{"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/2","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":2,"pages_in_order":39,"rows_per_page":100,"rows":[101,200],"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","next":"/method/pruning/papers/3","papers":[{"paper":"/paper/minilongbench-the-low-cost-long-context","slug":"minilongbench-the-low-cost-long-context","title":"MiniLongBench: The Low-cost Long Context Understanding Benchmark for Large Language Models","date":"2025-05-26","arxiv_id":"2505.19959","n_code_links":1,"syntology":null},{"paper":null,"slug":"multimodal-machine-translation-with-visual","title":"Multimodal Machine Translation with Visual Scene Graph Pruning","date":"2025-05-26","arxiv_id":"2505.19507","n_code_links":0,"syntology":null},{"paper":null,"slug":"pangu-light-weight-re-initialization-for","title":"Pangu Light: Weight Re-Initialization for Pruning and Accelerating LLMs","date":"2025-05-26","arxiv_id":"2505.20155","n_code_links":0,"syntology":null},{"paper":"/paper/syftr-pareto-optimal-generative-ai","slug":"syftr-pareto-optimal-generative-ai","title":"syftr: Pareto-Optimal Generative AI","date":"2025-05-26","arxiv_id":"2505.20266","n_code_links":1,"syntology":null},{"paper":null,"slug":"context-driven-dynamic-pruning-for-large","title":"Context-Driven Dynamic Pruning for Large Speech Foundation Models","date":"2025-05-24","arxiv_id":"2505.18860","n_code_links":0,"syntology":null},{"paper":null,"slug":"is-attention-required-for-transformer","title":"Is Attention Required for Transformer Inference? Explore Function-preserving Attention Replacement","date":"2025-05-24","arxiv_id":"2505.21535","n_code_links":0,"syntology":null},{"paper":null,"slug":"m-moe-test-time-pruning-as-micro-grained","title":"$μ$-MoE: Test-Time Pruning as Micro-Grained Mixture-of-Experts","date":"2025-05-24","arxiv_id":"2505.18451","n_code_links":0,"syntology":null},{"paper":null,"slug":"neural-parameter-search-for-slimmer-fine","title":"Neural Parameter Search for Slimmer Fine-Tuned Models and Better Transfer","date":"2025-05-24","arxiv_id":"2505.18713","n_code_links":0,"syntology":null},{"paper":null,"slug":"pactrain-pruning-and-adaptive-sparse-gradient","title":"PacTrain: Pruning and Adaptive Sparse Gradient Compression for Efficient Collective Communication in Distributed Deep Learning","date":"2025-05-24","arxiv_id":"2505.18563","n_code_links":0,"syntology":null},{"paper":null,"slug":"pruning-for-performance-efficient-idiom-and","title":"Pruning for Performance: Efficient Idiom and Metaphor Classification in Low-Resource Konkani Using mBERT","date":"2025-05-24","arxiv_id":"2506.02005","n_code_links":0,"syntology":null},{"paper":null,"slug":"todre-visual-token-pruning-via-diversity-and","title":"ToDRE: Visual Token Pruning via Diversity and Task Awareness for Efficient Large Vision-Language Models","date":"2025-05-24","arxiv_id":"2505.18757","n_code_links":0,"syntology":null},{"paper":null,"slug":"elder-getting-efficient-llms-through-data","title":"ELDeR: Getting Efficient LLMs through Data-Driven Regularized Layer-wise Pruning","date":"2025-05-23","arxiv_id":"2505.18232","n_code_links":0,"syntology":null},{"paper":null,"slug":"embracing-contradiction-theoretical","title":"Embracing Contradiction: Theoretical Inconsistency Will Not Impede the Road of Building Responsible AI Systems","date":"2025-05-23","arxiv_id":"2505.18139","n_code_links":0,"syntology":null},{"paper":null,"slug":"task-specific-pruning-with-llm-sieve-how-many","title":"Task Specific Pruning with LLM-Sieve: How Many Parameters Does Your Task Really