{"total":82,"rows":[{"id":"2106.04533","title":"Chasing Sparsity in Vision Transformers: An End-to-End Exploration","created":"2021-06-08","cited_by_count":183,"area":null},{"id":"2204.00408","title":"Structured Pruning Learns Compact and Accurate Models","created":"2022-04-01","cited_by_count":170,"area":null},{"id":"2305.10160","title":"Stop Uploading Test Data in Plain Text: Practical Strategies for Mitigating Data Contamination by Evaluation Benchmarks","created":"2023-05-17","cited_by_count":142,"area":null},{"id":"2108.05542","title":"AMMUS : A Survey of Transformer-based Pretrained Models in Natural Language Processing","created":"2021-08-12","cited_by_count":131,"area":null},{"id":"2201.05273","title":"Pretrained Language Models for Text Generation: A Survey","created":"2022-01-14","cited_by_count":122,"area":null},{"id":"2105.06990","title":"BERT Busters: Outlier Dimensions that Disrupt Transformers","created":"2021-05-14","cited_by_count":112,"area":null},{"id":"2110.05357","title":"Graph-Guided Network for Irregularly Sampled Multivariate Time Series","created":"2021-10-11","cited_by_count":111,"area":null},{"id":"2309.12314","title":"TinyCLIP: CLIP Distillation via Affinity Mimicking and Weight Inheritance","created":"2023-09-21","cited_by_count":90,"area":null},{"id":"2111.08284","title":"Few-Shot Self-Rationalization with Natural Language Prompts","created":"2021-11-16","cited_by_count":83,"area":null},{"id":"2203.08243","title":"Unified Visual Transformer Compression","created":"2022-03-15","cited_by_count":79,"area":null},{"id":"2405.14917","title":"SliM-LLM: Salience-Driven Mixed-Precision Quantization for Large Language Models","created":"2024-05-23","cited_by_count":63,"area":null},{"id":"2101.00234","title":"Subformer: Exploring Weight Sharing for Parameter Efficiency in Generative Transformers","created":"2021-01-01","cited_by_count":43,"area":null},{"id":"2402.05445","title":"Accurate LoRA-Finetuning Quantization of LLMs via Information Retention","created":"2024-02-08","cited_by_count":41,"area":null},{"id":"2104.08682","title":"Rethinking Network Pruning -- under the Pre-train and Fine-tune Paradigm","created":"2021-04-18","cited_by_count":40,"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":"2106.02205","title":"Enabling Lightweight Fine-tuning for Pre-trained Language Model Compression based on Matrix Product Operators","created":"2021-06-04","cited_by_count":29,"area":null},{"id":"2205.01541","title":"Efficient Fine-Tuning of BERT Models on the Edge","created":"2022-05-03","cited_by_count":29,"area":null},{"id":"2303.04185","title":"Gradient-Free Structured Pruning with Unlabeled Data","created":"2023-03-07","cited_by_count":26,"area":null},{"id":"2108.12594","title":"Layer-wise Model Pruning based on Mutual Information","created":"2021-08-28","cited_by_count":19,"area":null},{"id":"2203.12758","title":"Mokey: Enabling Narrow Fixed-Point Inference for Out-of-the-Box Floating-Point Transformer Models","created":"2022-03-23","cited_by_count":19,"area":null},{"id":"2406.16330","title":"Pruning via Merging: Compressing LLMs via Manifold Alignment Based Layer Merging","created":"2024-06-24","cited_by_count":19,"area":null},{"id":"2307.00067","title":"Transformers in Healthcare: A Survey","created":"2023-06-30","cited_by_count":17,"area":null},{"id":"2311.09335","title":"Investigating Hallucinations in Pruned Large Language Models for Abstractive Summarization","created":"2023-11-15","cited_by_count":16,"area":null},{"id":"2211.02738","title":"Intriguing Properties of Compression on Multilingual Models","created":"2022-11-04","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":"2206.01838","title":"Differentially Private Model Compression","created":"2022-06-03","cited_by_count":13,"area":null},{"id":"2105.03343","title":"Adapting by Pruning: A Case Study on BERT","created":"2021-05-07","cited_by_count":11,"area":null},{"id":"2210.03923","title":"Sparse Teachers Can Be Dense with Knowledge","created":"2022-10-08","cited_by_count":11,"area":null},{"id":"2401.06034","title":"LinguAlchemy: Fusing Typological and Geographical Elements for Unseen Language Generalization","created":"2024-01-11","cited_by_count":10,"area":null},{"id":"2408.04619","title":"Transformer