{"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/5","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":5,"pages_in_order":39,"rows_per_page":100,"rows":[401,500],"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/4","next":"/method/pruning/papers/6","papers":[{"paper":"/paper/kvtuner-sensitivity-aware-layer-wise-mixed","slug":"kvtuner-sensitivity-aware-layer-wise-mixed","title":"KVTuner: Sensitivity-Aware Layer-wise Mixed Precision KV Cache Quantization for Efficient and Nearly Lossless LLM Inference","date":"2025-02-06","arxiv_id":"2502.04420","n_code_links":1,"syntology":null},{"paper":"/paper/mxmap-a-multivariate-cross-mapping-framework","slug":"mxmap-a-multivariate-cross-mapping-framework","title":"MXMap: A Multivariate Cross Mapping Framework for Causal Discovery in Dynamical Systems","date":"2025-02-06","arxiv_id":"2502.03802","n_code_links":1,"syntology":null},{"paper":null,"slug":"unicp-a-unified-caching-and-pruning-framework","title":"UniCP: A Unified Caching and Pruning Framework for Efficient Video Generation","date":"2025-02-06","arxiv_id":"2502.04393","n_code_links":0,"syntology":null},{"paper":null,"slug":"adapt-pruner-adaptive-structural-pruning-for","title":"Adapt-Pruner: Adaptive Structural Pruning for Efficient Small Language Model Training","date":"2025-02-05","arxiv_id":"2502.03460","n_code_links":0,"syntology":null},{"paper":null,"slug":"deep-weight-factorization-sparse-learning","title":"Deep Weight Factorization: Sparse Learning Through the Lens of Artificial Symmetries","date":"2025-02-04","arxiv_id":"2502.02496","n_code_links":0,"syntology":null},{"paper":"/paper/gp-gs-gaussian-processes-for-enhanced","slug":"gp-gs-gaussian-processes-for-enhanced","title":"GP-GS: Gaussian Processes for Enhanced Gaussian Splatting","date":"2025-02-04","arxiv_id":"2502.02283","n_code_links":1,"syntology":null},{"paper":null,"slug":"prompt-based-depth-pruning-of-large-language","title":"Prompt-based Depth Pruning of Large Language Models","date":"2025-02-04","arxiv_id":"2502.04348","n_code_links":0,"syntology":null},{"paper":null,"slug":"pruning-aware-loss-functions-for-stoi","title":"Pruning-aware Loss Functions for STOI-Optimized Pruned Recurrent Autoencoders for the Compression of the Stimulation Patterns of Cochlear Implants at Zero Delay","date":"2025-02-04","arxiv_id":"2502.02424","n_code_links":0,"syntology":null},{"paper":null,"slug":"reachability-based-contingency-planning","title":"Reachability-Based Contingency Planning against Multi-Modal Predictions with Branch MPC","date":"2025-02-04","arxiv_id":"2502.02550","n_code_links":0,"syntology":null},{"paper":null,"slug":"choose-your-model-size-any-compression-by-a","title":"Choose Your Model Size: Any Compression by a Single Gradient Descent","date":"2025-02-03","arxiv_id":"2502.01717","n_code_links":0,"syntology":null},{"paper":"/paper/progressive-binarization-with-semi-structured","slug":"progressive-binarization-with-semi-structured","title":"Progressive Binarization with Semi-Structured Pruning for LLMs","date":"2025-02-03","arxiv_id":"2502.01705","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"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) · 0 unverified","official":{"repos":["xianglongyan/pbs2p"],"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"]}}},{"paper":null,"slug":"multi-frequency-wavefield-solutions-for","title":"Multi-frequency wavefield solutions for variable velocity models using meta-learning enhanced low-rank physics-informed neural network","date":"2025-02-02","arxiv_id":"2502.00897","n_code_links":0,"syntology":null},{"paper":null,"slug":"structural-latency-perturbation-in-large","title":"Structural