{"total":98,"rows":[{"id":"2211.17192","title":"Fast Inference from Transformers via Speculative Decoding","created":"2022-11-30","cited_by_count":1653,"area":"inference"},{"id":"2205.05638","title":"Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning","created":"2022-05-11","cited_by_count":896,"area":null},{"id":"2302.05442","title":"Scaling Vision Transformers to 22 Billion Parameters","created":"2023-02-10","cited_by_count":694,"area":null},{"id":"2111.07991","title":"LiT: Zero-Shot Transfer with Locked-image text Tuning","created":"2021-11-15","cited_by_count":577,"area":null},{"id":"2207.00032","title":"DeepSpeed Inference: Enabling Efficient Inference of Transformer Models at Unprecedented Scale","created":"2022-06-30","cited_by_count":407,"area":null},{"id":"2207.07061","title":"Confident Adaptive Language Modeling","created":"2022-07-14","cited_by_count":310,"area":"inference"},{"id":"2205.05131","title":"UL2: Unifying Language Learning Paradigms","created":"2022-05-10","cited_by_count":295,"area":null},{"id":"2307.10169","title":"Challenges and Applications of Large Language Models","created":"2023-07-19","cited_by_count":254,"area":null},{"id":"2307.06304","title":"Patch n' Pack: NaViT, a Vision Transformer for any Aspect Ratio and Resolution","created":"2023-07-12","cited_by_count":229,"area":null},{"id":"2212.05055","title":"Sparse Upcycling: Training Mixture-of-Experts from Dense Checkpoints","created":"2022-12-09","cited_by_count":209,"area":"moe"},{"id":"2305.07027","title":"EfficientViT: Memory Efficient Vision Transformer with Cascaded Group Attention","created":"2023-05-11","cited_by_count":172,"area":null},{"id":"2212.08013","title":"FlexiViT: One Model for All Patch Sizes","created":"2022-12-15","cited_by_count":152,"area":null},{"id":"2310.12963","title":"AutoMix: Automatically Mixing Language Models","created":"2023-10-19","cited_by_count":125,"area":null},{"id":"2206.04040","title":"MobileOne: An Improved One millisecond Mobile Backbone","created":"2022-06-08","cited_by_count":109,"area":null},{"id":"2207.10551","title":"Scaling Laws vs Model Architectures: How does Inductive Bias Influence Scaling?","created":"2022-07-21","cited_by_count":103,"area":null},{"id":"2403.02181","title":"Not All Layers of LLMs Are Necessary During Inference","created":"2024-03-04","cited_by_count":96,"area":null},{"id":"2305.13035","title":"Getting ViT in Shape: Scaling Laws for Compute-Optimal Model Design","created":"2023-05-22","cited_by_count":89,"area":null},{"id":"2203.08101","title":"ARTEMIS: Attention-based Retrieval with Text-Explicit Matching and Implicit Similarity","created":"2022-03-15","cited_by_count":83,"area":null},{"id":"2212.14034","title":"Cramming: Training a Language Model on a Single GPU in One Day","created":"2022-12-28","cited_by_count":81,"area":null},{"id":"2209.00099","title":"Efficient Methods for Natural Language Processing: A Survey","created":"2022-08-31","cited_by_count":78,"area":null},{"id":"2410.20672","title":"Relaxed Recursive Transformers: Effective Parameter Sharing with Layer-wise LoRA","created":"2024-10-28","cited_by_count":78,"area":null},{"id":"2205.09726","title":"RankGen: Improving Text Generation with Large Ranking Models","created":"2022-05-19","cited_by_count":72,"area":null},{"id":"2203.00759","title":"HyperPrompt: Prompt-based Task-Conditioning of Transformers","created":"2022-03-01","cited_by_count":67,"area":null},{"id":"2502.08606","title":"Distillation Scaling Laws","created":"2025-02-12","cited_by_count":67,"area":"lr"},{"id":"2303.14177","title":"Scaling Expert Language Models with Unsupervised Domain Discovery","created":"2023-03-24","cited_by_count":60,"area":null},{"id":"2308.04657","title":"Which Tokens to Use? Investigating Token Reduction in Vision