Need?","date":"2025-05-23","arxiv_id":"2505.18350","n_code_links":0,"syntology":null},{"paper":null,"slug":"align-grag-reasoning-guided-dual-alignment","title":"Align-GRAG: Reasoning-Guided Dual Alignment for Graph Retrieval-Augmented Generation","date":"2025-05-22","arxiv_id":"2505.16237","n_code_links":0,"syntology":null},{"paper":null,"slug":"bottlenecked-transformers-periodic-kv-cache","title":"Bottlenecked Transformers: Periodic KV Cache Abstraction for Generalised Reasoning","date":"2025-05-22","arxiv_id":"2505.16950","n_code_links":0,"syntology":null},{"paper":null,"slug":"fixing-data-that-hurts-performance-cascading","title":"Fixing Data That Hurts Performance: Cascading LLMs to Relabel Hard Negatives for Robust Information Retrieval","date":"2025-05-22","arxiv_id":"2505.16967","n_code_links":0,"syntology":null},{"paper":"/paper/hierarchical-safety-realignment-lightweight","slug":"hierarchical-safety-realignment-lightweight","title":"Hierarchical Safety Realignment: Lightweight Restoration of Safety in Pruned Large Vision-Language Models","date":"2025-05-22","arxiv_id":"2505.16104","n_code_links":1,"syntology":null},{"paper":"/paper/quickvideo-real-time-long-video-understanding","slug":"quickvideo-real-time-long-video-understanding","title":"QuickVideo: Real-Time Long Video Understanding with System Algorithm Co-Design","date":"2025-05-22","arxiv_id":"2505.16175","n_code_links":1,"syntology":null},{"paper":null,"slug":"rap-runtime-adaptive-pruning-for-llm","title":"RAP: Runtime-Adaptive Pruning for LLM Inference","date":"2025-05-22","arxiv_id":"2505.17138","n_code_links":0,"syntology":null},{"paper":"/paper/trim-achieving-extreme-sparsity-with-targeted","slug":"trim-achieving-extreme-sparsity-with-targeted","title":"TRIM: Achieving Extreme Sparsity with Targeted Row-wise Iterative Metric-driven Pruning","date":"2025-05-22","arxiv_id":"2505.16743","n_code_links":1,"syntology":null},{"paper":"/paper/clustering-and-pruning-in-causal-data-fusion","slug":"clustering-and-pruning-in-causal-data-fusion","title":"Clustering and Pruning in Causal Data Fusion","date":"2025-05-21","arxiv_id":"2505.15215","n_code_links":1,"syntology":null},{"paper":null,"slug":"deftx-denoised-sparse-fine-tuning-for-zero","title":"DeFTX: Denoised Sparse Fine-Tuning for Zero-Shot Cross-Lingual Transfer","date":"2025-05-21","arxiv_id":"2505.15090","n_code_links":0,"syntology":null},{"paper":"/paper/diffprob-data-pruning-for-face-recognition","slug":"diffprob-data-pruning-for-face-recognition","title":"DiffProb: Data Pruning for Face Recognition","date":"2025-05-21","arxiv_id":"2505.15272","n_code_links":1,"syntology":null},{"paper":"/paper/on-the-creation-of-narrow-ai-hierarchy-and","slug":"on-the-creation-of-narrow-ai-hierarchy-and","title":"On the creation of narrow AI: hierarchy and nonlocality of neural network skills","date":"2025-05-21","arxiv_id":"2505.15811","n_code_links":1,"syntology":null},{"paper":null,"slug":"self-give-associative-thinking-from-limited","title":"Self-GIVE: Associative Thinking from Limited Structured Knowledge for Enhanced Large Language Model Reasoning","date":"2025-05-21","arxiv_id":"2505.15062","n_code_links":0,"syntology":null},{"paper":"/paper/adaptive-pruning-of-deep-neural-networks-for","slug":"adaptive-pruning-of-deep-neural-networks-for","title":"Adaptive Pruning of Deep Neural Networks for Resource-Aware Embedded Intrusion Detection on the Edge","date":"2025-05-20","arxiv_id":"2505.14592","n_code_links":1,"syntology":null},{"paper":null,"slug":"can-pruning-improve-reasoning-revisiting-long","title":"Can Pruning Improve Reasoning? Revisiting Long-CoT Compression with Capability in Mind for