{"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/7","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":7,"pages_in_order":39,"rows_per_page":100,"rows":[601,700],"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/6","next":"/method/pruning/papers/8","papers":[{"paper":"/paper/libragrad-balancing-gradient-flow-for","slug":"libragrad-balancing-gradient-flow-for","title":"LibraGrad: Balancing Gradient Flow for Universally Better Vision Transformer Attributions","date":"2024-11-24","arxiv_id":"2411.16760","n_code_links":1,"syntology":null},{"paper":"/paper/reassessing-layer-pruning-in-llms-new","slug":"reassessing-layer-pruning-in-llms-new","title":"Reassessing Layer Pruning in LLMs: New Insights and Methods","date":"2024-11-23","arxiv_id":"2411.15558","n_code_links":1,"syntology":null},{"paper":"/paper/dycoke-dynamic-compression-of-tokens-for-fast","slug":"dycoke-dynamic-compression-of-tokens-for-fast","title":"DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Models","date":"2024-11-22","arxiv_id":"2411.15024","n_code_links":1,"syntology":{"ran":7,"of":14,"n_ran_checked":2,"n_instrument":5,"unverified":7,"pointer_only":6,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 1 violated, 1 with no contract checked; 5 where Syntology's instrument failed) · 7 unverified","official":{"repos":["kd-tao/dycoke"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":6,"ran_from_kinds":["official","unlocated"]}}},{"paper":null,"slug":"efficient-pruning-of-text-to-image-models","title":"Efficient Pruning of Text-to-Image Models: Insights from Pruning Stable Diffusion","date":"2024-11-22","arxiv_id":"2411.15113","n_code_links":0,"syntology":null},{"paper":null,"slug":"automixq-self-adjusting-quantization-for-high","title":"AutoMixQ: Self-Adjusting Quantization for High Performance Memory-Efficient Fine-Tuning","date":"2024-11-21","arxiv_id":"2411.13814","n_code_links":0,"syntology":null},{"paper":"/paper/drpruning-efficient-large-language-model","slug":"drpruning-efficient-large-language-model","title":"DRPruning: Efficient Large Language Model Pruning through Distributionally Robust Optimization","date":"2024-11-21","arxiv_id":"2411.14055","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":1,"n_instrument":1,"unverified":0,"pointer_only":1,"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":["hexuandeng/drpruning"],"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","unlocated"]}}},{"paper":null,"slug":"fopru-focal-pruning-for-efficient-large","title":"FoPru: Focal Pruning for Efficient Large Vision-Language Models","date":"2024-11-21","arxiv_id":"2411.14164","n_code_links":0,"syntology":null},{"paper":"/paper/fusegpt-learnable-layers-fusion-of-generative","slug":"fusegpt-learnable-layers-fusion-of-generative","title":"FuseGPT: Learnable Layers Fusion of Generative Pre-trained Transformers","date":"2024-11-21","arxiv_id":"2411.14507","n_code_links":1,"syntology":null},{"paper":"/paper/layer-pruning-with-consensus-a-triple-win","slug":"layer-pruning-with-consensus-a-triple-win","title":"Layer Pruning with Consensus: A Triple-Win Solution","date":"2024-11-21","arxiv_id":"2411.14345","n_code_links":1,"syntology":null},{"paper":"/paper/adversarial-diffusion-compression-for-real","slug":"adversarial-diffusion-compression-for-real","title":"Adversarial Diffusion Compression for Real-World Image Super-Resolution","date":"2024-11-20","arxiv_id":"2411.13383","n_code_links":2,"syntology":{"ran":10,"of":14,"n_ran_checked":8,"n_instrument":2,"unverified":4,"pointer_only":4,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified","official":{"repos":["guaishou74851/adcsr"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/on-device-content-based-recommendation-with","slug":"on-device-content-based-recommendation-with","title":"On-device