Transformers","created":"2023-08-09","cited_by_count":60,"area":"inference"},{"id":"2111.12993","title":"PolyViT: Co-training Vision Transformers on Images, Videos and Audio","created":"2021-11-25","cited_by_count":58,"area":null},{"id":"2210.11399","title":"Transcending Scaling Laws with 0.1% Extra Compute","created":"2022-10-20","cited_by_count":57,"area":null},{"id":"2305.19268","title":"Intriguing Properties of Quantization at Scale","created":"2023-05-30","cited_by_count":49,"area":null},{"id":"2305.11841","title":"How Does Generative Retrieval Scale to Millions of Passages?","created":"2023-05-19","cited_by_count":48,"area":null},{"id":"2307.06440","title":"No Train No Gain: Revisiting Efficient Training Algorithms For Transformer-based Language Models","created":"2023-07-12","cited_by_count":41,"area":null},{"id":"2210.06640","title":"Compute-Efficient Deep Learning: Algorithmic Trends and Opportunities","created":"2022-10-13","cited_by_count":38,"area":null},{"id":"2304.00287","title":"Vision Transformers with Mixed-Resolution Tokenization","created":"2023-04-01","cited_by_count":36,"area":null},{"id":"2410.16377","title":"A Simple Model of Inference Scaling Laws","created":"2024-10-21","cited_by_count":36,"area":null},{"id":"2306.08107","title":"AutoML in the Age of Large Language Models: Current Challenges, Future Opportunities and Risks","created":"2023-06-13","cited_by_count":35,"area":null},{"id":"2406.02657","title":"Block Transformer: Global-to-Local Language Modeling for Fast Inference","created":"2024-06-04","cited_by_count":32,"area":"inference"},{"id":"2112.13692","title":"Augmenting Convolutional networks with attention-based aggregation","created":"2021-12-27","cited_by_count":29,"area":null},{"id":"2402.02887","title":"Time-, Memory- and Parameter-Efficient Visual Adaptation","created":"2024-02-05","cited_by_count":28,"area":null},{"id":"2112.11435","title":"Learned Queries for Efficient Local Attention","created":"2021-12-21","cited_by_count":27,"area":null},{"id":"2301.02240","title":"Skip-Attention: Improving Vision Transformers by Paying Less Attention","created":"2023-01-05","cited_by_count":24,"area":null},{"id":"2408.14471","title":"A Practitioner's Guide to Continual Multimodal Pretraining","created":"2024-08-26","cited_by_count":23,"area":null},{"id":"2301.13195","title":"Adaptive Computation with Elastic Input Sequence","created":"2023-01-30","cited_by_count":22,"area":null},{"id":"2306.11726","title":"How can objects help action recognition?","created":"2023-06-20","cited_by_count":21,"area":null},{"id":"2407.05694","title":"On the Limitations of Compute Thresholds as a Governance Strategy","created":"2024-07-08","cited_by_count":18,"area":null},{"id":"2210.02720","title":"Understanding Gradient Regularization in Deep Learning: Efficient Finite-Difference Computation and Implicit Bias","created":"2022-10-06","cited_by_count":16,"area":null},{"id":"2310.06522","title":"Watt For What: Rethinking Deep Learning's Energy-Performance Relationship","created":"2023-10-10","cited_by_count":16,"area":null},{"id":"2308.15291","title":"Towards quantitative precision for ECG analysis: Leveraging state space models, self-supervision and patient metadata","created":"2023-08-29","cited_by_count":15,"area":null},{"id":"2505.01821","title":"Edge-Cloud Collaborative Computing on Distributed Intelligence and Model Optimization: A Survey","created":"2025-05-03","cited_by_count":14,"area":null},{"id":"2211.06088","title":"RepGhost: A Hardware-Efficient Ghost Module via Re-parameterization","created":"2022-11-11","cited_by_count":13,"area":null},{"id":"2210.07111","title":"A Multi-dimensional Evaluation of Tokenizer-free Multilingual Pretrained Models","created":"2022-10-13","cited_by_count":12,"area":null},{"id":"2411.05818","title":"Open LLMs are Necessary for Current Private Adaptations and