{"total":115,"rows":[{"id":"2301.00774","title":"SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot","created":"2023-01-02","cited_by_count":1121,"area":null},{"id":"2304.14997","title":"Towards Automated Circuit Discovery for Mechanistic Interpretability","created":"2023-04-28","cited_by_count":724,"area":"mechinterp"},{"id":"2305.11627","title":"LLM-Pruner: On the Structural Pruning of Large Language Models","created":"2023-05-19","cited_by_count":650,"area":null},{"id":"2401.15077","title":"EAGLE: Speculative Sampling Requires Rethinking Feature Uncertainty","created":"2024-01-26","cited_by_count":578,"area":"lr"},{"id":"2208.11580","title":"Optimal Brain Compression: A Framework for Accurate Post-Training Quantization and Pruning","created":"2022-08-24","cited_by_count":322,"area":null},{"id":"2306.07629","title":"SqueezeLLM: Dense-and-Sparse Quantization","created":"2023-06-13","cited_by_count":294,"area":null},{"id":"2404.14294","title":"A Survey on Efficient Inference for Large Language Models","created":"2024-04-22","cited_by_count":205,"area":"inference"},{"id":"2308.06767","title":"A Survey on Deep Neural Network Pruning-Taxonomy, Comparison, Analysis, and Recommendations","created":"2023-08-13","cited_by_count":202,"area":null},{"id":"2310.05175","title":"Outlier Weighed Layerwise Sparsity (OWL): A Missing Secret Sauce for Pruning LLMs to High Sparsity","created":"2023-10-08","cited_by_count":165,"area":null},{"id":"2302.07863","title":"Speculative Decoding with Big Little Decoder","created":"2023-02-15","cited_by_count":164,"area":"inference"},{"id":"2204.09656","title":"A Fast Post-Training Pruning Framework for Transformers","created":"2022-03-29","cited_by_count":162,"area":null},{"id":"2302.14017","title":"Full Stack Optimization of Transformer Inference: a Survey","created":"2023-02-27","cited_by_count":80,"area":null},{"id":"2402.09748","title":"Model Compression and Efficient Inference for Large Language Models: A Survey","created":"2024-02-15","cited_by_count":64,"area":null},{"id":"2310.01382","title":"Compressing LLMs: The Truth is Rarely Pure and Never Simple","created":"2023-10-02","cited_by_count":62,"area":null},{"id":"2310.08915","title":"Dynamic Sparse No Training: Training-Free Fine-tuning for Sparse LLMs","created":"2023-10-13","cited_by_count":61,"area":null},{"id":"2302.04089","title":"ZipLM: Inference-Aware Structured Pruning of Language Models","created":"2023-02-07","cited_by_count":49,"area":null},{"id":"2401.04679","title":"RoSA: Accurate Parameter-Efficient Fine-Tuning via Robust Adaptation","created":"2024-01-09","cited_by_count":48,"area":null},{"id":"2408.09632","title":"MoDeGPT: Modular Decomposition for Large Language Model Compression","created":"2024-08-19","cited_by_count":48,"area":null},{"id":"2309.08520","title":"Scaling Laws for Sparsely-Connected Foundation Models","created":"2023-09-15","cited_by_count":43,"area":null},{"id":"2306.03805","title":"The Emergence of Essential Sparsity in Large Pre-trained Models: The Weights that Matter","created":"2023-06-06","cited_by_count":42,"area":null},{"id":"2310.16795","title":"QMoE: Practical Sub-1-Bit Compression of Trillion-Parameter Models","created":"2023-10-25","cited_by_count":42,"area":"moe"},{"id":"2404.08763","title":"CATS: Contextually-Aware Thresholding for Sparsity in Large Language Models","created":"2024-04-12","cited_by_count":41,"area":null},{"id":"2307.05908","title":"Predictive Pipelined Decoding: A Compute-Latency Trade-off for Exact LLM Decoding","created":"2023-07-12","cited_by_count":40,"area":null},{"id":"2312.17244","title":"The LLM Surgeon","created":"2023-12-28","cited_by_count":38,"area":null},{"id":"2410.10912","title":"AlphaPruning: Using Heavy-Tailed Self Regularization Theory for Improved Layer-wise Pruning of Large Language Models","created":"2024-10-14","cited_by_count":36,"area":null},{"id":"2307.07982","title":"A Survey of Techniques for Optimizing Transformer Inference","created":"2023-07-16","cited_by_count":35,"area":null},{"id":"2505.07004","title":"GuidedQuant: Large Language Model Quantization via Exploiting End Loss Guidance","created":"2025-05-11","cited_by_count":32,"area":null},{"id":"2409.06211","title":"STUN: Structured-Then-Unstructured Pruning for Scalable MoE Pruning","created":"2024-09-10","cited_by_count":30,"area":"moe"},{"id":"2303.02141","title":"Sparsity May Cry: Let Us Fail (Current) Sparse Neural Networks Together!","created":"2023-03-03","cited_by_count":27,"area":null},{"id":"2303.04185","title":"Gradient-Free Structured Pruning with Unlabeled Data","created":"2023-03-07","cited_by_count":26,"area":null},{"id":"2302.02596","title":"Ten Lessons We Have Learned in the New \"Sparseland\": A Short Handbook for Sparse Neural Network Researchers","created":"2023-02-06","cited_by_count":25,"area":null},{"id":"2407.10032","title":"LeanQuant: Accurate and Scalable Large Language Model Quantization with Loss-error-aware Grid","created":"2024-07-14","cited_by_count":22,"area":null},{"id":"2210.09223","title":"CAP: Correlation-Aware Pruning for Highly-Accurate Sparse Vision Models","created":"2022-10-14","cited_by_count":20,"area":null},{"id":"2405.20935","title":"Effective Interplay between Sparsity and Quantization: From Theory to Practice","created":"2024-05-31","cited_by_count":19,"area":null},{"id":"2406.07831","title":"ALPS: Improved Optimization for Highly Sparse One-Shot Pruning for Large Language Models","created":"2024-06-12","cited_by_count":19,"area":null},{"id":"2502.07780","title":"DarwinLM: Evolutionary Structured Pruning of Large Language Models","created":"2025-02-11","cited_by_count":18,"area":null},{"id":"2310.09499","title":"One-Shot Sensitivity-Aware Mixed Sparsity Pruning for Large Language Models","created":"2023-10-14","cited_by_count":16,"area":null},{"id":"2407.02068","title":"LPViT: Low-Power Semi-structured Pruning for Vision Transformers","created":"2024-07-02","cited_by_count":16,"area":null},{"id":"2210.06384","title":"GMP*: Well-Tuned Gradual Magnitude Pruning Can Outperform Most BERT-Pruning Methods","created":"2022-10-12","cited_by_count":15,"area":null},{"id":"2401.15347","title":"A Comprehensive Survey of Compression Algorithms for Language Models","created":"2024-01-27","cited_by_count":15,"area":null},{"id":"2405.03594","title":"Enabling High-Sparsity Foundational Llama Models with Efficient Pretraining and Deployment","created":"2024-05-06","cited_by_count":15,"area":null},{"id":"2310.06927","title":"Sparse Fine-tuning for Inference Acceleration of Large Language Models","created":"2023-10-10","cited_by_count":14,"area":"inference"},{"id":"2209.14624","title":"Is Complexity Required for Neural Network Pruning? A Case Study on Global Magnitude Pruning","created":"2022-09-29","cited_by_count":13,"area":null},{"id":"2302.04852","title":"SparseProp: Efficient Sparse Backpropagation for Faster Training of Neural Networks","created":"2023-02-09","cited_by_count":13,"area":null},{"id":"2310.02065","title":"VENOM: A Vectorized N:M Format for Unleashing the Power of Sparse Tensor Cores","created":"2023-10-03","cited_by_count":13,"area":null},{"id":"2310.02277","title":"Junk DNA Hypothesis: Pruning Small Pre-Trained Weights Irreversibly and Monotonically Impairs \"Difficult\" Downstream Tasks in LLMs","created":"2023-09-29","cited_by_count":13,"area":null},{"id":"2403.08058","title":"CHAI: Clustered Head Attention for Efficient LLM Inference","created":"2024-03-12","cited_by_count":13,"area":"inference"},{"id":"2404.05621","title":"MULTIFLOW: Shifting Towards Task-Agnostic Vision-Language Pruning","created":"2024-04-08","cited_by_count":13,"area":"mllm"},{"id":"2305.11203","title":"PDP: Parameter-free Differentiable Pruning is All You Need","created":"2023-05-18","cited_by_count":12,"area":null},{"id":"2404.09695","title":"LoRAP: Transformer Sub-Layers Deserve Differentiated Structured Compression for Large Language Models","created":"2024-04-15","cited_by_count":12,"area":null},{"id":"2410.02159","title":"Mitigating Memorization In Language Models","created":"2024-10-03","cited_by_count":12,"area":"safety"},{"id":"2304.12622","title":"Bias in Pruned Vision Models: In-Depth Analysis and Countermeasures","created":"2023-04-25","cited_by_count":11,"area":null},{"id":"2502.06604","title":"Do we really have to filter out random noise in pre-training data for language models?","created":"2025-02-10","cited_by_count":11,"area":null},{"id":"2308.02060","title":"Accurate Neural Network Pruning Requires Rethinking Sparse Optimization","created":"2023-08-03","cited_by_count":10,"area":null},{"id":"2401.12819","title":"Dynamic Layer Tying for Parameter-Efficient Transformers","created":"2024-01-23","cited_by_count":10,"area":"deeprl"},{"id":"2405.03637","title":"Collage: Light-Weight Low-Precision Strategy for LLM Training","created":"2024-05-06","cited_by_count":10,"area":null},{"id":"2501.15316","title":"ToMoE: Converting Dense Large Language Models to Mixture-of-Experts through Dynamic Structural Pruning","created":"2025-01-25","cited_by_count":10,"area":"moe"},{"id":"2212.07634","title":"Gradient-based Intra-attention Pruning on Pre-trained Language Models","created":"2022-12-15","cited_by_count":9,"area":"distill"},{"id":"2503.10135","title":"Gumiho: A Hybrid Architecture to Prioritize Early Tokens in Speculative Decoding","created":"2025-03-13","cited_by_count":9,"area":"inference"},{"id":"2505.01731","title":"Efficient Shapley Value-based Non-Uniform Pruning of Large Language Models","created":"2025-05-03","cited_by_count":8,"area":null},{"id":"2207.14200","title":"CrAM: A Compression-Aware Minimizer","created":"2022-07-28","cited_by_count":7,"area":null},{"id":"2511.16156","title":"Pluggable Pruning with Contiguous Layer Distillation for Diffusion Transformers","created":"2025-11-20","cited_by_count":7,"area":"diffusion"},{"id":"2406.10576","title":"Bypass Back-propagation: Optimization-based Structural Pruning for Large Language Models via Policy Gradient","created":"2024-06-15","cited_by_count":6,"area":null},{"id":"2304.01016","title":"Quick Dense Retrievers Consume KALE: Post Training Kullback Leibler Alignment of Embeddings for Asymmetrical dual encoders","created":"2023-03-31","cited_by_count":5,"area":null},{"id":"2304.12576","title":"Harnessing Deep Learning and HPC Kernels via High-Level Loop and Tensor Abstractions on CPU Architectures","created":"2023-04-25","cited_by_count":5,"area":null},{"id":"2407.11681","title":"MINI-LLM: Memory-Efficient Structured Pruning for Large Language Models","created":"2024-07-16","cited_by_count":5,"area":null},{"id":"2510.18358","title":"Ensembling Pruned Attention Heads For Uncertainty-Aware Efficient Transformers","created":"2025-10-21","cited_by_count":5,"area":null},{"id":"2407.13331","title":"Reconstruct the Pruned Model without Any Retraining","created":"2024-07-18","cited_by_count":4,"area":null},{"id":"2412.02328","title":"Efficient Model Compression Techniques with FishLeg","created":"2024-12-03","cited_by_count":4,"area":null},{"id":"2505.11564","title":"HessFormer: Hessians at Foundation Scale","created":"2025-05-16","cited_by_count":4,"area":"moe"},{"id":"2602.18116","title":"Cut Less, Fold More: Model Compression through the Lens of Projection Geometry","created":"2026-02-20","cited_by_count":4,"area":null},{"id":"2303.02331","title":"Training-Free Acceleration of ViTs with Delayed Spatial Merging","created":"2023-03-04","cited_by_count":3,"area":"inference"},{"id":"2306.07030","title":"Resource Efficient Neural Networks Using Hessian Based Pruning","created":"2023-06-12","cited_by_count":3,"area":null},{"id":"2402.05948","title":"DE$^3$-BERT: Distance-Enhanced Early Exiting for BERT based on Prototypical Networks","created":"2024-02-03","cited_by_count":3,"area":"inference"},{"id":"2501.17905","title":"DReSS: Data-driven Regularized Structured Streamlining for Large Language Models","created":"2025-01-29","cited_by_count":3,"area":null},{"id":"2502.00899","title":"HASSLE-free: A unified Framework for Sparse plus Low-Rank Matrix Decomposition for LLMs","created":"2025-02-02","cited_by_count":3,"area":null},{"id":"2502.13604","title":"BeamLoRA: Beam-Constraint Low-Rank Adaptation","created":"2025-02-19","cited_by_count":3,"area":null},{"id":"2507.03117","title":"BLaST: High Performance Inference and Pretraining using BLock Sparse Transformers","created":"2025-07-03","cited_by_count":3,"area":null},{"id":"2603.18426","title":"Prune-then-Quantize or Quantize-then-Prune? Understanding the Impact of Compression Order in Joint Model Compression","created":"2026-03-19","cited_by_count":3,"area":null},{"id":"2211.07715","title":"Fast DistilBERT on CPUs","created":"2022-10-27","cited_by_count":2,"area":null},{"id":"2303.14409","title":"Vision Models Can Be Efficiently Specialized via Few-Shot Task-Aware Compression","created":"2023-03-25","cited_by_count":2,"area":null},{"id":"2306.16601","title":"An Efficient Sparse Inference Software Accelerator for Transformer-based Language Models on CPUs","created":"2023-06-28","cited_by_count":2,"area":null},{"id":"2307.11764","title":"Sensi-BERT: Towards Sensitivity Driven Fine-Tuning for Parameter-Efficient BERT","created":"2023-07-14","cited_by_count":2,"area":null},{"id":"2312.13547","title":"How to Prune Your Language Model: Recovering Accuracy on the \"Sparsity May Cry'' Benchmark","created":"2023-12-21","cited_by_count":2,"area":null},{"id":"2406.00061","title":"STAT: Shrinking Transformers After Training","created":"2024-05-29","cited_by_count":2,"area":null},{"id":"2407.02098","title":"DM3D: Distortion-Minimized Weight Pruning for Lossless 3D Object Detection","created":"2024-07-02","cited_by_count":2,"area":null},{"id":"2411.14507","title":"From Pruning to Grafting: Dynamic Knowledge Redistribution via Learnable Layer Fusion","created":"2024-11-21","cited_by_count":2,"area":null},{"id":"2502.18518","title":"Swallowing the Poison Pills: Insights from Vulnerability Disparity Among LLMs","created":"2025-02-23","cited_by_count":2,"area":"safety"},{"id":"2503.12211","title":"Changing Base Without Losing Pace: A GPU-Efficient Alternative to MatMul in DNNs","created":"2025-03-15","cited_by_count":2,"area":null},{"id":"2505.00624","title":"FineScope : SAE-guided Data Selection Enables Domain Specific LLM Pruning and Finetuning","created":"2025-05-01","cited_by_count":2,"area":"mechinterp"},{"id":"2512.09953","title":"ZK-APEX: Zero-Knowledge Approximate Personalized Unlearning with Executable Proofs","created":"2025-12-09","cited_by_count":2,"area":"safety"},{"id":"2209.03990","title":"Vision for Bosnia and Herzegovina in Artificial Intelligence Age: Global Trends, Potential Opportunities, Selected Use-cases and Realistic Goals","created":"2022-09-08","cited_by_count":1,"area":null},{"id":"2212.13392","title":"DeepCuts: Single-Shot Interpretability based Pruning for BERT","created":"2022-12-27","cited_by_count":1,"area":null},{"id":"2303.17612","title":"oBERTa: Improving Sparse Transfer Learning via improved initialization, distillation, and pruning regimes","created":"2023-03-30","cited_by_count":1,"area":null},{"id":"2304.02721","title":"To Asymmetry and Beyond: Structured Pruning of Sequence to Sequence Models for Improved Inference Efficiency","created":"2023-04-05","cited_by_count":1,"area":null},{"id":"2411.00969","title":"Magnitude Pruning of Large Pretrained Transformer Models with a Mixture Gaussian Prior","created":"2024-11-01","cited_by_count":1,"area":null},{"id":"2411.17796","title":"Scalable iterative pruning of large language and vision models using block coordinate descent","created":"2024-11-26","cited_by_count":1,"area":null},{"id":"2510.00192","title":"Train Large, Deploy Compact: Structured Compression for Compact Low-Rank Adaptation","created":"2025-09-30","cited_by_count":1,"area":null},{"id":"2510.13832","title":"Entropy Meets Importance: A Unified Head Importance-Entropy Score for Stable and Efficient Transformer Pruning","created":"2025-10-10","cited_by_count":1,"area":null},{"id":"2511.18692","title":"VLM in a flash: I/O-Efficient Sparsification of Vision-Language Model via Neuron Chunking","created":"2025-11-24","cited_by_count":1,"area":"mllm"}],"next_cursor":"100"}