Content-based Recommendation with Single-shot Embedding Pruning: A Cooperative Game Perspective","date":"2024-11-20","arxiv_id":"2411.13052","n_code_links":1,"syntology":null},{"paper":null,"slug":"c-2-inet-realizing-incremental-trajectory","title":"C$^{2}$INet: Realizing Incremental Trajectory Prediction with Prior-Aware Continual Causal Intervention","date":"2024-11-19","arxiv_id":"2411.12313","n_code_links":0,"syntology":null},{"paper":"/paper/data-pruning-in-generative-diffusion-models","slug":"data-pruning-in-generative-diffusion-models","title":"Data Pruning in Generative Diffusion Models","date":"2024-11-19","arxiv_id":"2411.12523","n_code_links":1,"syntology":null},{"paper":null,"slug":"detrigger-a-gradient-centric-approach-to","title":"DeTrigger: A Gradient-Centric Approach to Backdoor Attack Mitigation in Federated Learning","date":"2024-11-19","arxiv_id":"2411.12220","n_code_links":0,"syntology":null},{"paper":"/paper/fgp-feature-gradient-prune-for-efficient","slug":"fgp-feature-gradient-prune-for-efficient","title":"FGP: Feature-Gradient-Prune for Efficient Convolutional Layer Pruning","date":"2024-11-19","arxiv_id":"2411.12781","n_code_links":1,"syntology":null},{"paper":null,"slug":"sparser-training-for-on-device-recommendation","title":"Sparser Training for On-Device Recommendation Systems","date":"2024-11-19","arxiv_id":"2411.12205","n_code_links":0,"syntology":null},{"paper":"/paper/distill-the-best-ignore-the-rest-improving","slug":"distill-the-best-ignore-the-rest-improving","title":"Distill the Best, Ignore the Rest: Improving Dataset Distillation with Loss-Value-Based Pruning","date":"2024-11-18","arxiv_id":"2411.12115","n_code_links":1,"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":["Brian-Moser/prune_and_distill"],"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":null,"slug":"just-leaf-it-accelerating-diffusion","title":"Just Leaf It: Accelerating Diffusion Classifiers with Hierarchical Class Pruning","date":"2024-11-18","arxiv_id":"2411.12073","n_code_links":0,"syntology":null},{"paper":null,"slug":"electrostatic-force-regularization-for-neural","title":"Electrostatic Force Regularization for Neural Structured Pruning","date":"2024-11-17","arxiv_id":"2411.11079","n_code_links":0,"syntology":null},{"paper":null,"slug":"enabling-explainable-recommendation-in-e","title":"Enabling Explainable Recommendation in E-commerce with LLM-powered Product Knowledge Graph","date":"2024-11-17","arxiv_id":"2412.01837","n_code_links":0,"syntology":null},{"paper":"/paper/an-exploration-of-the-effect-of-quantisation","slug":"an-exploration-of-the-effect-of-quantisation","title":"An exploration of the effect of quantisation on energy consumption and inference time of StarCoder2","date":"2024-11-15","arxiv_id":"2411.12758","n_code_links":1,"syntology":null},{"paper":"/paper/efficient-density-control-for-3d-gaussian","slug":"efficient-density-control-for-3d-gaussian","title":"Efficient Density Control for 3D Gaussian Splatting","date":"2024-11-15","arxiv_id":"2411.10133","n_code_links":1,"syntology":{"ran":8,"of":10,"n_ran_checked":8,"n_instrument":0,"unverified":2,"pointer_only":10,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 2 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["XiaoBin2001/EDC"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"layer-importance-and-hallucination-analysis","title":"Layer Importance and Hallucination Analysis in Large Language Models via Enhanced Activation Variance-Sparsity","date":"2024-11-15","arxiv_id":"2411.10069","n_code_links":0,"syntology":null},{"paper":null,"slug":"redtest-towards-measuring-redundancy-in-deep","title":"RedTest: Towards Measuring Redundancy in Deep Neural Networks Effectively","date":"2024-11-15","arxiv_id":"2411.10507","n_code_links":0,"syntology":null},{"paper":null,"slug":"scaling-law-for-post-training-after-model","title":"P$^2$ Law: Scaling Law for Post-Training After Model Pruning","date":"2024-11-15","arxiv_id":"2411.10272","n_code_links":0,"syntology":null},{"paper":null,"slug":"systolic-arrays-and-structured-pruning-co","title":"Systolic Arrays and Structured Pruning Co-design for Efficient Transformers in Edge Systems","date":"2024-11-15","arxiv_id":"2411.10285","n_code_links":0,"syntology":null},{"paper":"/paper/the-spatial-complexity-of-optical-computing","slug":"the-spatial-complexity-of-optical-computing","title":"The Spatial Complexity of Optical Computing and How to Reduce It","date":"2024-11-15","arxiv_id":"2411.10435","n_code_links":1,"syntology":null},{"paper":null,"slug":"complexity-aware-training-of-deep-neural","title":"Complexity-Aware Training of Deep Neural Networks for Optimal Structure Discovery","date":"2024-11-14","arxiv_id":"2411.09127","n_code_links":0,"syntology":null},{"paper":null,"slug":"ghost-connect-net-a-generalization-enhanced","title":"Ghost-Connect Net: A Generalization-Enhanced Guidance For Sparse Deep Networks Under Distribution Shifts","date":"2024-11-14","arxiv_id":"2411.09199","n_code_links":0,"syntology":null},{"paper":"/paper/scan-bootstrapping-contrastive-pre-training","slug":"scan-bootstrapping-contrastive-pre-training","title":"SCAN: Bootstrapping Contrastive Pre-training for Data Efficiency","date":"2024-11-14","arxiv_id":"2411.09126","n_code_links":1,"syntology":null},{"paper":null,"slug":"efficient-3d-perception-on-multi-sweep-point","title":"Efficient 3D Perception on Multi-Sweep Point Cloud with Gumbel Spatial Pruning","date":"2024-11-12","arxiv_id":"2411.07742","n_code_links":0,"syntology":null},{"paper":null,"slug":"how-to-discover-short-shorter-and-the","title":"How To Discover Short, Shorter, and the Shortest Proofs of Unsatisfiability: A Branch-and-Bound Approach for Resolution Proof Length Minimization","date":"2024-11-12","arxiv_id":"2411.07955","n_code_links":0,"syntology":null},{"paper":"/paper/owled-outlier-weighed-layerwise-pruning-for","slug":"owled-outlier-weighed-layerwise-pruning-for","title":"OWLed: Outlier-weighed Layerwise Pruning for Efficient Autonomous Driving Framework","date":"2024-11-12","arxiv_id":"2411.07711","n_code_links":1,"syntology":null},{"paper":"/paper/federated-learning-client-pruning-for-noisy","slug":"federated-learning-client-pruning-for-noisy","title":"Federated Learning Client Pruning for Noisy Labels","date":"2024-11-11","arxiv_id":"2411.07391","n_code_links":1,"syntology":null},{"paper":"/paper/the-super-weight-in-large-language-models","slug":"the-super-weight-in-large-language-models","title":"The Super Weight in Large Language Models","date":"2024-11-11","arxiv_id":"2411.07191","n_code_links":1,"syntology":{"ran":4,"of":8,"n_ran_checked":4,"n_instrument":0,"unverified":4,"pointer_only":8,"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) · 4 unverified","official":{"repos":["mengxiayu/llmsuperweight"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/zeroth-order-adaptive-neuron-alignment-based","slug":"zeroth-order-adaptive-neuron-alignment-based","title":"Zeroth-Order Adaptive Neuron Alignment Based Pruning without Re-Training","date":"2024-11-11","arxiv_id":"2411.07066","n_code_links":1,"syntology":null},{"paper":null,"slug":"cull-mt-compression-using-language-and-layer","title":"CULL-MT: Compression Using Language and Layer pruning for Machine Translation","date":"2024-11-10","arxiv_id":"2411.06506","n_code_links":0,"syntology":null},{"paper":"/paper/rl-pruner-structured-pruning-using","slug":"rl-pruner-structured-pruning-using","title":"RL-Pruner: Structured Pruning Using Reinforcement Learning for CNN Compression and Acceleration","date":"2024-11-10","arxiv_id":"2411.06463","n_code_links":1,"syntology":null},{"paper":null,"slug":"fggp-fixed-rate-gradient-first-gradual","title":"FGGP: Fixed-Rate Gradient-First Gradual Pruning","date":"2024-11-08","arxiv_id":"2411.05500","n_code_links":0,"syntology":null},{"paper":null,"slug":"how-good-is-your-wikipedia","title":"How Good is Your Wikipedia? Auditing Data Quality for Low-resource and Multilingual NLP","date":"2024-11-08","arxiv_id":"2411.05527","n_code_links":0,"syntology":null},{"paper":"/paper/microscopiq-accelerating-foundational-models","slug":"microscopiq-accelerating-foundational-models","title":"MicroScopiQ: Accelerating Foundational Models through Outlier-Aware Microscaling Quantization","date":"2024-11-08","arxiv_id":"2411.05282","n_code_links":1,"syntology":{"ran":6,"of":12,"n_ran_checked":4,"n_instrument":2,"unverified":6,"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) · 6 unverified","official":{"repos":["georgia-tech-synergy-lab/microscopiq-llm-quantization"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":6,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"quancrypt-fl-quantized-homomorphic-encryption","title":"QuanCrypt-FL: Quantized Homomorphic Encryption with Pruning for Secure Federated Learning","date":"2024-11-08","arxiv_id":"2411.05260","n_code_links":0,"syntology":null},{"paper":null,"slug":"pruning-literals-for-highly-efficient","title":"Pruning Literals for Highly Efficient Explainability at Word Level","date":"2024-11-07","arxiv_id":"2411.04557","n_code_links":0,"syntology":null},{"paper":"/paper/an-edge-computing-based-solution-for-real","slug":"an-edge-computing-based-solution-for-real","title":"An Edge Computing-Based Solution for Real-Time Leaf Disease Classification using Thermal Imaging","date":"2024-11-06","arxiv_id":"2411.03835","n_code_links":1,"syntology":null},{"paper":null,"slug":"human-in-the-loop-feature-selection-using","title":"Human-in-the-Loop Feature Selection Using Interpretable Kolmogorov-Arnold Network-based Double Deep Q-Network","date":"2024-11-06","arxiv_id":"2411.03740","n_code_links":0,"syntology":null},{"paper":"/paper/optimal-defenses-against-gradient","slug":"optimal-defenses-against-gradient","title":"Optimal Defenses Against Gradient Reconstruction Attacks","date":"2024-11-06","arxiv_id":"2411.03746","n_code_links":1,"syntology":null},{"paper":null,"slug":"towards-resource-efficient-federated-learning","title":"Towards Resource-Efficient Federated Learning in Industrial IoT for Multivariate Time Series Analysis","date":"2024-11-06","arxiv_id":"2411.03996","n_code_links":0,"syntology":null},{"paper":"/paper/change-is-the-only-constant-dynamic-llm","slug":"change-is-the-only-constant-dynamic-llm","title":"Change Is the Only Constant: Dynamic LLM Slicing based on Layer Redundancy","date":"2024-11-05","arxiv_id":"2411.03513","n_code_links":1,"syntology":null},{"paper":"/paper/htmlrag-html-is-better-than-plain-text-for","slug":"htmlrag-html-is-better-than-plain-text-for","title":"HtmlRAG: HTML is Better Than Plain Text for Modeling Retrieved Knowledge in RAG Systems","date":"2024-11-05","arxiv_id":"2411.02959","n_code_links":1,"syntology":null},{"paper":"/paper/layer-adaptive-state-pruning-for-deep-state","slug":"layer-adaptive-state-pruning-for-deep-state","title":"Layer-Adaptive State Pruning for Deep State Space Models","date":"2024-11-05","arxiv_id":"2411.02824","n_code_links":1,"syntology":{"ran":16,"of":18,"n_ran_checked":15,"n_instrument":1,"unverified":2,"pointer_only":18,"phrase":"16 ran (of which 0 constructed an