Latency Perturbation in Large Language Models Through Recursive State Induction","date":"2025-02-02","arxiv_id":"2502.00758","n_code_links":0,"syntology":null},{"paper":null,"slug":"bridging-internal-probability-and-self","title":"Bridging Internal Probability and Self-Consistency for Effective and Efficient LLM Reasoning","date":"2025-02-01","arxiv_id":"2502.00511","n_code_links":0,"syntology":null},{"paper":"/paper/cat-pruning-cluster-aware-token-pruning-for","slug":"cat-pruning-cluster-aware-token-pruning-for","title":"CAT Pruning: Cluster-Aware Token Pruning For Text-to-Image Diffusion Models","date":"2025-02-01","arxiv_id":"2502.00433","n_code_links":1,"syntology":null},{"paper":"/paper/cache-me-if-you-must-adaptive-key-value","slug":"cache-me-if-you-must-adaptive-key-value","title":"Cache Me If You Must: Adaptive Key-Value Quantization for Large Language Models","date":"2025-01-31","arxiv_id":"2501.19392","n_code_links":1,"syntology":null},{"paper":"/paper/fedrts-federated-robust-pruning-via","slug":"fedrts-federated-robust-pruning-via","title":"FedRTS: Federated Robust Pruning via Combinatorial Thompson Sampling","date":"2025-01-31","arxiv_id":"2501.19122","n_code_links":0,"syntology":{"ran":2,"of":3,"n_ran_checked":1,"n_instrument":1,"unverified":1,"pointer_only":3,"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) · 1 unverified","official":null}},{"paper":null,"slug":"pivoting-factorization-a-compact-meta-low","title":"Pivoting Factorization: A Compact Meta Low-Rank Representation of Sparsity for Efficient Inference in Large Language Models","date":"2025-01-31","arxiv_id":"2501.19090","n_code_links":0,"syntology":null},{"paper":null,"slug":"symmetric-pruning-of-large-language-models","title":"Symmetric Pruning of Large Language Models","date":"2025-01-31","arxiv_id":"2501.18980","n_code_links":0,"syntology":null},{"paper":null,"slug":"safl-structure-aware-personalized-federated","title":"SAFL: Structure-Aware Personalized Federated Learning via Client-Specific Clustering and SCSI-Guided Model Pruning","date":"2025-01-30","arxiv_id":"2501.18659","n_code_links":0,"syntology":null},{"paper":"/paper/2ssp-a-two-stage-framework-for-structured","slug":"2ssp-a-two-stage-framework-for-structured","title":"2SSP: A Two-Stage Framework for Structured Pruning of LLMs","date":"2025-01-29","arxiv_id":"2501.17771","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-proximal-operator-for-inducing-2-4-sparsity","title":"A Proximal Operator for Inducing 2:4-Sparsity","date":"2025-01-29","arxiv_id":"2501.18015","n_code_links":0,"syntology":null},{"paper":null,"slug":"asap-learning-generalizable-online-bin","title":"ASAP: Learning Generalizable Online Bin Packing via Adaptive Selection After Pruning","date":"2025-01-29","arxiv_id":"2501.17377","n_code_links":0,"syntology":null},{"paper":null,"slug":"dress-data-driven-regularized-structured","title":"DReSS: Data-driven Regularized Structured Streamlining for Large Language Models","date":"2025-01-29","arxiv_id":"2501.17905","n_code_links":0,"syntology":null},{"paper":null,"slug":"explainable-machine-learning-an-illustration","title":"Explainable Machine Learning: An Illustration of Kolmogorov-Arnold Network Model for Airfoil Lift Prediction","date":"2025-01-29","arxiv_id":"2501.17896","n_code_links":0,"syntology":null},{"paper":null,"slug":"hybrid-graphs-for-table-and-text-based","title":"Hybrid Graphs for Table-and-Text based Question Answering using LLMs","date":"2025-01-29","arxiv_id":"2501.17767","n_code_links":0,"syntology":null},{"paper":"/paper/when-less-is-more-evolving-large-neural","slug":"when-less-is-more-evolving-large-neural","title":"When less is more: evolving large neural networks from small ones","date":"2025-01-29","arxiv_id":"2501.18012","n_code_links":1,"syntology":null},{"paper":null,"slug":"b-fpgm-lightweight-face-detection-via","title":"B-FPGM: Lightweight Face Detection via Bayesian-Optimized Soft FPGM Pruning","date":"2025-01-28","arxiv_id":"2501.16917","n_code_links":0,"syntology":null},{"paper":"/paper/graph-of-attacks-with-pruning-optimizing","slug":"graph-of-attacks-with-pruning-optimizing","title":"Graph of Attacks with Pruning: Optimizing Stealthy Jailbreak Prompt Generation for Enhanced LLM Content Moderation","date":"2025-01-28","arxiv_id":"2501.18638","n_code_links":1,"syntology":null},{"paper":null,"slug":"efficient-object-detection-of-marine-debris","title":"Efficient Object Detection of Marine Debris using Pruned YOLO Model","date":"2025-01-27","arxiv_id":"2501.16571","n_code_links":0,"syntology":null},{"paper":null,"slug":"provence-efficient-and-robust-context-pruning","title":"Provence: efficient and robust context pruning for retrieval-augmented generation","date":"2025-01-27","arxiv_id":"2501.16214","n_code_links":0,"syntology":null},{"paper":"/paper/information-consistent-pruning-how-to","slug":"information-consistent-pruning-how-to","title":"Information Consistent Pruning: How to Efficiently Search for Sparse Networks?","date":"2025-01-26","arxiv_id":"2501.15592","n_code_links":1,"syntology":null},{"paper":null,"slug":"hardware-aware-dnn-compression-for","title":"Hardware-Aware DNN Compression for Homogeneous Edge Devices","date":"2025-01-25","arxiv_id":"2501.15240","n_code_links":0,"syntology":null},{"paper":null,"slug":"lightweight-and-post-training-structured","title":"Lightweight and Post-Training Structured Pruning for On-Device Large Lanaguage Models","date":"2025-01-25","arxiv_id":"2501.15255","n_code_links":0,"syntology":null},{"paper":null,"slug":"on-accelerating-edge-ai-optimizing-resource","title":"On Accelerating Edge AI: Optimizing Resource-Constrained Environments","date":"2025-01-25","arxiv_id":"2501.15014","n_code_links":0,"syntology":null},{"paper":null,"slug":"pip-perturbation-based-iterative-pruning-for","title":"PIP: Perturbation-based Iterative Pruning for Large Language Models","date":"2025-01-25","arxiv_id":"2501.15278","n_code_links":0,"syntology":null},{"paper":null,"slug":"tomoe-converting-dense-large-language-models","title":"ToMoE: Converting Dense Large Language Models to Mixture-of-Experts through Dynamic Structural Pruning","date":"2025-01-25","arxiv_id":"2501.15316","n_code_links":0,"syntology":null},{"paper":null,"slug":"you-only-prune-once-designing-calibration","title":"You Only Prune Once: Designing Calibration-Free Model Compression With Policy Learning","date":"2025-01-25","arxiv_id":"2501.15296","n_code_links":0,"syntology":null},{"paper":null,"slug":"adaptive-rank-allocation-for-federated","title":"Adaptive Rank Allocation for Federated Parameter-Efficient Fine-Tuning of Language Models","date":"2025-01-24","arxiv_id":"2501.14406","n_code_links":0,"syntology":null},{"paper":null,"slug":"dynamic-token-reduction-during-generation-for","title":"Dynamic Token Reduction during Generation for Vision Language Models","date":"2025-01-24","arxiv_id":"2501.14204","n_code_links":0,"syntology":null},{"paper":"/paper/fast-think-on-graph-wider-deeper-and-faster","slug":"fast-think-on-graph-wider-deeper-and-faster","title":"Fast Think-on-Graph: Wider, Deeper and Faster Reasoning of Large Language Model on Knowledge Graph","date":"2025-01-24","arxiv_id":"2501.14300","n_code_links":1,"syntology":null},{"paper":null,"slug":"hwpq-hessian-free-weight-pruning-quantization","title":"SwiftPrune: Hessian-Free Weight Pruning