Outperform their Closed Alternatives","created":"2024-11-02","cited_by_count":12,"area":null},{"id":"2502.12123","title":"On the Query Complexity of Verifier-Assisted Language Generation","created":"2025-02-17","cited_by_count":12,"area":"lr"},{"id":"2302.06117","title":"The Framework Tax: Disparities Between Inference Efficiency in NLP Research and Deployment","created":"2023-02-13","cited_by_count":11,"area":null},{"id":"2402.19472","title":"Efficient Lifelong Model Evaluation in an Era of Rapid Progress","created":"2024-02-29","cited_by_count":10,"area":null},{"id":"2204.11458","title":"ED2LM: Encoder-Decoder to Language Model for Faster Document Re-ranking Inference","created":"2022-04-25","cited_by_count":9,"area":null},{"id":"2304.00897","title":"Accuracy is not the only Metric that matters: Estimating the Energy Consumption of Deep Learning Models","created":"2023-04-03","cited_by_count":9,"area":null},{"id":"2308.09372","title":"Which Transformer to Favor: A Comparative Analysis of Efficiency in Vision Transformers","created":"2023-08-18","cited_by_count":9,"area":null},{"id":"2311.03747","title":"SBCFormer: Lightweight Network Capable of Full-size ImageNet Classification at 1 FPS on Single Board Computers","created":"2023-11-07","cited_by_count":9,"area":null},{"id":"2311.12821","title":"Advancing The Rate-Distortion-Computation Frontier For Neural Image Compression","created":"2023-09-26","cited_by_count":9,"area":null},{"id":"2411.13055","title":"Hardware Scaling Trends and Diminishing Returns in Large-Scale Distributed Training","created":"2024-11-20","cited_by_count":8,"area":null},{"id":"2307.09701","title":"Efficiency Pentathlon: A Standardized Arena for Efficiency Evaluation","created":"2023-07-19","cited_by_count":7,"area":null},{"id":"2411.07501","title":"LAuReL: Learned Augmented Residual Layer","created":"2024-11-12","cited_by_count":7,"area":null},{"id":"2206.14098","title":"RevBiFPN: The Fully Reversible Bidirectional Feature Pyramid Network","created":"2022-06-28","cited_by_count":6,"area":null},{"id":"2409.03460","title":"LowFormer: Hardware Efficient Design for Convolutional Transformer Backbones","created":"2024-09-05","cited_by_count":6,"area":null},{"id":"2410.23261","title":"$100K or 100 Days: Trade-offs when Pre-Training with Academic Resources","created":"2024-10-30","cited_by_count":6,"area":null},{"id":"2204.08226","title":"Empirical Evaluation and Theoretical Analysis for Representation Learning: A Survey","created":"2022-04-18","cited_by_count":5,"area":null},{"id":"2504.21174","title":"Efficient LLMs with AMP: Attention Heads and MLP Pruning","created":"2025-04-29","cited_by_count":5,"area":null},{"id":"2305.13905","title":"EfficientSpeech: An On-Device Text to Speech Model","created":"2023-05-23","cited_by_count":4,"area":null},{"id":"2306.04822","title":"Optimizing ViViT Training: Time and Memory Reduction for Action Recognition","created":"2023-06-07","cited_by_count":4,"area":null},{"id":"2309.06047","title":"Real-Time Semantic Segmentation: A Brief Survey & Comparative Study in Remote Sensing","created":"2023-09-12","cited_by_count":4,"area":null},{"id":"2407.12220","title":"Questionable practices in machine learning","created":"2024-07-17","cited_by_count":4,"area":null},{"id":"2410.05930","title":"Fortify Your Foundations: Practical Privacy and Security for Foundation Model Deployments In The Cloud","created":"2024-10-08","cited_by_count":4,"area":null},{"id":"2601.22362","title":"Understanding Efficiency: Quantization, Batching, and Serving Strategies in LLM Energy Use","created":"2026-01-29","cited_by_count":4,"area":null},{"id":"2402.17227","title":"Efficient Backpropagation with Variance-Controlled Adaptive Sampling","created":"2024-02-27","cited_by_count":3,"area":null},{"id":"2211.06646","title":"Efficient Speech