object rather than computing a result; 15 with no instrument failure: 0 honoured, 0 violated, 15 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","official":{"repos":["msgwak/last"],"state":"official (archive's flag): 16 ran","n_ran":16,"n_constructed":0,"n_ran_no_instrument_failure":15,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/navigating-extremes-dynamic-sparsity-in-large","slug":"navigating-extremes-dynamic-sparsity-in-large","title":"Navigating Extremes: Dynamic Sparsity in Large Output Space","date":"2024-11-05","arxiv_id":"2411.03171","n_code_links":1,"syntology":{"ran":6,"of":6,"n_ran_checked":6,"n_instrument":0,"unverified":0,"pointer_only":6,"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) · 0 unverified","official":{"repos":["xmc-aalto/NeurIPS24-dst"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/privacy-preserving-graph-based-machine","slug":"privacy-preserving-graph-based-machine","title":"Privacy-Preserving Graph-Based Machine Learning with Fully Homomorphic Encryption for Collaborative Anti-Money Laundering","date":"2024-11-05","arxiv_id":"2411.02926","n_code_links":1,"syntology":{"ran":8,"of":10,"n_ran_checked":8,"n_instrument":0,"unverified":2,"pointer_only":1,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["fabecode/GraphML-FHE"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/automatic-structured-pruning-for-efficient","slug":"automatic-structured-pruning-for-efficient","title":"Automatic Structured Pruning for Efficient Architecture in Federated Learning","date":"2024-11-04","arxiv_id":"2411.01759","n_code_links":1,"syntology":null},{"paper":null,"slug":"autoformulation-of-mathematical-optimization","title":"Autoformulation of Mathematical Optimization Models Using LLMs","date":"2024-11-03","arxiv_id":"2411.01679","n_code_links":0,"syntology":null},{"paper":null,"slug":"efficient-model-compression-for-bayesian","title":"Efficient Model Compression for Bayesian Neural Networks","date":"2024-11-01","arxiv_id":"2411.00273","n_code_links":0,"syntology":null},{"paper":null,"slug":"magnitude-pruning-of-large-pretrained","title":"Magnitude Pruning of Large Pretrained Transformer Models with a Mixture Gaussian Prior","date":"2024-11-01","arxiv_id":"2411.00969","n_code_links":0,"syntology":null},{"paper":null,"slug":"mbexplainer-multilevel-bandit-based","title":"MBExplainer: Multilevel bandit-based explanations for downstream models with augmented graph embeddings","date":"2024-11-01","arxiv_id":"2411.00287","n_code_links":0,"syntology":null},{"paper":null,"slug":"moe-i-2-compressing-mixture-of-experts-models","title":"MoE-I$^2$: Compressing Mixture of Experts Models through Inter-Expert Pruning and Intra-Expert Low-Rank Decomposition","date":"2024-11-01","arxiv_id":"2411.01016","n_code_links":0,"syntology":null},{"paper":null,"slug":"on-the-impact-of-white-box-deployment","title":"On the Impact of White-box Deployment Strategies for Edge AI on Latency and Model Performance","date":"2024-11-01","arxiv_id":"2411.00907","n_code_links":0,"syntology":null},{"paper":null,"slug":"approximate-attention-with-mlp-a-pruning","title":"RAM: Replace Attention with MLP for Efficient Multivariate Time Series Forecasting","date":"2024-10-31","arxiv_id":"2410.24023","n_code_links":0,"syntology":null},{"paper":null,"slug":"context-aware-token-selection-and-packing-for","title":"Context-Aware Token Selection and Packing for Enhanced Vision Transformer","date":"2024-10-31","arxiv_id":"2410.23608","n_code_links":0,"syntology":null},{"paper":null,"slug":"mutual-information-preserving-neural-network","title":"Mutual Information Preserving Neural Network