{"total":67,"rows":[{"id":"2404.16710","title":"LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding","created":"2024-04-25","cited_by_count":307,"area":"inference"},{"id":"2507.10524","title":"Mixture-of-Recursions: Learning Dynamic Recursive Depths for Adaptive Token-Level Computation","created":"2025-07-14","cited_by_count":133,"area":null},{"id":"2307.09476","title":"Overthinking the Truth: Understanding how Language Models Process False Demonstrations","created":"2023-07-18","cited_by_count":81,"area":"lr"},{"id":"2106.05022","title":"Adaptive Inference through Early-Exit Networks: Design, Challenges and Directions","created":"2021-06-09","cited_by_count":75,"area":"inference"},{"id":"2602.11451","title":"LoopFormer: Elastic-Depth Looped Transformers for Latent Reasoning via Shortcut Modulation","created":"2026-02-11","cited_by_count":61,"area":"lr"},{"id":"2307.02764","title":"When Does Confidence-Based Cascade Deferral Suffice?","created":"2023-07-06","cited_by_count":60,"area":null},{"id":"2209.08310","title":"Learning to Weight Samples for Dynamic Early-exiting Networks","created":"2022-09-17","cited_by_count":44,"area":"inference"},{"id":"2211.11152","title":"You Need Multiple Exiting: Dynamic Early Exiting for Accelerating Unified Vision Language Model","created":"2022-11-21","cited_by_count":43,"area":"mllm"},{"id":"2304.01230","title":"SEENN: Towards Temporal Spiking Early-Exit Neural Networks","created":"2023-04-02","cited_by_count":41,"area":null},{"id":"2312.00333","title":"Green Edge AI: A Contemporary Survey","created":"2023-12-01","cited_by_count":25,"area":null},{"id":"2205.07324","title":"Transkimmer: Transformer Learns to Layer-wise Skim","created":"2022-05-15","cited_by_count":24,"area":null},{"id":"2206.04685","title":"Predictive Exit: Prediction of Fine-Grained Early Exits for Computation- and Energy-Efficient Inference","created":"2022-06-09","cited_by_count":24,"area":"inference"},{"id":"2510.07358","title":"Encode, Think, Decode: Scaling test-time reasoning with recursive latent thoughts","created":"2025-10-08","cited_by_count":24,"area":"lr"},{"id":"2104.09949","title":"DynO: Dynamic Onloading of Deep Neural Networks from Cloud to Device","created":"2021-04-20","cited_by_count":18,"area":null},{"id":"2105.04104","title":"AppealNet: An Efficient and Highly-Accurate Edge/Cloud Collaborative Architecture for DNN Inference","created":"2021-05-10","cited_by_count":17,"area":null},{"id":"2104.09286","title":"Learning to Cascade: Confidence Calibration for Improving the Accuracy and Computational Cost of Cascade Inference Systems","created":"2021-04-15","cited_by_count":14,"area":null},{"id":"2212.03354","title":"HADAS: Hardware-Aware Dynamic Neural Architecture Search for Edge Performance Scaling","created":"2022-12-06","cited_by_count":14,"area":null},{"id":"2103.15750","title":"Enabling Design Methodologies and Future Trends for Edge AI: Specialization and Co-design","created":"2021-03-25","cited_by_count":13,"area":null},{"id":"2402.00518","title":"EE-Tuning: An Economical yet Scalable Solution for Tuning Early-Exit Large Language Models","created":"2024-02-01","cited_by_count":13,"area":"inference"},{"id":"2505.21594","title":"Fast and Cost-effective Speculative Edge-Cloud Decoding with Early Exits","created":"2025-05-27","cited_by_count":11,"area":"inference"},{"id":"2112.15131","title":"Resource-Efficient Deep Learning: A Survey on Model-, Arithmetic-, and Implementation-Level Techniques","created":"2021-12-30","cited_by_count":9,"area":null},{"id":"2102.01875","title":"AHAR: Adaptive CNN for Energy-efficient Human Activity Recognition in Low-power Edge