{"total":56,"rows":[{"id":"2306.07629","title":"SqueezeLLM: Dense-and-Sparse Quantization","created":"2023-06-13","cited_by_count":294,"area":null},{"id":"2402.14905","title":"MobileLLM: Optimizing Sub-billion Parameter Language Models for On-Device Use Cases","created":"2024-02-22","cited_by_count":223,"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":"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":"2109.15082","title":"Towards Efficient Post-training Quantization of Pre-trained Language Models","created":"2021-09-30","cited_by_count":39,"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":"2410.20011","title":"A Survey of Small Language Models","created":"2024-10-25","cited_by_count":31,"area":null},{"id":"2310.16712","title":"LLM Performance Predictors are good initializers for Architecture Search","created":"2023-10-25","cited_by_count":29,"area":null},{"id":"2205.01500","title":"Meta Learning for Natural Language Processing: A Survey","created":"2022-05-03","cited_by_count":26,"area":null},{"id":"2303.04185","title":"Gradient-Free Structured Pruning with Unlabeled Data","created":"2023-03-07","cited_by_count":26,"area":null},{"id":"2111.11802","title":"Pruning Self-attentions into Convolutional Layers in Single Path","created":"2021-11-23","cited_by_count":24,"area":null},{"id":"2108.12821","title":"Analyzing and Mitigating Interference in Neural Architecture Search","created":"2021-08-29","cited_by_count":20,"area":null},{"id":"2410.14649","title":"EvoPress: Accurate Dynamic Model Compression via Evolutionary Search","created":"2024-10-18","cited_by_count":20,"area":null},{"id":"2109.07222","title":"EfficientBERT: Progressively Searching Multilayer Perceptron via Warm-up Knowledge Distillation","created":"2021-09-15","cited_by_count":15,"area":"distill"},{"id":"2205.10036","title":"Exploring Extreme Parameter Compression for Pre-trained Language Models","created":"2022-05-20","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":"2205.11656","title":"FlexiBERT: Are Current Transformer Architectures too Homogeneous and Rigid?","created":"2022-05-23","cited_by_count":12,"area":null},{"id":"2207.03677","title":"SuperTickets: Drawing Task-Agnostic Lottery Tickets from Supernets via Jointly Architecture Searching and Parameter Pruning","created":"2022-07-08","cited_by_count":12,"area":null},{"id":"2210.07535","title":"AutoMoE: Heterogeneous Mixture-of-Experts with Adaptive Computation for Efficient Neural Machine Translation","created":"2022-10-14","cited_by_count":10,"area":"moe"},{"id":"2502.06663","title":"EfficientLLM: Scalable Pruning-Aware Pretraining for Architecture-Agnostic Edge Language Models","created":"2025-02-10","cited_by_count":10,"area":null},{"id":"2306.00288","title":"Training-free Neural Architecture Search for RNNs and Transformers","created":"2023-06-01","cited_by_count":9,"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":"2306.04845","title":"Mixture-of-Supernets: Improving Weight-Sharing Supernet Training with Architecture-Routed Mixture-of-Experts","created":"2023-06-08","cited_by_count":7,"area":"moe"},{"id":"2510.00379","title":"Composer: A Search Framework for Hybrid Neural Architecture Design","created":"2025-10-01","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":"2306.14393","title":"Constraint-aware and Ranking-distilled Token Pruning for Efficient Transformer Inference","created":"2023-06-26","cited_by_count":6,"area":"inference"},{"id":"2404.01353","title":"Efficiently Distilling LLMs for Edge Applications","created":"2024-04-01","cited_by_count":5,"area":"distill"},{"id":"2405.02267","title":"Structural Pruning of Pre-trained Language Models via Neural Architecture Search","created":"2024-05-03","cited_by_count":5,"area":null},{"id":"2406.01414","title":"CE-NAS: An End-to-End Carbon-Efficient Neural Architecture