Pruning","date":"2024-10-31","arxiv_id":"2411.00147","n_code_links":0,"syntology":null},{"paper":"/paper/rsl-sql-robust-schema-linking-in-text-to-sql","slug":"rsl-sql-robust-schema-linking-in-text-to-sql","title":"RSL-SQL: Robust Schema Linking in Text-to-SQL Generation","date":"2024-10-31","arxiv_id":"2411.00073","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":["laqcce-cao/rsl-sql"],"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":"copra-a-progressive-lora-training-strategy","title":"CopRA: A Progressive LoRA Training Strategy","date":"2024-10-30","arxiv_id":"2410.22911","n_code_links":0,"syntology":null},{"paper":null,"slug":"elmgs-enhancing-memory-and-computation","title":"ELMGS: Enhancing memory and computation scaLability through coMpression for 3D Gaussian Splatting","date":"2024-10-30","arxiv_id":"2410.23213","n_code_links":0,"syntology":null},{"paper":null,"slug":"leveraging-recurrent-neural-networks-for-1","title":"Leveraging Recurrent Neural Networks for Predicting Motor Movements from Primate Motor Cortex Neural Recordings","date":"2024-10-29","arxiv_id":"2410.22283","n_code_links":0,"syntology":null},{"paper":null,"slug":"uncovering-capabilities-of-model-pruning-in","title":"Uncovering Capabilities of Model Pruning in Graph Contrastive Learning","date":"2024-10-27","arxiv_id":"2410.20356","n_code_links":0,"syntology":null},{"paper":"/paper/geollava-efficient-fine-tuned-vision-language","slug":"geollava-efficient-fine-tuned-vision-language","title":"GeoLLaVA: Efficient Fine-Tuned Vision-Language Models for Temporal Change Detection in Remote Sensing","date":"2024-10-25","arxiv_id":"2410.19552","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"pointer_only":2,"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":["HosamGen/GeoLLaVA"],"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":"rethinking-visual-dependency-in-long-context","title":"Rethinking Visual Dependency in Long-Context Reasoning for Large Vision-Language Models","date":"2024-10-25","arxiv_id":"2410.19732","n_code_links":0,"syntology":null},{"paper":"/paper/dynamic-vocabulary-pruning-in-early-exit-llms","slug":"dynamic-vocabulary-pruning-in-early-exit-llms","title":"Dynamic Vocabulary Pruning in Early-Exit LLMs","date":"2024-10-24","arxiv_id":"2410.18952","n_code_links":1,"syntology":null},{"paper":"/paper/pixelgaussian-generalizable-3d-gaussian","slug":"pixelgaussian-generalizable-3d-gaussian","title":"PixelGaussian: Generalizable 3D Gaussian Reconstruction from Arbitrary Views","date":"2024-10-24","arxiv_id":"2410.18979","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":["barrybarry-smith/pixelgaussian"],"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":"tailored-llama-optimizing-few-shot-learning","title":"Tailored-LLaMA: Optimizing Few-Shot Learning in Pruned LLaMA Models with Task-Specific Prompts","date":"2024-10-24","arxiv_id":"2410.19185","n_code_links":0,"syntology":null},{"paper":null,"slug":"beware-of-calibration-data-for-pruning-large","title":"Beware of Calibration Data for Pruning Large Language Models","date":"2024-10-23","arxiv_id":"2410.17711","n_code_links":0,"syntology":null},{"paper":null,"slug":"lego-language-model-building-blocks","title":"LEGO: Language Model Building Blocks","date":"2024-10-23","arxiv_id":"2410.18287","n_code_links":0,"syntology":null},{"paper":null,"slug":"petah-parameter-efficient-task-adaptation-for","title":"PETAH: Parameter Efficient Task Adaptation for Hybrid Transformers in a resource-limited Context","date":"2024-10-23","arxiv_id":"2410.17661","n_code_links":0,"syntology":null},{"paper":null,"slug":"theoretically-grounded-pruning-of-large","title":"Theoretically Grounded Pruning of Large Ground Sets for Constrained, Discrete Optimization","date":"2024-10-23","arxiv_id":"2410.17945","n_code_links":0,"syntology":null},{"paper":null,"slug":"dip-go-a-diffusion-pruner-via-few-step","title":"DiP-GO: A Diffusion Pruner via Few-step Gradient Optimization","date":"2024-10-22","arxiv_id":"2410.16942","n_code_links":0,"syntology":null},{"paper":"/paper/math-neurosurgery-isolating-language-models","slug":"math-neurosurgery-isolating-language-models","title":"Math Neurosurgery: Isolating Language Models' Math Reasoning Abilities Using Only Forward Passes","date":"2024-10-22","arxiv_id":"2410.16930","n_code_links":1,"syntology":null},{"paper":"/paper/mitigating-vanishing-activations-in-deep","slug":"mitigating-vanishing-activations-in-deep","title":"Mitigating Vanishing Activations in Deep CapsNets Using Channel Pruning","date":"2024-10-22","arxiv_id":"2410.16908","n_code_links":1,"syntology":null},{"paper":null,"slug":"self-calibration-for-language-model","title":"Self-calibration for Language Model Quantization and Pruning","date":"2024-10-22","arxiv_id":"2410.17170","n_code_links":0,"syntology":null},{"paper":null,"slug":"neural-search-space-in-gboard-decoder","title":"Neural Search Space in Gboard Decoder","date":"2024-10-21","arxiv_id":"2410.15575","n_code_links":0,"syntology":null},{"paper":"/paper/pruning-foundation-models-for-high-accuracy","slug":"pruning-foundation-models-for-high-accuracy","title":"Pruning Foundation Models for High Accuracy without Retraining","date":"2024-10-21","arxiv_id":"2410.15567","n_code_links":1,"syntology":null},{"paper":null,"slug":"small-contributions-small-networks-efficient","title":"Small Contributions, Small Networks: Efficient Neural Network Pruning Based on Relative Importance","date":"2024-10-21","arxiv_id":"2410.16151","n_code_links":0,"syntology":null},{"paper":null,"slug":"beyond-pruning-criteria-the-dominant-role-of","title":"Beyond Pruning Criteria: The Dominant Role of Fine-Tuning and Adaptive Ratios in Neural Network Robustness","date":"2024-10-19","arxiv_id":"2410.15176","n_code_links":0,"syntology":null},{"paper":null,"slug":"dpvs-shapley-faster-and-universal","title":"DPVS-Shapley:Faster and Universal Contribution Evaluation Component in Federated Learning","date":"2024-10-19","arxiv_id":"2410.15093","n_code_links":0,"syntology":null},{"paper":null,"slug":"dmgnn-detecting-and-mitigating-backdoor","title":"DMGNN: Detecting and Mitigating Backdoor Attacks in Graph Neural Networks","date":"2024-10-18","arxiv_id":"2410.14105","n_code_links":0,"syntology":null},{"paper":"/paper/evopress-towards-optimal-dynamic-model","slug":"evopress-towards-optimal-dynamic-model","title":"EvoPress: Towards Optimal Dynamic Model Compression via Evolutionary Search","date":"2024-10-18","arxiv_id":"2410.14649","n_code_links":1,"syntology":{"ran":10,"of":17,"n_ran_checked":5,"n_instrument":5,"unverified":7,"pointer_only":0,"phrase":"10 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; 5 where Syntology's instrument failed) · 7 unverified","official":{"repos":["ist-daslab/evopress"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":7,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"fedspallm-federated-pruning-of-large-language","title":"FedSpaLLM: Federated Pruning of Large Language Models","date":"2024-10-18","arxiv_id":"2410.14852","n_code_links":0,"syntology":null},{"paper":null,"slug":"large-language-models-are-overparameterized","title":"Large Language Models Are Overparameterized Text Encoders","date":"2024-10-18","arxiv_id":"2410.14578","n_code_links":0,"syntology":null},{"paper":"/paper/paths-over-graph-knowledge-graph-enpowered","slug":"paths-over-graph-knowledge-graph-enpowered","title":"Paths-over-Graph: Knowledge Graph Empowered Large Language Model