Explainer: Learning LLM Transformers with Interactive Visual Explanation and Experimentation","created":"2024-08-08","cited_by_count":10,"area":null},{"id":"2602.17835","title":"Influence-Preserving Proxies for Gradient-Based Data Selection in LLM Fine-tuning","created":"2026-02-19","cited_by_count":10,"area":null},{"id":"2310.17903","title":"Pitfalls in Language Models for Code Intelligence: A Taxonomy and Survey","created":"2023-10-27","cited_by_count":9,"area":null},{"id":"2110.10305","title":"When in Doubt, Summon the Titans: Efficient Inference with Large Models","created":"2021-10-19","cited_by_count":8,"area":null},{"id":"2308.04637","title":"Sparse Binary Transformers for Multivariate Time Series Modeling","created":"2023-08-09","cited_by_count":8,"area":null},{"id":"2210.05211","title":"A Win-win Deal: Towards Sparse and Robust Pre-trained Language Models","created":"2022-10-11","cited_by_count":7,"area":null},{"id":"2101.07086","title":"Model Compression for Domain Adaptation through Causal Effect Estimation","created":"2021-01-18","cited_by_count":6,"area":null},{"id":"2202.05451","title":"ACORT: A Compact Object Relation Transformer for Parameter Efficient Image Captioning","created":"2022-02-11","cited_by_count":6,"area":null},{"id":"2208.13363","title":"Survey: Exploiting Data Redundancy for Optimization of Deep Learning","created":"2022-08-29","cited_by_count":6,"area":null},{"id":"2210.07904","title":"HashFormers: Towards Vocabulary-independent Pre-trained Transformers","created":"2022-10-14","cited_by_count":6,"area":null},{"id":"2109.11047","title":"Cross-Modal Coherence for Text-to-Image Retrieval","created":"2021-09-22","cited_by_count":5,"area":null},{"id":"2112.13236","title":"An Ensemble of Pre-trained Transformer Models For Imbalanced Multiclass Malware Classification","created":"2021-12-25","cited_by_count":5,"area":null},{"id":"2210.06425","title":"MiniALBERT: Model Distillation via Parameter-Efficient Recursive Transformers","created":"2022-10-12","cited_by_count":5,"area":null},{"id":"2306.00014","title":"PreQuant: A Task-agnostic Quantization Approach for Pre-trained Language Models","created":"2023-05-30","cited_by_count":5,"area":null},{"id":"2309.03340","title":"Parameter Efficient Audio Captioning With Faithful Guidance Using Audio-text Shared Latent Representation","created":"2023-09-06","cited_by_count":5,"area":null},{"id":"2203.09055","title":"Fine- and Coarse-Granularity Hybrid Self-Attention for Efficient BERT","created":"2022-03-17","cited_by_count":4,"area":null},{"id":"2209.09593","title":"EffEval: A Comprehensive Evaluation of Efficiency for MT Evaluation Metrics","created":"2022-09-20","cited_by_count":4,"area":null},{"id":"2302.07612","title":"Towards Optimal Compression: Joint Pruning and Quantization","created":"2023-02-15","cited_by_count":4,"area":null},{"id":"2306.11903","title":"Deep Fusion: Efficient Network Training via Pre-trained Initializations","created":"2023-06-20","cited_by_count":4,"area":null},{"id":"2405.06772","title":"CANAL -- Cyber Activity News Alerting Language Model: Empirical Approach vs. Expensive LLM","created":"2024-05-10","cited_by_count":4,"area":null},{"id":"2412.03527","title":"FANAL -- Financial Activity News Alerting Language Modeling Framework","created":"2024-12-04","cited_by_count":4,"area":null},{"id":"2503.04704","title":"Universality of Layer-Level Entropy-Weighted Quantization Beyond Model Architecture and Size","created":"2025-03-06","cited_by_count":4,"area":null},{"id":"2111.15205","title":"Benchmark Static API Call Datasets for Malware Family Classification","created":"2021-11-30","cited_by_count":3,"area":null},{"id":"2207.08006","title":"S4: a High-sparsity, High-performance AI Accelerator","created":"2022-07-16","cited_by_count":3,"area":null},{"id":"2404.05415","title":"Relation Extraction Using Large Language Models: A Case Study on Acupuncture Point Locations","created":"2024-04-08","cited_by_count":3,"area":null},{"id":"2411.18148","title":"A Runtime-Adaptive Transformer Neural Network Accelerator on FPGAs","created":"2024-11-27","cited_by_count":3,"area":null},{"id":"2412.13737","title":"On the Compression of Language Models for Code: An Empirical Study on