for Large Language Models","date":"2025-01-24","arxiv_id":"2501.16376","n_code_links":0,"syntology":null},{"paper":null,"slug":"neural-symbolic-message-passing-with-dynamic","title":"Neural-Symbolic Message Passing with Dynamic Pruning","date":"2025-01-24","arxiv_id":"2501.14661","n_code_links":0,"syntology":null},{"paper":"/paper/referdino-referring-video-object-segmentation","slug":"referdino-referring-video-object-segmentation","title":"ReferDINO: Referring Video Object Segmentation with Visual Grounding Foundations","date":"2025-01-24","arxiv_id":"2501.14607","n_code_links":0,"syntology":null},{"paper":null,"slug":"gode-gaussians-on-demand-for-progressive","title":"GoDe: Gaussians on Demand for Progressive Level of Detail and Scalable Compression","date":"2025-01-23","arxiv_id":"2501.13558","n_code_links":0,"syntology":null},{"paper":null,"slug":"lvpruning-an-effective-yet-simple-language","title":"LVPruning: An Effective yet Simple Language-Guided Vision Token Pruning Approach for Multi-modal Large Language Models","date":"2025-01-23","arxiv_id":"2501.13652","n_code_links":0,"syntology":null},{"paper":null,"slug":"one-cycle-structured-pruning-with-stability","title":"One-cycle Structured Pruning with Stability Driven Structure Search","date":"2025-01-23","arxiv_id":"2501.13439","n_code_links":0,"syntology":null},{"paper":null,"slug":"overcoming-support-dilution-for-robust-few","title":"Overcoming Support Dilution for Robust Few-shot Semantic Segmentation","date":"2025-01-23","arxiv_id":"2501.13529","n_code_links":0,"syntology":null},{"paper":"/paper/advanced-deep-architecture-pruning-using","slug":"advanced-deep-architecture-pruning-using","title":"Advanced deep architecture pruning using single filter performance","date":"2025-01-22","arxiv_id":"2501.12880","n_code_links":1,"syntology":null},{"paper":null,"slug":"blr-moe-boosted-language-routing-mixture-of","title":"BLR-MoE: Boosted Language-Routing Mixture of Experts for Domain-Robust Multilingual E2E ASR","date":"2025-01-22","arxiv_id":"2501.12602","n_code_links":0,"syntology":null},{"paper":null,"slug":"unified-cnns-and-transformers-underlying","title":"Unified CNNs and transformers underlying learning mechanism reveals multi-head attention modus vivendi","date":"2025-01-22","arxiv_id":"2501.12900","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-journey-matters-average-parameter-count","title":"The Journey Matters: Average Parameter Count over Pre-training Unifies Sparse and Dense Scaling Laws","date":"2025-01-21","arxiv_id":"2501.12486","n_code_links":0,"syntology":null},{"paper":"/paper/communication-efficient-federated-learning-26","slug":"communication-efficient-federated-learning-26","title":"Communication-Efficient Federated Learning Based on Explanation-Guided Pruning for Remote Sensing Image Classification","date":"2025-01-20","arxiv_id":"2501.11493","n_code_links":1,"syntology":null},{"paper":null,"slug":"meta-instance-selection-instance-selection-as","title":"Meta-Instance Selection. Instance Selection as a Classification Problem with Meta-Features","date":"2025-01-20","arxiv_id":"2501.11526","n_code_links":0,"syntology":null},{"paper":null,"slug":"accelerating-large-language-models-through","title":"Accelerating Large Language Models through Partially Linear Feed-Forward Network","date":"2025-01-17","arxiv_id":"2501.10054","n_code_links":0,"syntology":null},{"paper":"/paper/multipruner-balanced-structure-removal-in","slug":"multipruner-balanced-structure-removal-in","title":"MultiPruner: Balanced Structure Removal in Foundation Models","date":"2025-01-17","arxiv_id":"2501.09949","n_code_links":1,"syntology":null},{"paper":null,"slug":"fasp-fast-and-accurate-structured-pruning-of","title":"FASP: Fast and Accurate Structured Pruning of Large Language Models","date":"2025-01-16","arxiv_id":"2501.09412","n_code_links":0,"syntology":null},{"paper":null,"slug":"pruning-for-sparse-diffusion-models-based-on","title":"Pruning for Sparse Diffusion Models based on Gradient Flow","date":"2025-01-16","arxiv_id":"2501.09464","n_code_links":0,"syntology":null},{"paper":"/paper/supersam-crafting-a-sam-supernetwork-via","slug":"supersam-crafting-a-sam-supernetwork-via","title":"SuperSAM: Crafting a SAM Supernetwork via Structured Pruning and Unstructured Parameter Prioritization","date":"2025-01-15","arxiv_id":"2501.08504","n_code_links":1,"syntology":null},{"paper":null,"slug":"deep-learning-and-natural-language-processing","title":"Deep Learning and Natural Language Processing in the Field of Construction","date":"2025-01-14","arxiv_id":"2501.07911","n_code_links":0,"syntology":null},{"paper":null,"slug":"object-centric-2d-gaussian-splatting","title":"Object-Centric 2D Gaussian Splatting: Background Removal and Occlusion-Aware Pruning for Compact Object Models","date":"2025-01-14","arxiv_id":"2501.08174","n_code_links":0,"syntology":null},{"paper":"/paper/optimal-classification-trees-for-continuous","slug":"optimal-classification-trees-for-continuous","title":"Optimal Classification Trees for Continuous Feature Data Using Dynamic Programming with Branch-and-Bound","date":"2025-01-14","arxiv_id":"2501.07903","n_code_links":2,"syntology":null},{"paper":null,"slug":"polylut-ultra-low-latency-polynomial","title":"PolyLUT: Ultra-low Latency Polynomial Inference with Hardware-Aware Structured Pruning","date":"2025-01-14","arxiv_id":"2501.08043","n_code_links":0,"syntology":null},{"paper":null,"slug":"flexquant-elastic-quantization-framework-for","title":"FlexQuant: Elastic Quantization Framework for Locally Hosted LLM on Edge Devices","date":"2025-01-13","arxiv_id":"2501.07139","n_code_links":0,"syntology":null},{"paper":"/paper/compact-bayesian-neural-networks-via-pruned","slug":"compact-bayesian-neural-networks-via-pruned","title":"Compact Bayesian Neural Networks via pruned MCMC sampling","date":"2025-01-12","arxiv_id":"2501.06962","n_code_links":1,"syntology":null},{"paper":"/paper/merging-feed-forward-sublayers-for-compressed","slug":"merging-feed-forward-sublayers-for-compressed","title":"Merging Feed-Forward Sublayers for Compressed Transformers","date":"2025-01-10","arxiv_id":"2501.06126","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-1mb-mixed-precision-quantized-encoder-for","title":"A 1Mb mixed-precision quantized encoder for image classification and patch-based compression","date":"2025-01-09","arxiv_id":"2501.05097","n_code_links":0,"syntology":null},{"paper":null,"slug":"deriving-coding-specific-sub-models-from-llms","title":"Deriving Coding-Specific Sub-Models from LLMs using Resource-Efficient Pruning","date":"2025-01-09","arxiv_id":"2501.05248","n_code_links":0,"syntology":null},{"paper":null,"slug":"upaq-a-framework-for-real-time-and-energy","title":"UPAQ: A Framework for Real-Time and Energy-Efficient 3D Object Detection in Autonomous Vehicles","date":"2025-01-08","arxiv_id":"2501.04213","n_code_links":0,"syntology":null},{"paper":null,"slug":"adaptive-pruning-of-pretrained-transformer","title":"Adaptive Pruning of Pretrained Transformer via Differential Inclusions","date":"2025-01-06","arxiv_id":"2501.03289","n_code_links":0,"syntology":null},{"paper":"/paper/lightgnn-simple-graph-neural-network-for","slug":"lightgnn-simple-graph-neural-network-for","title":"LightGNN: Simple Graph Neural Network for