Reasoning","date":"2024-10-18","arxiv_id":"2410.14211","n_code_links":1,"syntology":{"ran":9,"of":12,"n_ran_checked":9,"n_instrument":0,"unverified":3,"pointer_only":2,"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) · 3 unverified","official":null}},{"paper":null,"slug":"the-propensity-for-density-in-feed-forward","title":"The Propensity for Density in Feed-forward Models","date":"2024-10-18","arxiv_id":"2410.14461","n_code_links":0,"syntology":null},{"paper":null,"slug":"treebon-enhancing-inference-time-alignment","title":"TreeBoN: Enhancing Inference-Time Alignment with Speculative Tree-Search and Best-of-N Sampling","date":"2024-10-18","arxiv_id":"2410.16033","n_code_links":0,"syntology":null},{"paper":"/paper/gder-safeguarding-efficiency-balancing-and","slug":"gder-safeguarding-efficiency-balancing-and","title":"GDeR: Safeguarding Efficiency, Balancing, and Robustness via Prototypical Graph Pruning","date":"2024-10-17","arxiv_id":"2410.13761","n_code_links":1,"syntology":{"ran":12,"of":18,"n_ran_checked":10,"n_instrument":2,"unverified":6,"pointer_only":18,"phrase":"12 ran (of which 4 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 0 violated, 9 with no contract checked; 2 where Syntology's instrument failed) · 6 unverified","official":{"repos":["ins1stenc3/gder"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":4,"n_ran_no_instrument_failure":10,"n_unverified":6,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"linguistically-grounded-analysis-of-language","title":"Linguistically Grounded Analysis of Language Models using Shapley Head Values","date":"2024-10-17","arxiv_id":"2410.13396","n_code_links":0,"syntology":null},{"paper":"/paper/llm-rank-a-graph-theoretical-approach-to","slug":"llm-rank-a-graph-theoretical-approach-to","title":"LLM-Rank: A Graph Theoretical Approach to Pruning Large Language Models","date":"2024-10-17","arxiv_id":"2410.13299","n_code_links":1,"syntology":null},{"paper":null,"slug":"long-lrm-long-sequence-large-reconstruction","title":"Long-LRM: Long-sequence Large Reconstruction Model for Wide-coverage Gaussian Splats","date":"2024-10-16","arxiv_id":"2410.12781","n_code_links":0,"syntology":null},{"paper":"/paper/rethinking-token-reduction-for-state-space","slug":"rethinking-token-reduction-for-state-space","title":"Rethinking Token Reduction for State Space Models","date":"2024-10-16","arxiv_id":"2410.14725","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":2,"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":["wuyushuwys/tor_ssm"],"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/tokens-on-demand-token-condensation-as","slug":"tokens-on-demand-token-condensation-as","title":"Is Less More? Exploring Token Condensation as Training-free Adaptation for CLIP","date":"2024-10-16","arxiv_id":"2410.14729","n_code_links":1,"syntology":null},{"paper":null,"slug":"beyond-linear-approximations-a-novel-pruning","title":"Beyond Linear Approximations: A Novel Pruning Approach for Attention Matrix","date":"2024-10-15","arxiv_id":"2410.11261","n_code_links":0,"syntology":null},{"paper":"/paper/disp-llm-dimension-independent-structural","slug":"disp-llm-dimension-independent-structural","title":"DISP-LLM: Dimension-Independent Structural Pruning for Large Language Models","date":"2024-10-15","arxiv_id":"2410.11988","n_code_links":1,"syntology":{"ran":7,"of":7,"n_ran_checked":2,"n_instrument":5,"unverified":0,"pointer_only":3,"phrase":"7 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; 5 where Syntology's instrument failed) · 0 unverified","official":{"repos":["ZhengaoLi/DISP-LLM-Dimension-Independent-Structural-Pruning"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}}],"record_sha256":"02bc1b856469d63e07b8b89749d8e14fda1e2d85c50275b55cbd9150cd2b774e","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}