CodeBERT","created":"2024-12-18","cited_by_count":3,"area":null},{"id":"2211.16648","title":"COMET: A Comprehensive Cluster Design Methodology for Distributed Deep Learning Training","created":"2022-11-30","cited_by_count":2,"area":null},{"id":"2304.01333","title":"Classification of integers based on residue classes via modern deep learning algorithms","created":"2023-04-03","cited_by_count":2,"area":null},{"id":"2305.06404","title":"LACoS-BLOOM: Low-rank Adaptation with Contrastive objective on 8 bits Siamese-BLOOM","created":"2023-05-10","cited_by_count":2,"area":null},{"id":"2311.12065","title":"Few-Shot Classification & Segmentation Using Large Language Models Agent","created":"2023-11-19","cited_by_count":2,"area":null},{"id":"2401.07456","title":"Only Send What You Need: Learning to Communicate Efficiently in Federated Multilingual Machine Translation","created":"2024-01-15","cited_by_count":2,"area":null},{"id":"2403.06497","title":"QuantTune: Optimizing Model Quantization with Adaptive Outlier-Driven Fine Tuning","created":"2024-03-11","cited_by_count":2,"area":null},{"id":"2505.06701","title":"RuleGenie: SIEM Detection Rule Set Optimization","created":"2025-05-10","cited_by_count":2,"area":null},{"id":"2102.02705","title":"EFloat: Entropy-coded Floating Point Format for Compressing Vector Embedding Models","created":"2021-02-04","cited_by_count":1,"area":null},{"id":"2208.02070","title":"Efficient Fine-Tuning of Compressed Language Models with Learners","created":"2022-08-03","cited_by_count":1,"area":null},{"id":"2305.18382","title":"Adaptive Sparsity Level during Training for Efficient Time Series Forecasting with Transformers","created":"2023-05-28","cited_by_count":1,"area":null},{"id":"2310.07911","title":"Pit One Against Many: Leveraging Attention-head Embeddings for Parameter-efficient Multi-head Attention","created":"2023-10-11","cited_by_count":1,"area":null},{"id":"2312.10702","title":"Can persistent homology whiten Transformer-based black-box models? A case study on BERT compression","created":"2023-12-17","cited_by_count":1,"area":null},{"id":"2406.00030","title":"Large Language Model Pruning","created":"2024-05-24","cited_by_count":1,"area":null},{"id":"2409.13975","title":"ProTEA: Programmable Transformer Encoder Acceleration on FPGA","created":"2024-09-21","cited_by_count":1,"area":null},{"id":"2409.14023","title":"FAMOUS: Flexible Accelerator for the Attention Mechanism of Transformer on UltraScale+ FPGAs","created":"2024-09-21","cited_by_count":1,"area":null},{"id":"2409.14168","title":"Towards Building Efficient Sentence BERT Models using Layer Pruning","created":"2024-09-21","cited_by_count":1,"area":null},{"id":"2502.08692","title":"Efficient Split Learning LSTM Models for FPGA-based Edge IoT Devices","created":"2025-02-12","cited_by_count":1,"area":null},{"id":"2604.22583","title":"Adaptive Head Budgeting for Efficient Multi-Head Attention","created":"2026-04-24","cited_by_count":1,"area":null},{"id":"2608.26926","title":"A Layer Importance Metric for Quantization Accounting for the Speed-Quality Trade-off in Autoregressive Models","created":"2026-08-27","cited_by_count":1,"area":null},{"id":"2109.08814","title":"Structured Pattern Pruning Using Regularization","created":"2021-09-18","cited_by_count":0,"area":null},{"id":"2208.00763","title":"HiKonv: Maximizing the Throughput of Quantized Convolution With Novel Bit-wise Management and Computation","created":"2022-07-22","cited_by_count":0,"area":null},{"id":"2302.00856","title":"idT5: Indonesian Version of Multilingual T5 Transformer","created":"2023-02-02","cited_by_count":0,"area":null},{"id":"2310.03424","title":"Neural Language Model Pruning for Automatic Speech Recognition","created":"2023-10-05","cited_by_count":0,"area":null},{"id":"2310.20144","title":"EELBERT: Tiny Models through Dynamic Embeddings","created":"2023-10-31","cited_by_count":0,"area":null},{"id":"2411.17720","title":"MAS-Attention: Memory-Aware Stream Processing for Attention Acceleration on Resource-Constrained Edge Devices","created":"2024-11-20","cited_by_count":0,"area":null},{"id":"2501.00733","title":"On Importance of Layer Pruning for Smaller BERT Models and Low Resource Languages","created":"2025-01-01","cited_by_count":0,"area":null}],"next_cursor":null}