Recommendation","date":"2025-01-06","arxiv_id":"2501.03228","n_code_links":1,"syntology":null},{"paper":null,"slug":"efficient-deployment-of-large-language-models","title":"Efficient Deployment of Large Language Models on Resource-constrained Devices","date":"2025-01-05","arxiv_id":"2501.02438","n_code_links":0,"syntology":null},{"paper":null,"slug":"prune-or-retrain-optimizing-the-vocabulary-of","title":"Prune or Retrain: Optimizing the Vocabulary of Multilingual Models for Estonian","date":"2025-01-05","arxiv_id":"2501.02631","n_code_links":0,"syntology":null},{"paper":null,"slug":"strategic-fusion-optimizes-transformer","title":"Strategic Fusion Optimizes Transformer Compression","date":"2025-01-05","arxiv_id":"2501.03273","n_code_links":0,"syntology":null},{"paper":"/paper/swift-cross-dataset-pruning-enhancing-fine","slug":"swift-cross-dataset-pruning-enhancing-fine","title":"Swift Cross-Dataset Pruning: Enhancing Fine-Tuning Efficiency in Natural Language Understanding","date":"2025-01-05","arxiv_id":"2501.02432","n_code_links":1,"syntology":null},{"paper":"/paper/boosting-explainability-through-selective","slug":"boosting-explainability-through-selective","title":"Boosting Explainability through Selective Rationalization in Pre-trained Language Models","date":"2025-01-03","arxiv_id":"2501.03182","n_code_links":1,"syntology":null},{"paper":null,"slug":"instruction-following-pruning-for-large","title":"Instruction-Following Pruning for Large Language Models","date":"2025-01-03","arxiv_id":"2501.02086","n_code_links":0,"syntology":null},{"paper":null,"slug":"pruning-based-data-selection-and-network","title":"Pruning-based Data Selection and Network Fusion for Efficient Deep Learning","date":"2025-01-02","arxiv_id":"2501.01118","n_code_links":0,"syntology":null},{"paper":null,"slug":"annotation-ambiguity-aware-semi-supervised","title":"Annotation Ambiguity Aware Semi-Supervised Medical Image Segmentation","date":"2025-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"bg-triangle-bezier-gaussian-triangle-for-3d-1","title":"BG-Triangle: Bezier Gaussian Triangle for 3D Vectorization and Rendering","date":"2025-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"d2sp-dynamic-dual-stage-purification","title":"D2SP: Dynamic Dual-Stage Purification Framework for Dual Noise Mitigation in Vision-based Affective Recognition.","date":"2025-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"efficient-test-time-adaptive-object-detection","title":"Efficient Test-time Adaptive Object Detection via Sensitivity-Guided Pruning","date":"2025-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"efficientllava-generalizable-auto-pruning-for-1","title":"EfficientLLaVA: Generalizable Auto-Pruning for Large Vision-language Models","date":"2025-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"fedcs-coreset-selection-for-federated","title":"FedCS: Coreset Selection for Federated Learning","date":"2025-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"fireplace-geometric-refinements-of-llm-common","title":"FirePlace: Geometric Refinements of LLM Common Sense Reasoning for 3D Object Placement","date":"2025-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"flexgs-train-once-deploy-everywhere-with-many","title":"FlexGS: Train Once, Deploy Everywhere with Many-in-One Flexible 3D Gaussian Splatting","date":"2025-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"flexible-group-count-enables-hassle-free","title":"Flexible Group Count Enables Hassle-Free Structured Pruning","date":"2025-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"icp-immediate-compensation-pruning-for-mid-to","title":"ICP: Immediate Compensation Pruning for Mid-to-high