Better Reasoning","date":"2025-05-20","arxiv_id":"2505.14582","n_code_links":0,"syntology":null},{"paper":null,"slug":"drp-distilled-reasoning-pruning-with-skill","title":"DRP: Distilled Reasoning Pruning with Skill-aware Step Decomposition for Efficient Large Reasoning Models","date":"2025-05-20","arxiv_id":"2505.13975","n_code_links":0,"syntology":null},{"paper":null,"slug":"improved-methods-for-model-pruning-and","title":"Improved Methods for Model Pruning and Knowledge Distillation","date":"2025-05-20","arxiv_id":"2505.14052","n_code_links":0,"syntology":null},{"paper":"/paper/a-token-is-worth-over-1000-tokens-efficient","slug":"a-token-is-worth-over-1000-tokens-efficient","title":"A Token is Worth over 1,000 Tokens: Efficient Knowledge Distillation through Low-Rank Clone","date":"2025-05-19","arxiv_id":"2505.12781","n_code_links":1,"syntology":null},{"paper":null,"slug":"a3-an-analytical-low-rank-approximation","title":"A3 : an Analytical Low-Rank Approximation Framework for Attention","date":"2025-05-19","arxiv_id":"2505.12942","n_code_links":0,"syntology":null},{"paper":null,"slug":"adatoken-3d-dynamic-spatial-gating-for","title":"AdaToken-3D: Dynamic Spatial Gating for Efficient 3D Large Multimodal-Models Reasoning","date":"2025-05-19","arxiv_id":"2505.12782","n_code_links":0,"syntology":null},{"paper":"/paper/an-overview-of-arithmetic-adaptations-for","slug":"an-overview-of-arithmetic-adaptations-for","title":"An Overview of Arithmetic Adaptations for Inference of Convolutional Neural Networks on Re-configurable Hardware","date":"2025-05-19","arxiv_id":"2505.13575","n_code_links":1,"syntology":null},{"paper":null,"slug":"automatic-complementary-separation-pruning","title":"Automatic Complementary Separation Pruning Toward Lightweight CNNs","date":"2025-05-19","arxiv_id":"2505.13225","n_code_links":0,"syntology":null},{"paper":null,"slug":"benchmarking-unified-face-attack-detection","title":"Benchmarking Unified Face Attack Detection via Hierarchical Prompt Tuning","date":"2025-05-19","arxiv_id":"2505.13327","n_code_links":0,"syntology":null},{"paper":null,"slug":"dimgrow-memory-efficient-field-level","title":"DimGrow: Memory-Efficient Field-level Embedding Dimension Search","date":"2025-05-19","arxiv_id":"2505.12683","n_code_links":0,"syntology":null},{"paper":null,"slug":"efficient-training-for-large-scale-optical","title":"Efficient training for large-scale optical neural network using an evolutionary strategy and attention pruning","date":"2025-05-19","arxiv_id":"2505.12906","n_code_links":0,"syntology":null},{"paper":"/paper/exploring-federated-pruning-for-large","slug":"exploring-federated-pruning-for-large","title":"Exploring Federated Pruning for Large Language Models","date":"2025-05-19","arxiv_id":"2505.13547","n_code_links":1,"syntology":null},{"paper":null,"slug":"heterospec-leveraging-contextual","title":"HeteroSpec: Leveraging Contextual Heterogeneity for Efficient Speculative Decoding","date":"2025-05-19","arxiv_id":"2505.13254","n_code_links":0,"syntology":null},{"paper":null,"slug":"totrl-unlock-llm-tree-of-thoughts-reasoning","title":"ToTRL: Unlock LLM Tree-of-Thoughts Reasoning Potential through Puzzles Solving","date":"2025-05-19","arxiv_id":"2505.12717","n_code_links":0,"syntology":null},{"paper":null,"slug":"bishop-sparsified-bundling-spiking","title":"Bishop: Sparsified Bundling Spiking Transformers on Heterogeneous Cores with Error-Constrained Pruning","date":"2025-05-18","arxiv_id":"2505.12281","n_code_links":0,"syntology":null},{"paper":null,"slug":"one-for-all-pruning-a-universal-model-for","title":"One-for-All Pruning: A Universal Model