Search Framework","created":"2024-06-03","cited_by_count":5,"area":null},{"id":"2408.01890","title":"Cross-layer Attention Sharing for Pre-trained Large Language Models","created":"2024-08-04","cited_by_count":5,"area":"inference"},{"id":"2209.00625","title":"SwiftPruner: Reinforced Evolutionary Pruning for Efficient Ad Relevance","created":"2022-08-30","cited_by_count":4,"area":null},{"id":"2308.02746","title":"Meta-Tsallis-Entropy Minimization: A New Self-Training Approach for Domain Adaptation on Text Classification","created":"2023-08-04","cited_by_count":4,"area":null},{"id":"2309.09003","title":"RingMo-lite: A Remote Sensing Multi-task Lightweight Network with CNN-Transformer Hybrid Framework","created":"2023-09-16","cited_by_count":4,"area":null},{"id":"2405.02543","title":"Exploring Extreme Quantization in Spiking Language Models","created":"2024-05-04","cited_by_count":4,"area":null},{"id":"2201.12507","title":"AutoDistil: Few-shot Task-agnostic Neural Architecture Search for Distilling Large Language Models","created":"2022-01-29","cited_by_count":3,"area":"distill"},{"id":"2310.01180","title":"Evolutionary Neural Architecture Search for Transformer in Knowledge Tracing","created":"2023-10-02","cited_by_count":3,"area":null},{"id":"2403.07921","title":"Merino: Entropy-driven Design for Generative Language Models on IoT Devices","created":"2024-02-28","cited_by_count":3,"area":null},{"id":"2410.17957","title":"MCUBERT: Memory-Efficient BERT Inference on Commodity Microcontrollers","created":"2024-10-23","cited_by_count":3,"area":null},{"id":"2303.13745","title":"EdgeTran: Co-designing Transformers for Efficient Inference on Mobile Edge Platforms","created":"2023-03-24","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":"2111.12952","title":"AutoHEnsGNN: Winning Solution to AutoGraph Challenge for KDD Cup 2020","created":"2021-11-25","cited_by_count":1,"area":null},{"id":"2208.10498","title":"Design Automation for Fast, Lightweight, and Effective Deep Learning Models: A Survey","created":"2022-08-22","cited_by_count":1,"area":null},{"id":"2303.14882","title":"TransCODE: Co-design of Transformers and Accelerators for Efficient Training and Inference","created":"2023-03-27","cited_by_count":1,"area":null},{"id":"2504.15983","title":"W-PCA Based Gradient-Free Proxy for Efficient Search of Lightweight Language Models","created":"2025-04-22","cited_by_count":1,"area":null},{"id":"2608.06901","title":"Prune Once: Retraining-Free Task-Agnostic Pruning for Vision-Language Models","created":"2026-08-07","cited_by_count":1,"area":"mllm"},{"id":"2209.12127","title":"SpeedLimit: Neural Architecture Search for Quantized Transformer Models","created":"2022-09-25","cited_by_count":0,"area":null},{"id":"2305.12868","title":"NAS-FM: Neural Architecture Search for Tunable and Interpretable Sound Synthesis based on Frequency Modulation","created":"2023-05-22","cited_by_count":0,"area":null},{"id":"2407.08887","title":"Automatic Pruning of Fine-tuning Datasets for Transformer-based Language Models","created":"2024-07-11","cited_by_count":0,"area":null},{"id":"2408.12526","title":"Exploiting Student Parallelism for Efficient GPU Inference of BERT-like Models in Online Services","created":"2024-08-22","cited_by_count":0,"area":null},{"id":"2510.27037","title":"Elastic Architecture Search for Efficient Language Models","created":"2025-10-30","cited_by_count":0,"area":null},{"id":"2601.04918","title":"Breaking Robustness Barriers in Cognitive Diagnosis: A One-Shot Neural Architecture Search Perspective","created":"2026-01-08","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":"2608.21712","title":"ATHENA: Knowledge-guided agentic neural architecture search for AutoFormer-based electronic health record modeling","created":"2026-08-22","cited_by_count":0,"area":"agents"}],"next_cursor":null}