Sparsity","date":"2025-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"libra-merging-importance-redundancy-and","title":"Libra-Merging: Importance-redundancy and Pruning-merging Trade-off for Acceleration Plug-in in Large Vision-Language Model","date":"2025-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"on-importance-of-layer-pruning-for-smaller","title":"On Importance of Layer Pruning for Smaller BERT Models and Low Resource Languages","date":"2025-01-01","arxiv_id":"2501.00733","n_code_links":0,"syntology":null},{"paper":null,"slug":"fast-and-interpretable-mixed-integer-linear","title":"Fast and Interpretable Mixed-Integer Linear Program Solving by Learning Model Reduction","date":"2024-12-31","arxiv_id":"2501.00307","n_code_links":0,"syntology":null},{"paper":"/paper/token-pruning-for-caching-better-9-times","slug":"token-pruning-for-caching-better-9-times","title":"Token Pruning for Caching Better: 9 Times Acceleration on Stable Diffusion for Free","date":"2024-12-31","arxiv_id":"2501.00375","n_code_links":1,"syntology":null},{"paper":null,"slug":"align-attention-heads-before-merging-them-an","title":"Align Attention Heads Before Merging Them: An Effective Way for Converting MHA to GQA","date":"2024-12-30","arxiv_id":"2412.20677","n_code_links":0,"syntology":null},{"paper":null,"slug":"edgerag-online-indexed-rag-for-edge-devices","title":"EdgeRAG: Online-Indexed RAG for Edge Devices","date":"2024-12-30","arxiv_id":"2412.21023","n_code_links":0,"syntology":null},{"paper":null,"slug":"exploring-and-controlling-diversity-in-llm","title":"Exploring and Controlling Diversity in LLM-Agent Conversation","date":"2024-12-30","arxiv_id":"2412.21102","n_code_links":0,"syntology":null},{"paper":"/paper/framefusion-combining-similarity-and","slug":"framefusion-combining-similarity-and","title":"FrameFusion: Combining Similarity and Importance for Video Token Reduction on Large Visual Language Models","date":"2024-12-30","arxiv_id":"2501.01986","n_code_links":1,"syntology":{"ran":10,"of":13,"n_ran_checked":8,"n_instrument":2,"unverified":3,"pointer_only":1,"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) · 3 unverified","official":{"repos":["thu-nics/framefusion"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/maskgaussian-adaptive-3d-gaussian","slug":"maskgaussian-adaptive-3d-gaussian","title":"MaskGaussian: Adaptive 3D Gaussian Representation from Probabilistic Masks","date":"2024-12-29","arxiv_id":"2412.20522","n_code_links":1,"syntology":null},{"paper":"/paper/retake-reducing-temporal-and-knowledge","slug":"retake-reducing-temporal-and-knowledge","title":"ReTaKe: Reducing Temporal and Knowledge Redundancy for Long Video Understanding","date":"2024-12-29","arxiv_id":"2412.20504","n_code_links":1,"syntology":{"ran":12,"of":15,"n_ran_checked":10,"n_instrument":2,"unverified":3,"pointer_only":0,"phrase":"12 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; 2 where Syntology's instrument failed) · 3 unverified","official":{"repos":["sczwangxiao/video-retake"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/mining-platoon-patterns-from-traffic-videos","slug":"mining-platoon-patterns-from-traffic-videos","title":"Mining Platoon Patterns from Traffic Videos","date":"2024-12-28","arxiv_id":"2412.20177","n_code_links":1,"syntology":null},{"paper":null,"slug":"st-3-accelerating-multimodal-large-language","title":"ST$^3$: Accelerating Multimodal Large Language Model by Spatial-Temporal Visual Token Trimming","date":"2024-12-28","arxiv_id":"2412.20105","n_code_links":0,"syntology":null}],"record_sha256":"04d2321af4785704e068d5dab6d8caac1df15547f4276c41638b3b958e0965a5","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}