for Customized Compression of Large Language Models","date":"2025-05-18","arxiv_id":"2505.12216","n_code_links":0,"syntology":null},{"paper":"/paper/pmq-ve-progressive-multi-frame-quantization","slug":"pmq-ve-progressive-multi-frame-quantization","title":"PMQ-VE: Progressive Multi-Frame Quantization for Video Enhancement","date":"2025-05-18","arxiv_id":"2505.12266","n_code_links":1,"syntology":null},{"paper":null,"slug":"star-stage-wise-attention-guided-token","title":"STAR: Stage-Wise Attention-Guided Token Reduction for Efficient Large Vision-Language Models Inference","date":"2025-05-18","arxiv_id":"2505.12359","n_code_links":0,"syntology":null},{"paper":"/paper/sepprune-structured-pruning-for-efficient","slug":"sepprune-structured-pruning-for-efficient","title":"SepPrune: Structured Pruning for Efficient Deep Speech Separation","date":"2025-05-17","arxiv_id":"2505.12079","n_code_links":1,"syntology":null},{"paper":"/paper/2505-10787","slug":"2505-10787","title":"EA-3DGS: Efficient and Adaptive 3D Gaussians with Highly Enhanced Quality for outdoor scenes","date":"2025-05-16","arxiv_id":"2505.10787","n_code_links":1,"syntology":null},{"paper":"/paper/2505-10832","slug":"2505-10832","title":"Learning When to Think: Shaping Adaptive Reasoning in R1-Style Models via Multi-Stage RL","date":"2025-05-16","arxiv_id":"2505.10832","n_code_links":2,"syntology":null},{"paper":null,"slug":"2505-10942","title":"Nosy Layers, Noisy Fixes: Tackling DRAs in Federated Learning Systems using Explainable AI","date":"2025-05-16","arxiv_id":"2505.10942","n_code_links":0,"syntology":null},{"paper":"/paper/2505-11076","slug":"2505-11076","title":"Addition is almost all you need: Compressing neural networks with double binary factorization","date":"2025-05-16","arxiv_id":"2505.11076","n_code_links":1,"syntology":{"ran":0,"of":2,"n_ran_checked":0,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"0 ran · 2 unverified","official":{"repos":["usamec/double_binary"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":[]}}},{"paper":null,"slug":"2505-11283","title":"SubROC: AUC-Based Discovery of Exceptional Subgroup Performance for Binary Classifiers","date":"2025-05-16","arxiv_id":"2505.11283","n_code_links":0,"syntology":null},{"paper":null,"slug":"2505-11344","title":"Dynamic Base model Shift for Delta Compression","date":"2025-05-16","arxiv_id":"2505.11344","n_code_links":0,"syntology":null},{"paper":null,"slug":"2505-11471","title":"CRISP: Clustering Multi-Vector Representations for Denoising and Pruning","date":"2025-05-16","arxiv_id":"2505.11471","n_code_links":0,"syntology":null},{"paper":null,"slug":"bingo-a-novel-pruning-mechanism-to-reduce-the","title":"BINGO: A Novel Pruning Mechanism to Reduce the Size of Neural Networks","date":"2025-05-15","arxiv_id":"2505.09864","n_code_links":0,"syntology":null},{"paper":null,"slug":"why-1-1-1-in-visual-token-pruning-beyond","title":"Why 1 + 1 < 1 in Visual Token Pruning: Beyond Naive Integration via Multi-Objective Balanced Covering","date":"2025-05-15","arxiv_id":"2505.10118","n_code_links":0,"syntology":null},{"paper":null,"slug":"interim-report-on-human-guided-adaptive","title":"Interim Report on Human-Guided Adaptive Hyperparameter Optimization with Multi-Fidelity Sprints","date":"2025-05-14","arxiv_id":"2505.09792","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-larger-the-merrier-efficient-large-ai","title":"The Larger the Merrier? Efficient Large AI Model Inference in Wireless Edge Networks","date":"2025-05-14","arxiv_id":"2505.09214","n_code_links":0,"syntology":null},{"paper":null,"slug":"constrained-edge-ai-deployment-fine-tuning-vs","title":"Constrained