{"total":153,"rows":[{"id":"2306.14048","title":"H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models","created":"2023-06-24","cited_by_count":832,"area":"inference"},{"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":"2302.08582","title":"Pretraining Language Models with Human Preferences","created":"2023-02-16","cited_by_count":247,"area":"alignment"},{"id":"2104.08826","title":"GPT3Mix: Leveraging Large-scale Language Models for Text Augmentation","created":"2021-04-18","cited_by_count":187,"area":null},{"id":"2108.13323","title":"FedKD: Communication Efficient Federated Learning via Knowledge Distillation","created":"2021-08-30","cited_by_count":187,"area":"distill"},{"id":"2109.04838","title":"Block Pruning For Faster Transformers","created":"2021-09-10","cited_by_count":177,"area":null},{"id":"2302.07863","title":"Speculative Decoding with Big Little Decoder","created":"2023-02-15","cited_by_count":164,"area":"inference"},{"id":"2107.00910","title":"Learned Token Pruning for Transformers","created":"2021-07-02","cited_by_count":139,"area":"inference"},{"id":"2307.15190","title":"f-Divergence Minimization for Sequence-Level Knowledge Distillation","created":"2023-07-27","cited_by_count":114,"area":"distill"},{"id":"2402.12374","title":"Sequoia: Scalable, Robust, and Hardware-aware Speculative Decoding","created":"2024-02-19","cited_by_count":103,"area":"inference"},{"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":"2407.01885","title":"Survey on Knowledge Distillation for Large Language Models: Methods, Evaluation, and Application","created":"2024-07-02","cited_by_count":56,"area":"distill"},{"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":"2402.13516","title":"ProSparse: Introducing and Enhancing Intrinsic Activation Sparsity within Large Language Models","created":"2024-02-21","cited_by_count":45,"area":"inference"},{"id":"2105.12967","title":"Selective Knowledge Distillation for Neural Machine Translation","created":"2021-05-27","cited_by_count":43,"area":"distill"},{"id":"2106.01023","title":"One Teacher is Enough? Pre-trained Language Model Distillation from Multiple Teachers","created":"2021-06-02","cited_by_count":40,"area":"distill"},{"id":"2109.08359","title":"Distilling Linguistic Context for Language Model Compression","created":"2021-09-17","cited_by_count":33,"area":"distill"},{"id":"2306.12509","title":"Joint Prompt Optimization of Stacked LLMs using Variational Inference","created":"2023-06-21","cited_by_count":32,"area":null},{"id":"2105.05912","title":"MATE-KD: Masked Adversarial TExt, a Companion to Knowledge Distillation","created":"2021-05-12","cited_by_count":27,"area":"distill"},{"id":"2308.04268","title":"Teacher-Student Architecture for Knowledge Distillation: A Survey","created":"2023-08-08","cited_by_count":26,"area":"distill"},{"id":"2302.09632","title":"HomoDistil: Homotopic Task-Agnostic Distillation of Pre-trained Transformers","created":"2023-02-19","cited_by_count":25,"area":"distill"},{"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":"2210.17332","title":"Teacher-Student Architecture for Knowledge Learning: A Survey","created":"2022-10-28","cited_by_count":23,"area":"distill"},{"id":"2404.08698","title":"Lossless Acceleration of Large Language Model via Adaptive N-gram Parallel Decoding","created":"2024-04-10","cited_by_count":23,"area":"inference"},{"id":"2312.10730","title":"Mixed Distillation Helps Smaller Language Model Better Reasoning","created":"2023-12-17","cited_by_count":19,"area":"lr"},{"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":"2102.04887","title":"NewsBERT: Distilling Pre-trained Language Model for Intelligent News Application","created":"2021-02-09","cited_by_count":17,"area":"distill"},{"id":"2308.15122","title":"SpikeBERT: A Language Spikformer Learned from BERT with Knowledge Distillation","created":"2023-08-29","cited_by_count":17,"area":"distill"},{"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":"2107.00175","title":"Elbert: Fast Albert with Confidence-Window Based Early Exit","created":"2021-07-01","cited_by_count":14,"area":"inference"},{"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":"2404.14827","title":"Sentence-Level or Token-Level? A Comprehensive Study on Knowledge Distillation","created":"2024-04-23","cited_by_count":12,"area":"distill"},{"id":"2302.08387","title":"LEALLA: Learning Lightweight Language-agnostic Sentence Embeddings with Knowledge Distillation","created":"2023-02-16","cited_by_count":11,"area":"distill"},{"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":"2503.24198","title":"TwT: Thinking without Tokens by Habitual Reasoning Distillation with Multi-Teachers' Guidance","created":"2025-03-31","cited_by_count":11,"area":"lr"},{"id":"2101.08890","title":"Distilling