Devices","created":"2021-02-03","cited_by_count":8,"area":null},{"id":"2103.01148","title":"E$^2$CM: Early Exit via Class Means for Efficient Supervised and Unsupervised Learning","created":"2021-03-01","cited_by_count":8,"area":null},{"id":"2210.05742","title":"Curved Representation Space of Vision Transformers","created":"2022-10-11","cited_by_count":8,"area":null},{"id":"2305.11322","title":"Knowing When to Stop: Delay-Adaptive Spiking Neural Network Classifiers with Reliability Guarantees","created":"2023-05-18","cited_by_count":8,"area":null},{"id":"2104.07521","title":"QuickLoc: Adaptive Deep-Learning for Fast Indoor Localization with Mobile Devices","created":"2021-04-15","cited_by_count":5,"area":null},{"id":"2501.07451","title":"A Survey on Dynamic Neural Networks: from Computer Vision to Multi-modal Sensor Fusion","created":"2025-01-13","cited_by_count":5,"area":null},{"id":"2106.11208","title":"Temporal Early Exits for Efficient Video Object Detection","created":"2021-06-21","cited_by_count":4,"area":null},{"id":"2110.10343","title":"EBJR: Energy-Based Joint Reasoning for Adaptive Inference","created":"2021-10-20","cited_by_count":4,"area":null},{"id":"2403.17726","title":"Tiny Models are the Computational Saver for Large Models","created":"2024-03-26","cited_by_count":4,"area":"inference"},{"id":"2408.05247","title":"Early-Exit meets Model-Distributed Inference at Edge Networks","created":"2024-08-08","cited_by_count":4,"area":"inference"},{"id":"2410.06024","title":"Jet Expansions of Residual Computation","created":"2024-10-08","cited_by_count":4,"area":null},{"id":"2506.03302","title":"Multi-Exit Kolmogorov-Arnold Networks: enhancing accuracy and parsimony","created":"2025-06-03","cited_by_count":4,"area":null},{"id":"2111.06500","title":"Dynamic Iterative Refinement for Efficient 3D Hand Pose Estimation","created":"2021-11-11","cited_by_count":3,"area":null},{"id":"2204.03431","title":"Energy-Efficient Adaptive Machine Learning on IoT End-Nodes With Class-Dependent Confidence","created":"2022-04-07","cited_by_count":3,"area":null},{"id":"2205.13838","title":"Adaptive Random Forests for Energy-Efficient Inference on Microcontrollers","created":"2022-05-27","cited_by_count":3,"area":null},{"id":"2210.04882","title":"Layer Ensembles","created":"2022-10-10","cited_by_count":3,"area":null},{"id":"2301.12168","title":"Anticipate, Ensemble and Prune: Improving Convolutional Neural Networks via Aggregated Early Exits","created":"2023-01-28","cited_by_count":3,"area":null},{"id":"2304.10020","title":"A Survey on Deep Neural Network Partition over Cloud, Edge and End Devices","created":"2023-04-20","cited_by_count":3,"area":null},{"id":"2404.05241","title":"LightFF: Lightweight Inference for Forward-Forward Algorithm","created":"2024-04-08","cited_by_count":3,"area":null},{"id":"2409.05336","title":"Early-exit Convolutional Neural Networks","created":"2024-09-09","cited_by_count":3,"area":null},{"id":"2505.12523","title":"Energy-Aware Deep Learning on Resource-Constrained Hardware","created":"2025-05-18","cited_by_count":3,"area":null},{"id":"2101.01543","title":"Noise Sensitivity-Based Energy Efficient and Robust Adversary Detection in Neural Networks","created":"2021-01-05","cited_by_count":2,"area":null},{"id":"2109.06440","title":"Complexity-aware Adaptive Training and Inference for Edge-Cloud Distributed AI Systems","created":"2021-09-14","cited_by_count":2,"area":null},{"id":"2309.05686","title":"Temporal Patience: Efficient Adaptive Deep Learning for Embedded Radar Data Processing","created":"2023-09-11","cited_by_count":2,"area":null},{"id":"2401.16694","title":"EdgeOL: Efficient in-situ Online Learning on Edge Devices","created":"2024-01-30","cited_by_count":2,"area":null},{"id":"2403.07404","title":"Improving Continual Learning Performance and Efficiency with Auxiliary Classifiers","created":"2024-03-12","cited_by_count":2,"area":null},{"id":"2501.02508","title":"PTEENet: Post-Trained Early-Exit Neural Networks Augmentation for Inference Cost Optimization","created":"2025-01-05","cited_by_count":2,"area":"inference"},{"id":"2512.15705","title":"Dynamic Rebatching for Efficient Early-Exit Inference with DREX","created":"2025-12-17","cited_by_count":2,"area":"inference"},{"id":"2103.12896","title":"SETGAN: Scale and Energy Trade-off GANs for Image Applications on Mobile Platforms","created":"2021-03-23","cited_by_count":1,"area":null},{"id":"2109.08231","title":"RAPID-RL: A Reconfigurable Architecture with Preemptive-Exits for Efficient Deep-Reinforcement Learning","created":"2021-09-16","cited_by_count":1,"area":null},{"id":"2212.12866","title":"QuickNets: Saving Training and Preventing Overconfidence in Early-Exit Neural Architectures","created":"2022-12-25","cited_by_count":1,"area":null},{"id":"2311.15947","title":"GloNets: Globally Connected Neural Networks","created":"2023-11-27","cited_by_count":1,"area":null},{"id":"2403.07036","title":"A Converting Autoencoder Toward Low-latency and Energy-efficient DNN Inference at the Edge","created":"2024-03-11","cited_by_count":1,"area":"inference"},{"id":"2403.07958","title":"Temporal Decisions: Leveraging Temporal Correlation for Efficient Decisions in Early Exit Neural Networks","created":"2024-03-12","cited_by_count":1,"area":null},{"id":"2407.14320","title":"How to Train Your Multi-Exit Model? Analyzing the Impact of Training Strategies","created":"2024-07-19","cited_by_count":1,"area":null},{"id":"2505.01730","title":"PASCAL: Precise and Efficient ANN- SNN Conversion using Spike Accumulation and Adaptive Layerwise Activation","created":"2025-05-03","cited_by_count":1,"area":null},{"id":"2512.20755","title":"Bridging Efficiency and Safety: Formal Verification of Neural Networks with Early Exits","created":"2025-12-23","cited_by_count":1,"area":"inference"},{"id":"2604.18396","title":"River-LLM: Large Language Model Seamless Exit Based on KV Share","created":"2026-04-20","cited_by_count":1,"area":"inference"},{"id":"2106.12810","title":"A Construction Kit for Efficient Low Power Neural Network Accelerator Designs","created":"2021-06-24","cited_by_count":0,"area":null},{"id":"2308.08222","title":"HyperSNN: A new efficient and robust deep learning model for resource constrained control applications","created":"2023-08-16","cited_by_count":0,"area":null},{"id":"2309.03530","title":"Efficient Single Object Detection on Image Patches with Early Exit Enhanced High-Precision CNNs","created":"2023-09-07","cited_by_count":0,"area":null},{"id":"2505.04850","title":"ORXE: Orchestrating Experts for Dynamically Configurable Efficiency","created":"2025-05-07","cited_by_count":0,"area":null},{"id":"2505.17626","title":"Leveraging Stochastic Depth Training for Adaptive Inference","created":"2025-05-23","cited_by_count":0,"area":null},{"id":"2508.21495","title":"Rethinking Calibration for Early-Exit Neural Networks","created":"2025-08-29","cited_by_count":0,"area":"inference"},{"id":"2511.00641","title":"More Than A Shortcut: A Hyperbolic Approach To Early-Exit Networks","created":"2025-11-01","cited_by_count":0,"area":"inference"},{"id":"2603.17275","title":"DANCE: Dynamic 3D CNN Pruning: Joint Frame, Channel, and Feature Adaptation for Energy Efficiency on the Edge","created":"2026-03-18","cited_by_count":0,"area":null}],"next_cursor":null}