Edge AI Deployment: Fine-Tuning vs Distillation for LLM Compression","date":"2025-05-13","arxiv_id":"2505.18166","n_code_links":0,"syntology":null},{"paper":null,"slug":"efficient-unstructured-pruning-of-mamba-state","title":"Efficient Unstructured Pruning of Mamba State-Space Models for Resource-Constrained Environments","date":"2025-05-13","arxiv_id":"2505.08299","n_code_links":0,"syntology":null},{"paper":null,"slug":"low-complexity-inference-in-continual","title":"Low-Complexity Inference in Continual Learning via Compressed Knowledge Transfer","date":"2025-05-13","arxiv_id":"2505.08327","n_code_links":0,"syntology":null},{"paper":null,"slug":"spat-sensitivity-based-multihead-attention","title":"SPAT: Sensitivity-based Multihead-attention Pruning on Time Series Forecasting Models","date":"2025-05-13","arxiv_id":"2505.08768","n_code_links":0,"syntology":null},{"paper":null,"slug":"channel-fingerprint-construction-for-massive","title":"Channel Fingerprint Construction for Massive MIMO: A Deep Conditional Generative Approach","date":"2025-05-12","arxiv_id":"2505.07893","n_code_links":0,"syntology":null},{"paper":"/paper/ice-pruning-an-iterative-cost-efficient","slug":"ice-pruning-an-iterative-cost-efficient","title":"ICE-Pruning: An Iterative Cost-Efficient Pruning Pipeline for Deep Neural Networks","date":"2025-05-12","arxiv_id":"2505.07411","n_code_links":1,"syntology":null},{"paper":null,"slug":"semantic-retention-and-extreme-compression-in","title":"Semantic Retention and Extreme Compression in LLMs: Can We Have Both?","date":"2025-05-12","arxiv_id":"2505.07289","n_code_links":0,"syntology":null},{"paper":null,"slug":"solving-nonlinear-pdes-with-sparse-radial","title":"Solving Nonlinear PDEs with Sparse Radial Basis Function Networks","date":"2025-05-12","arxiv_id":"2505.07765","n_code_links":0,"syntology":null},{"paper":null,"slug":"bi-lstm-based-multi-agent-drl-with","title":"Bi-LSTM based Multi-Agent DRL with Computation-aware Pruning for Agent Twins Migration in Vehicular Embodied AI Networks","date":"2025-05-09","arxiv_id":"2505.06378","n_code_links":0,"syntology":null},{"paper":null,"slug":"dpq-hd-post-training-compression-for-ultra","title":"DPQ-HD: Post-Training Compression for Ultra-Low Power Hyperdimensional Computing","date":"2025-05-08","arxiv_id":"2505.05413","n_code_links":0,"syntology":null},{"paper":"/paper/guiding-evolutionary-autoencoder-training","slug":"guiding-evolutionary-autoencoder-training","title":"Guiding Evolutionary AutoEncoder Training with Activation-Based Pruning Operators","date":"2025-05-08","arxiv_id":"2505.05138","n_code_links":1,"syntology":null},{"paper":null,"slug":"text2cypher-data-pruning-using-hard-example","title":"Text2Cypher: Data Pruning using Hard Example Selection","date":"2025-05-08","arxiv_id":"2505.05122","n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-initialization-agnostic-clustering","title":"Towards Initialization-Agnostic Clustering with Iterative Adaptive Resonance Theory","date":"2025-05-07","arxiv_id":"2505.04440","n_code_links":0,"syntology":null},{"paper":null,"slug":"mitigating-mode-collapse-in-normalizing-flows","title":"Mitigating mode collapse in normalizing flows by annealing with an adaptive schedule: Application to parameter estimation","date":"2025-05-06","arxiv_id":"2505.03652","n_code_links":0,"syntology":null},{"paper":null,"slug":"spap-structured-pruning-via-alternating","title":"SPAP: Structured Pruning via Alternating Optimization and Penalty Methods","date":"2025-05-06","arxiv_id":"2505.03373","n_code_links":0,"syntology":null},{"paper":null,"slug":"end-to-end-fully-binarized-network-design","title":"End-to-end