Large Language Models into Tiny and Effective Students using pQRNN","created":"2021-01-21","cited_by_count":10,"area":"distill"},{"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":"2311.08640","title":"Multistage Collaborative Knowledge Distillation from a Large Language Model for Semi-Supervised Sequence Generation","created":"2023-11-15","cited_by_count":10,"area":"distill"},{"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":"2507.01887","title":"MiCoTA: Bridging the Learnability Gap with Intermediate CoT and Teacher Assistants","created":"2025-07-02","cited_by_count":9,"area":"lr"},{"id":"2602.01064","title":"Exploring Knowledge Purification in Multi-Teacher Knowledge Distillation for LLMs","created":"2026-02-01","cited_by_count":9,"area":"distill"},{"id":"2305.09651","title":"Tailoring Instructions to Student's Learning Levels Boosts Knowledge Distillation","created":"2023-05-16","cited_by_count":8,"area":"distill"},{"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":"2205.02340","title":"Knowledge Distillation of Russian Language Models with Reduction of Vocabulary","created":"2022-05-04","cited_by_count":7,"area":"distill"},{"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":"2308.11807","title":"Towards an On-device Agent for Text Rewriting","created":"2023-08-22","cited_by_count":7,"area":"agents"},{"id":"2104.11928","title":"Extract then Distill: Efficient and Effective Task-Agnostic BERT Distillation","created":"2021-04-24","cited_by_count":6,"area":"distill"},{"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":"2308.16561","title":"MoMA: Momentum Contrastive Learning with Multi-head Attention-based Knowledge Distillation for Histopathology Image Analysis","created":"2023-08-31","cited_by_count":6,"area":"distill"},{"id":"2505.00284","title":"LightEMMA: A Longitudinal Evaluation of Vision-Language Models for Autonomous Driving","created":"2025-05-01","cited_by_count":6,"area":"mllm"},{"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":"2107.00411","title":"Knowledge Distillation for Quality Estimation","created":"2021-07-01","cited_by_count":5,"area":"distill"},{"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":"2201.00558","title":"Which Student is Best? A Comprehensive Knowledge Distillation Exam for Task-Specific BERT Models","created":"2022-01-03","cited_by_count":5,"area":"distill"},{"id":"2211.01071","title":"Gradient Knowledge Distillation for Pre-trained Language Models","created":"2022-11-02","cited_by_count":5,"area":"distill"},{"id":"2305.14864","title":"Just CHOP: Embarrassingly Simple LLM Compression","created":"2023-05-24","cited_by_count":5,"area":"lr"},{"id":"2306.08909","title":"Bridging the Gap between Decision and Logits in Decision-based Knowledge Distillation for Pre-trained Language Models","created":"2023-06-15","cited_by_count":5,"area":"distill"},{"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":"2407.20299","title":"Dataset Distillation for Offline Reinforcement Learning","created":"2024-07-29","cited_by_count":5,"area":"offlinerl"},{"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":"2204.07674","title":"CILDA: Contrastive Data Augmentation using Intermediate Layer Knowledge Distillation","created":"2022-04-15","cited_by_count":4,"area":"distill"},{"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":"2301.03416","title":"ERNIE 3.0 Tiny: Frustratingly Simple Method to Improve Task-Agnostic Distillation Generalization","created":"2023-01-09","cited_by_count":3,"area":"distill"},{"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":"2411.00052","title":"Larger models yield better results? Streamlined severity classification of ADHD-related concerns using BERT-based knowledge distillation","created":"2024-10-30","cited_by_count":3,"area":"distill"},{"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":"2412.15750","title":"Extracting Interpretable Task-Specific Circuits from Large Language Models for Faster Inference","created":"2024-12-20","cited_by_count":3,"area":"mechinterp"},{"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":"2101.08106","title":"Learning to Augment for Data-Scarce Domain BERT Knowledge Distillation","created":"2021-01-20","cited_by_count":2,"area":"distill"},{"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":"2109.10724","title":"Low-Latency Incremental Text-to-Speech Synthesis with Distilled Context Prediction Network","created":"2021-09-22","cited_by_count":2,"area":"distill"},{"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":"2210.11768","title":"Augmentation with Projection: Towards an Effective and Efficient Data Augmentation Paradigm for Distillation","created":"2022-10-21","cited_by_count":2,"area":"distill"}],"next_cursor":"100"}