Quality Assessment using Self-supervised Framewise Embeddings","created":"2022-11-12","cited_by_count":2,"area":null},{"id":"2306.11304","title":"Traversing Between Modes in Function Space for Fast Ensembling","created":"2023-06-20","cited_by_count":2,"area":null},{"id":"2503.08524","title":"Position-Aware Depth Decay Decoding ($D^3$): Boosting Large Language Model Inference Efficiency","created":"2025-03-11","cited_by_count":2,"area":null},{"id":"2112.08570","title":"Can Multilinguality benefit Non-autoregressive Machine Translation?","created":"2021-12-16","cited_by_count":1,"area":null},{"id":"2503.11335","title":"APLA: A Simple Adaptation Method for Vision Transformers","created":"2025-03-14","cited_by_count":1,"area":null},{"id":"2503.17110","title":"Beyond Accuracy: What Matters in Designing Well-Behaved Image Classification Models?","created":"2025-03-21","cited_by_count":1,"area":null},{"id":"2510.06502","title":"GUIDE: Guided Initialization and Distillation of Embeddings","created":"2025-10-07","cited_by_count":1,"area":"distill"},{"id":"2511.22849","title":"PerfMamba: Performance Analysis and Pruning of Selective State Space Models","created":"2025-11-28","cited_by_count":1,"area":"ssm"},{"id":"2601.22357","title":"Small Talk, Big Impact: The Energy Cost of Thanking AI","created":"2026-01-29","cited_by_count":1,"area":null},{"id":"2210.12022","title":"Performance-Efficiency Trade-Offs in Adapting Language Models to Text Classification Tasks","created":"2022-10-21","cited_by_count":0,"area":null},{"id":"2306.08667","title":"When to Use Efficient Self Attention? Profiling Text, Speech and Image Transformer Variants","created":"2023-06-14","cited_by_count":0,"area":null},{"id":"2404.00807","title":"GAMA-IR: Global Additive Multidimensional Averaging for Fast Image Restoration","created":"2024-03-31","cited_by_count":0,"area":null},{"id":"2411.14345","title":"Layer Pruning with Consensus: A Triple-Win Solution","created":"2024-11-21","cited_by_count":0,"area":null},{"id":"2412.03871","title":"CLIP-PING: Boosting Lightweight Vision-Language Models with Proximus Intrinsic Neighbors Guidance","created":"2024-12-05","cited_by_count":0,"area":"mllm"},{"id":"2509.10530","title":"Dynamic Adaptive Shared Experts with Grouped Multi-Head Attention Mixture of Experts","created":"2025-09-05","cited_by_count":0,"area":"moe"},{"id":"2511.17031","title":"Energy Scaling Laws for Diffusion Models: Quantifying Compute in Image Generation","created":"2025-11-21","cited_by_count":0,"area":"diffusion"},{"id":"2603.26551","title":"Beyond MACs: Hardware Efficient Architecture Design for Vision Backbones","created":"2026-03-27","cited_by_count":0,"area":null},{"id":"2605.18029","title":"What Matters for Grocery Product Retrieval with Open Source Vision Language Models","created":"2026-05-18","cited_by_count":0,"area":"mllm"},{"id":"2606.07632","title":"Evaluation of ML Resource Utilization Requires Model Life Cycle Assessment","created":"2026-05-31","cited_by_count":0,"area":null},{"id":"2608.24056","title":"PhysicsBench: A Unified Leaderboard for Generative and Predictive Models in Engineering Design and Simulation","created":"2026-08-25","cited_by_count":0,"area":null},{"id":"2608.29376","title":"Evaluating Tiny Recursive Models Across Training for Code Generation","created":"2026-08-29","cited_by_count":0,"area":null},{"id":"2609.10355","title":"Why Is Video Still So Expensive? A Survey of Inference-Efficiency Mechanisms in Video and Audiovisual LLMs","created":"2026-09-09","cited_by_count":0,"area":null},{"id":"2609.24782","title":"Virtual neural networks: hundreds of souls in a body","created":"2026-09-21","cited_by_count":0,"area":null},{"id":"2609.38426","title":"LoopVL: Recurrent Visual Intelligence","created":"2026-09-29","cited_by_count":0,"area":null}],"next_cursor":null}