fully-binarized network design: from Generic Learned Thermometer to Block Pruning","date":"2025-05-05","arxiv_id":"2505.13462","n_code_links":0,"syntology":null},{"paper":null,"slug":"optimizing-llms-for-resource-constrained","title":"Optimizing LLMs for Resource-Constrained Environments: A Survey of Model Compression Techniques","date":"2025-05-05","arxiv_id":"2505.02309","n_code_links":0,"syntology":null},{"paper":"/paper/replaceme-network-simplification-via-layer","slug":"replaceme-network-simplification-via-layer","title":"ReplaceMe: Network Simplification via Layer Pruning and Linear Transformations","date":"2025-05-05","arxiv_id":"2505.02819","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":["mts-ai/replaceme"],"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":"optimization-over-trained-and-sparse-neural","title":"Optimization over Trained (and Sparse) Neural Networks: A Surrogate within a Surrogate","date":"2025-05-04","arxiv_id":"2505.01985","n_code_links":0,"syntology":null},{"paper":null,"slug":"efficient-shapley-value-based-non-uniform","title":"Efficient Shapley Value-based Non-Uniform Pruning of Large Language Models","date":"2025-05-03","arxiv_id":"2505.01731","n_code_links":0,"syntology":null},{"paper":"/paper/a-darts-stable-model-selection-for-data","slug":"a-darts-stable-model-selection-for-data","title":"A-DARTS: Stable Model Selection for Data Repair in Time Series","date":"2025-05-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"efficient-recommendation-with-millions-of","title":"Efficient Recommendation with Millions of Items by Dynamic Pruning of Sub-Item Embeddings","date":"2025-05-01","arxiv_id":"2505.00560","n_code_links":0,"syntology":null},{"paper":null,"slug":"finescope-precision-pruning-for-domain","title":"FineScope : Precision Pruning for Domain-Specialized Large Language Models Using SAE-Guided Self-Data Cultivation","date":"2025-05-01","arxiv_id":"2505.00624","n_code_links":0,"syntology":null},{"paper":null,"slug":"redundancy-analysis-and-mitigation-for","title":"Redundancy Analysis and Mitigation for Machine Learning-Based Process Monitoring of Additive Manufacturing","date":"2025-04-30","arxiv_id":"2504.21317","n_code_links":0,"syntology":null},{"paper":null,"slug":"scalable-multi-task-learning-for-particle","title":"Scalable Multi-Task Learning for Particle Collision Event Reconstruction with Heterogeneous Graph Neural Networks","date":"2025-04-30","arxiv_id":"2504.21844","n_code_links":0,"syntology":null},{"paper":null,"slug":"cacheprune-neural-based-attribution-defense","title":"CachePrune: Neural-Based Attribution Defense Against Indirect Prompt Injection Attacks","date":"2025-04-29","arxiv_id":"2504.21228","n_code_links":0,"syntology":null},{"paper":"/paper/efficient-llms-with-amp-attention-heads-and","slug":"efficient-llms-with-amp-attention-heads-and","title":"Efficient LLMs with AMP: Attention Heads and MLP Pruning","date":"2025-04-29","arxiv_id":"2504.21174","n_code_links":2,"syntology":null},{"paper":null,"slug":"small-brains-but-big-challenges-white-matter","title":"Small brains but big challenges: white matter tractography in early life samples","date":"2025-04-29","arxiv_id":"2504.20554","n_code_links":0,"syntology":null},{"paper":null,"slug":"hardware-software-co-design-of-risc-v","title":"Hardware/Software Co-Design of RISC-V Extensions for Accelerating Sparse DNNs on FPGAs","date":"2025-04-28","arxiv_id":"2504.19659","n_code_links":0,"syntology":null},{"paper":"/paper/lodap-on-device-incremental-learning-via","slug":"lodap-on-device-incremental-learning-via","title":"LODAP: On-Device Incremental Learning Via Lightweight Operations and Data Pruning","date":"2025-04-28","arxiv_id":"2504.19638","n_code_links":1,"syntology":null},{"paper":"/paper/towards-faster-and-more-compact-foundation","slug":"towards-faster-and-more-compact-foundation","title":"Towards Faster and More Compact Foundation Models for Molecular Property Prediction","date":"2025-04-28","arxiv_id":"2504.19538","n_code_links":1,"syntology":null},{"paper":null,"slug":"uncovering-potential-effects-of-spontaneous","title":"Uncovering potential effects of spontaneous waves on synaptic development: the visual system as a model","date":"2025-04-26","arxiv_id":"2504.18991","n_code_links":0,"syntology":null},{"paper":null,"slug":"coding-for-computation-efficient-compression","title":"Coding for Computation: Efficient Compression of Neural Networks for Reconfigurable Hardware","date":"2025-04-24","arxiv_id":"2504.17403","n_code_links":0,"syntology":null},{"paper":null,"slug":"backslash-rate-constrained-optimized-training","title":"BackSlash: Rate Constrained Optimized Training of Large Language Models","date":"2025-04-23","arxiv_id":"2504.16968","n_code_links":0,"syntology":null},{"paper":null,"slug":"dynamic-superblock-pruning-for-fast-learned","title":"Dynamic Superblock Pruning for Fast Learned Sparse Retrieval","date":"2025-04-23","arxiv_id":"2504.17045","n_code_links":0,"syntology":null},{"paper":null,"slug":"donod-robust-and-generalizable-instruction","title":"DONOD: Robust and Generalizable Instruction Fine-Tuning for LLMs via Model-Intrinsic Dataset Pruning","date":"2025-04-21","arxiv_id":"2504.14810","n_code_links":0,"syntology":null},{"paper":null,"slug":"connecting-parameter-magnitudes-and-hessian","title":"Connecting Parameter Magnitudes and Hessian Eigenspaces at Scale using Sketched Methods","date":"2025-04-20","arxiv_id":"2504.14701","n_code_links":0,"syntology":null},{"paper":null,"slug":"matrix-factorization-with-dynamic-multi-view","title":"Matrix Factorization with Dynamic Multi-view Clustering for Recommender System","date":"2025-04-20","arxiv_id":"2504.14565","n_code_links":0,"syntology":null},{"paper":"/paper/nowag-a-unified-framework-for-shape","slug":"nowag-a-unified-framework-for-shape","title":"NoWag: A Unified Framework for Shape Preserving Compression of Large Language Models","date":"2025-04-20","arxiv_id":"2504.14569","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":["lawrencerliu/nowag"],"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":"omniv-med-scaling-medical-vision-language","title":"OmniV-Med: Scaling Medical Vision-Language Model for Universal Visual Understanding","date":"2025-04-20","arxiv_id":"2504.14692","n_code_links":0,"syntology":null},{"paper":null,"slug":"accelerating-llm-inference-with-flexible-n-m","title":"Accelerating LLM Inference with Flexible N:M Sparsity via A Fully Digital Compute-in-Memory Accelerator","date":"2025-04-19","arxiv_id":"2504.14365","n_code_links":0,"syntology":null},{"paper":null,"slug":"from-large-to-super-tiny-end-to-end","title":"From Large to Super-Tiny: End-to-End Optimization for Cost-Efficient LLMs","date":"2025-04-18","arxiv_id":"2504.13471","n_code_links":0,"syntology":null},{"paper":null,"slug":"d-2-moe-dual-routing-and-dynamic-scheduling","title":"D$^{2}$MoE: Dual Routing and Dynamic Scheduling for Efficient On-Device MoE-based LLM Serving","date":"2025-04-17","arxiv_id":"2504.15299","n_code_links":0,"syntology":null}],"record_sha256":"9fdeef23872c79009995ddc6ba2e3c116a1eb3d9fe285db8bd659d4d74d80a16","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}