{"total":75,"rows":[{"id":"2312.04916","title":"EE-LLM: Large-Scale Training and Inference of Early-Exit Large Language Models with 3D Parallelism","created":"2023-12-08","cited_by_count":69,"area":"inference"},{"id":"2211.09961","title":"Path Independent Equilibrium Models Can Better Exploit Test-Time Computation","created":"2022-11-18","cited_by_count":38,"area":null},{"id":"2403.12844","title":"MELTing point: Mobile Evaluation of Language Transformers","created":"2024-03-19","cited_by_count":36,"area":null},{"id":"2408.10681","title":"HMoE: Heterogeneous Mixture of Experts for Language Modeling","created":"2024-08-20","cited_by_count":29,"area":"moe"},{"id":"2109.13963","title":"Smart at what cost? Characterising Mobile Deep Neural Networks in the wild","created":"2021-09-28","cited_by_count":25,"area":null},{"id":"2308.14363","title":"Mobile Foundation Model as Firmware","created":"2023-08-28","cited_by_count":25,"area":null},{"id":"2312.00333","title":"Green Edge AI: A Contemporary Survey","created":"2023-12-01","cited_by_count":25,"area":null},{"id":"2411.02829","title":"CE-CoLLM: Efficient and Adaptive Large Language Models Through Cloud-Edge Collaboration","created":"2024-11-05","cited_by_count":25,"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":"2504.08850","title":"SpecEE: Accelerating Large Language Model Inference with Speculative Early Exiting","created":"2025-04-11","cited_by_count":23,"area":"inference"},{"id":"2302.06359","title":"Fixing Overconfidence in Dynamic Neural Networks","created":"2023-02-13","cited_by_count":19,"area":null},{"id":"2303.07129","title":"AdaptiveNet: Post-deployment Neural Architecture Adaptation for Diverse Edge Environments","created":"2023-03-13","cited_by_count":19,"area":null},{"id":"2303.08010","title":"Window-Based Early-Exit Cascades for Uncertainty Estimation: When Deep Ensembles are More Efficient than Single Models","created":"2023-03-14","cited_by_count":16,"area":"inference"},{"id":"2310.09163","title":"Jointly-Learned Exit and Inference for a Dynamic Neural Network : JEI-DNN","created":"2023-10-13","cited_by_count":15,"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":"2202.06512","title":"Benchmarking of DL Libraries and Models on Mobile Devices","created":"2022-02-14","cited_by_count":12,"area":null},{"id":"2210.10514","title":"The Future of Consumer Edge-AI Computing","created":"2022-10-19","cited_by_count":12,"area":null},{"id":"2206.07269","title":"Resource-Constrained Edge AI with Early Exit Prediction","created":"2022-06-15","cited_by_count":11,"area":"inference"},{"id":"2301.07099","title":"Adaptive Deep Neural Network Inference Optimization with EENet","created":"2023-01-15","cited_by_count":9,"area":"inference"},{"id":"2407.03086","title":"Effective Heterogeneous Federated Learning via Efficient Hypernetwork-based Weight Generation","created":"2024-07-03","cited_by_count":9,"area":null},{"id":"2308.14929","title":"Maestro: Uncovering Low-Rank Structures via Trainable Decomposition","created":"2023-08-28","cited_by_count":8,"area":null},{"id":"2308.16678","title":"Dynamic nsNet2: Efficient Deep Noise Suppression with Early Exiting","created":"2023-08-31","cited_by_count":7,"area":null},{"id":"2310.08866","title":"Adaptivity and Modularity for Efficient Generalization Over Task Complexity","created":"2023-10-13","cited_by_count":7,"area":null},{"id":"2504.12988","title":"Why Ask One When You Can Ask $k$? Learning-to-Defer to the Top-$k$ Experts","created":"2025-04-17","cited_by_count":7,"area":null},{"id":"2209.13443","title":"Fluid Batching: Exit-Aware Preemptive Serving of