{"total":89,"rows":[{"id":"2305.02301","title":"Distilling Step-by-Step! Outperforming Larger Language Models with Less Training Data and Smaller Model Sizes","created":"2023-05-03","cited_by_count":737,"area":null},{"id":"2101.01321","title":"I-BERT: Integer-only BERT Quantization","created":"2021-01-05","cited_by_count":255,"area":null},{"id":"2310.17157","title":"Deja Vu: Contextual Sparsity for Efficient LLMs at Inference Time","created":"2023-10-26","cited_by_count":252,"area":null},{"id":"2104.08826","title":"GPT3Mix: Leveraging Large-scale Language Models for Text Augmentation","created":"2021-04-18","cited_by_count":187,"area":null},{"id":"2109.04838","title":"Block Pruning For Faster Transformers","created":"2021-09-10","cited_by_count":177,"area":null},{"id":"2107.06641","title":"Trustworthy AI: A Computational Perspective","created":"2021-07-12","cited_by_count":93,"area":null},{"id":"2205.07877","title":"A Comprehensive Survey on Model Quantization for Deep Neural Networks in Image Classification","created":"2022-05-14","cited_by_count":65,"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":"2111.00035","title":"Skyformer: Remodel Self-Attention with Gaussian Kernel and Nystr\\\"om Method","created":"2021-10-29","cited_by_count":63,"area":null},{"id":"2402.05964","title":"A Survey on Transformer Compression","created":"2024-02-05","cited_by_count":46,"area":null},{"id":"2202.07105","title":"A Survey on Model Compression and Acceleration for Pretrained Language Models","created":"2022-02-15","cited_by_count":45,"area":null},{"id":"2306.12509","title":"Joint Prompt Optimization of Stacked LLMs using Variational Inference","created":"2023-06-21","cited_by_count":32,"area":null},{"id":"2307.13912","title":"Embedding Democratic Values into Social Media AIs via Societal Objective Functions","created":"2023-07-26","cited_by_count":25,"area":null},{"id":"2105.06232","title":"Retrieval-Free Knowledge-Grounded Dialogue Response Generation with Adapters","created":"2021-05-13","cited_by_count":23,"area":null},{"id":"2106.04563","title":"XtremeDistilTransformers: Task Transfer for Task-agnostic Distillation","created":"2021-06-08","cited_by_count":18,"area":null},{"id":"2108.13873","title":"Student Surpasses Teacher: Imitation Attack for Black-Box NLP APIs","created":"2021-08-29","cited_by_count":18,"area":null},{"id":"2104.10640","title":"The NLP Cookbook: Modern Recipes for Transformer based Deep Learning Architectures","created":"2021-03-23","cited_by_count":16,"area":null},{"id":"2305.11096","title":"Cross-modality Data Augmentation for End-to-End Sign Language Translation","created":"2023-05-18","cited_by_count":16,"area":null},{"id":"2307.10757","title":"Vesper: A Compact and Effective Pretrained Model for Speech Emotion Recognition","created":"2023-07-20","cited_by_count":16,"area":null},{"id":"2103.11367","title":"ROSITA: Refined BERT cOmpreSsion with InTegrAted techniques","created":"2021-03-21","cited_by_count":14,"area":null},{"id":"2106.02834","title":"MergeDistill: Merging Pre-trained Language Models using Distillation","created":"2021-06-05","cited_by_count":13,"area":null},{"id":"2205.01549","title":"Adaptable Adapters","created":"2022-05-03","cited_by_count":13,"area":null},{"id":"2206.01838","title":"Differentially Private Model Compression","created":"2022-06-03","cited_by_count":13,"area":null},{"id":"2402.13098","title":"ELAD: Explanation-Guided Large Language Models Active Distillation","created":"2024-02-20","cited_by_count":12,"area":null},{"id":"2308.03449","title":"Accurate Retraining-free Pruning for Pretrained Encoder-based Language Models","created":"2023-08-07","cited_by_count":11,"area":null},{"id":"2105.09816","title":"Intra-Document Cascading: Learning to Select Passages for Neural Document Ranking","created":"2021-05-20","cited_by_count":10,"area":null},{"id":"2403.10351","title":"TriSum: Learning Summarization Ability from Large Language Models with Structured Rationale","created":"2024-03-15","cited_by_count":10,"area":null},{"id":"2410.17152","title":"Improving Pinterest Search Relevance Using Large Language Models","created":"2024-10-22","cited_by_count":8,"area":null},{"id":"2105.14636","title":"LEAP: Learnable Pruning for Transformer-based Models","created":"2021-05-30","cited_by_count":7,"area":null},{"id":"2201.08539","title":"AutoDistill: an End-to-End Framework to Explore and Distill Hardware-Efficient Language Models","created":"2022-01-21","cited_by_count":7,"area":null},{"id":"2209.13736","title":"An Effective, Performant Named Entity Recognition System for Noisy Business Telephone Conversation Transcripts","created":"2022-09-27","cited_by_count":7,"area":null},{"id":"2110.04711","title":"SuperShaper: Task-Agnostic Super Pre-training of BERT Models with Variable Hidden Dimensions","created":"2021-10-10","cited_by_count":6,"area":null},{"id":"2205.03235","title":"A Review on Text-Based Emotion Detection -- Techniques, Applications, Datasets, and Future Directions","created":"2022-04-26","cited_by_count":6,"area":null},{"id":"2302.12044","title":"Exploring Social Media for Early Detection of Depression in COVID-19 Patients","created":"2023-02-23","cited_by_count":6,"area":null},{"id":"2306.02090","title":"Deep Classifier Mimicry without Data Access","created":"2023-06-03","cited_by_count":6,"area":null},{"id":"2103.06418","title":"LightMBERT: A Simple Yet Effective Method for Multilingual BERT Distillation","created":"2021-03-11","cited_by_count":5,"area":null},{"id":"2110.11869","title":"FLiText: A Faster and Lighter Semi-Supervised Text Classification with Convolution Networks","created":"2021-09-12","cited_by_count":5,"area":null},{"id":"2402.01051","title":"Generation, Distillation and Evaluation of Motivational Interviewing-Style Reflections with a Foundational Language Model","created":"2024-02-01","cited_by_count":5,"area":null},{"id":"2502.13533","title":"Train Small, Infer Large: Memory-Efficient LoRA Training for Large Language Models","created":"2025-02-19","cited_by_count":5,"area":null},{"id":"2508.00546","title":"SPENCER: Self-Adaptive Model Distillation for Efficient Code Retrieval","created":"2025-08-01","cited_by_count":5,"area":null},{"id":"2204.13511","title":"RobBERTje: a Distilled Dutch BERT Model","created":"2022-04-28","cited_by_count":4,"area":null},{"id":"2402.01093","title":"Need a Small Specialized Language Model? Plan Early!","created":"2024-02-02","cited_by_count":4,"area":null},{"id":"2501.10175","title":"Multi-stage Training of Bilingual Islamic LLM for Neural Passage Retrieval","created":"2025-01-17","cited_by_count":4,"area":null},{"id":"2507.04385","title":"Tractable Representation Learning with Probabilistic Circuits","created":"2025-07-06","cited_by_count":4,"area":null},{"id":"2112.04195","title":"VIRT: Improving Representation-based Models for Text Matching through Virtual Interaction","created":"2021-12-08","cited_by_count":3,"area":null},{"id":"2302.05454","title":"Distillation of encoder-decoder transformers for sequence labelling","created":"2023-02-10","cited_by_count":3,"area":null},{"id":"2406.05276","title":"VTrans: Accelerating Transformer Compression with Variational Information Bottleneck based Pruning","created":"2024-06-07","cited_by_count":3,"area":null},{"id":"2411.06151","title":"Building an Efficient Multilingual Non-Profit IR System for the Islamic Domain Leveraging Multiprocessing Design in Rust","created":"2024-11-09","cited_by_count":3,"area":null},{"id":"2412.08564","title":"Visual Program Distillation with Template-Based Augmentation","created":"2024-12-11","cited_by_count":3,"area":null},{"id":"2504.20033","title":"Mitigating Catastrophic Forgetting in the Incremental Learning of Medical Images","created":"2025-04-28","cited_by_count":3,"area":null},{"id":"2106.15085","title":"Automatic Construction of Enterprise Knowledge Base","created":"2021-06-29","cited_by_count":2,"area":null},{"id":"2108.10197","title":"Deploying a BERT-based Query-Title Relevance Classifier in a Production System: a View from the Trenches","created":"2021-08-23","cited_by_count":2,"area":null},{"id":"2204.03479","title":"Delta Keyword Transformer: Bringing Transformers to the Edge through Dynamically Pruned Multi-Head Self-Attention","created":"2022-03-20","cited_by_count":2,"area":null},{"id":"2211.11740","title":"SpeechNet: Weakly Supervised, End-to-End Speech Recognition at Industrial Scale","created":"2022-11-21","cited_by_count":2,"area":null},{"id":"2302.11812","title":"Teacher Intervention: Improving Convergence of Quantization Aware Training for Ultra-Low Precision Transformers","created":"2023-02-23","cited_by_count":2,"area":null},{"id":"2304.11520","title":"Processing Natural Language on Embedded Devices: How Well Do Transformer Models Perform?","created":"2023-04-23","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":"2511.07998","title":"Self-Correction Distillation for Structured Data Question Answering","created":"2025-11-11","cited_by_count":2,"area":null},{"id":"2109.08449","title":"General Cross-Architecture Distillation of Pretrained Language Models into Matrix Embeddings","created":"2021-09-17","cited_by_count":1,"area":null},{"id":"2110.08536","title":"Sparse Distillation: Speeding Up Text Classification by Using Bigger Student Models","created":"2021-10-16","cited_by_count":1,"area":null},{"id":"2111.01992","title":"Leveraging