paper":null,"slug":"recognizing-multiple-ingredients-in-food","title":"Recognizing Multiple Ingredients in Food Images Using a Single-Ingredient Classification Model","date":"2024-01-26","arxiv_id":"2401.14579","n_code_links":0,"syntology":null},{"paper":"/paper/prunesymnet-a-symbolic-neural-network-and","slug":"prunesymnet-a-symbolic-neural-network-and","title":"PruneSymNet: A Symbolic Neural Network and Pruning Algorithm for Symbolic Regression","date":"2024-01-25","arxiv_id":"2401.15103","n_code_links":1,"syntology":null},{"paper":null,"slug":"pragmatic-communication-in-multi-agent","title":"Pragmatic Communication in Multi-Agent Collaborative Perception","date":"2024-01-23","arxiv_id":"2401.12694","n_code_links":0,"syntology":null}],"record_sha256":"e637bc1285c07e5aa688f59cad6c7277d4d60cd23418d4f1a277e1b0f6b32477","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}