Advantages of Interactive and Non-Interactive Models for Vector-Based Cross-Lingual Information Retrieval","created":"2021-11-03","cited_by_count":1,"area":null},{"id":"2112.11480","title":"On the Compression of Natural Language Models","created":"2021-12-13","cited_by_count":1,"area":null},{"id":"2203.12814","title":"Bilaterally Slimmable Transformer for Elastic and Efficient Visual Question Answering","created":"2022-03-24","cited_by_count":1,"area":null},{"id":"2205.07582","title":"Chemical transformer compression for accelerating both training and inference of molecular modeling","created":"2022-05-16","cited_by_count":1,"area":null},{"id":"2208.00483","title":"Building an Efficiency Pipeline: Commutativity and Cumulativeness of Efficiency Operators for Transformers","created":"2022-07-31","cited_by_count":1,"area":null},{"id":"2211.08842","title":"Fast and Accurate FSA System Using ELBERT: An Efficient and Lightweight BERT","created":"2022-11-16","cited_by_count":1,"area":null},{"id":"2312.03038","title":"Sample-based Dynamic Hierarchical Transformer with Layer and Head Flexibility via Contextual Bandit","created":"2023-12-05","cited_by_count":1,"area":null},{"id":"2406.15476","title":"Self-Regulated Data-Free Knowledge Amalgamation for Text Classification","created":"2024-06-16","cited_by_count":1,"area":null},{"id":"2412.12178","title":"Activation Sparsity Opportunities for Compressing General Large Language Models","created":"2024-12-13","cited_by_count":1,"area":null},{"id":"2508.09960","title":"GBC: Generalized Behavior-Cloning Framework for Whole-Body Humanoid Imitation","created":"2025-08-13","cited_by_count":1,"area":null},{"id":"2512.07846","title":"MixLM: High-Throughput and Effective LLM Ranking via Text-Embedding Mix-Interaction","created":"2025-11-25","cited_by_count":1,"area":null},{"id":"2602.05393","title":"Late-to-Early Training: LET LLMs Learn Earlier, So Faster and Better","created":"2026-02-05","cited_by_count":1,"area":null},{"id":"2102.12936","title":"Risk factor identification for incident heart failure using neural network distillation and variable selection","created":"2021-02-17","cited_by_count":0,"area":null},{"id":"2106.08898","title":"RefBERT: Compressing BERT by Referencing to Pre-computed Representations","created":"2021-06-11","cited_by_count":0,"area":null},{"id":"2109.08627","title":"Classification-based Quality Estimation: Small and Efficient Models for Real-world Applications","created":"2021-09-17","cited_by_count":0,"area":null},{"id":"2204.13353","title":"Attention Mechanism with Energy-Friendly Operations","created":"2022-04-28","cited_by_count":0,"area":null},{"id":"2208.10246","title":"SDBERT: SparseDistilBERT, a faster and smaller BERT model","created":"2022-07-28","cited_by_count":0,"area":null},{"id":"2211.13852","title":"Adaptive Attention Link-based Regularization for Vision Transformers","created":"2022-11-25","cited_by_count":0,"area":null},{"id":"2212.03279","title":"From Knowledge Augmentation to Multi-tasking: Towards Human-like Dialogue Systems","created":"2022-11-14","cited_by_count":0,"area":null},{"id":"2302.13475","title":"Elementwise Language Representation","created":"2023-02-27","cited_by_count":0,"area":null},{"id":"2305.14066","title":"One-stop Training of Multiple Capacity Models","created":"2023-05-23","cited_by_count":0,"area":null},{"id":"2306.13474","title":"Efficient Online Processing with Deep Neural Networks","created":"2023-06-23","cited_by_count":0,"area":null},{"id":"2407.02779","title":"Croppable Knowledge Graph Embedding","created":"2024-07-03","cited_by_count":0,"area":null},{"id":"2501.05248","title":"Deriving Coding-Specific Sub-Models from LLMs using Resource-Efficient Pruning","created":"2025-01-09","cited_by_count":0,"area":null},{"id":"2601.00526","title":"Federated Customization of Large Models: Approaches, Experiments, and Insights","created":"2026-01-02","cited_by_count":0,"area":null},{"id":"2603.03535","title":"Trade-offs in Ensembling, Merging and Routing Among Parameter-Efficient Experts","created":"2026-03-03","cited_by_count":0,"area":null},{"id":"2604.25903","title":"Carbon-Taxed Transformers: A Green Compression Pipeline for Overgrown Language Models","created":"2026-04-28","cited_by_count":0,"area":null},{"id":"2610.00820","title":"On-the-fly Weight Generation: A Hypernetwork Proof of Concept on ARC-1D","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.03112","title":"Building Interpretable Feature Representations for Resume-Vacancy Matching by Distilling Production LLM Signals","created":"2026-10-02","cited_by_count":0,"area":null}],"next_cursor":null}