Early-Exit Neural Networks on Edge NPUs","created":"2022-09-27","cited_by_count":6,"area":"inference"},{"id":"2212.04084","title":"Federated Learning for Inference at Anytime and Anywhere","created":"2022-12-08","cited_by_count":6,"area":null},{"id":"2311.05931","title":"Early-Exit Neural Networks with Nested Prediction Sets","created":"2023-11-10","cited_by_count":6,"area":null},{"id":"2503.22567","title":"Benchmarking Ultra-Low-Power $\\mu$NPUs","created":"2025-03-28","cited_by_count":6,"area":null},{"id":"2110.02865","title":"Spike-inspired Rank Coding for Fast and Accurate Recurrent Neural Networks","created":"2021-10-06","cited_by_count":5,"area":null},{"id":"2212.00192","title":"Towards Practical Few-shot Federated NLP","created":"2022-12-01","cited_by_count":5,"area":null},{"id":"2312.01692","title":"Risk-Controlling Model Selection via Guided Bayesian Optimization","created":"2023-12-04","cited_by_count":5,"area":null},{"id":"2212.01562","title":"Understanding the Robustness of Multi-Exit Models under Common Corruptions","created":"2022-12-03","cited_by_count":4,"area":"inference"},{"id":"2403.17726","title":"Tiny Models are the Computational Saver for Large Models","created":"2024-03-26","cited_by_count":4,"area":"inference"},{"id":"2412.19325","title":"Performance Control in Early Exiting to Deploy Large Models at the Same Cost of Smaller Ones","created":"2024-12-26","cited_by_count":4,"area":"inference"},{"id":"2506.03302","title":"Multi-Exit Kolmogorov-Arnold Networks: enhancing accuracy and parsimony","created":"2025-06-03","cited_by_count":4,"area":null},{"id":"2205.09376","title":"Multi-DNN Accelerators for Next-Generation AI Systems","created":"2022-05-19","cited_by_count":3,"area":null},{"id":"2304.08400","title":"ATHEENA: A Toolflow for Hardware Early-Exit Network Automation","created":"2023-04-17","cited_by_count":3,"area":null},{"id":"2304.10306","title":"FIANCEE: Faster Inference of Adversarial Networks via Conditional Early Exits","created":"2023-04-20","cited_by_count":3,"area":"inference"},{"id":"2305.15389","title":"Comparing Humans and Models on a Similar Scale: Towards Cognitive Gender Bias Evaluation in Coreference Resolution","created":"2023-05-24","cited_by_count":3,"area":null},{"id":"2309.11691","title":"RAI4IoE: Responsible AI for Enabling the Internet of Energy","created":"2023-09-20","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":"2503.17497","title":"You Only Look Once at Anytime (AnytimeYOLO): Analysis and Optimization of Early-Exits for Object-Detection","created":"2025-03-21","cited_by_count":3,"area":"inference"},{"id":"2505.12523","title":"Energy-Aware Deep Learning on Resource-Constrained Hardware","created":"2025-05-18","cited_by_count":3,"area":null},{"id":"2506.11431","title":"TruncQuant: Truncation-Ready Quantization for DNNs with Flexible Weight Bit Precision","created":"2025-06-13","cited_by_count":3,"area":null},{"id":"2106.15021","title":"How to Reach Real-Time AI on Consumer Devices? Solutions for Programmable and Custom Architectures","created":"2021-06-21","cited_by_count":2,"area":null},{"id":"2402.03779","title":"EERO: Early Exit with Reject Option for Efficient Classification with limited budget","created":"2024-02-06","cited_by_count":2,"area":null},{"id":"2405.12705","title":"Multimodal Adaptive Inference for Document Image Classification with Anytime Early Exiting","created":"2024-05-21","cited_by_count":2,"area":"inference"},{"id":"2409.11403","title":"UniLCD: Unified Local-Cloud Decision-Making via Reinforcement Learning","created":"2024-09-17","cited_by_count":2,"area":"deeprl"},{"id":"2206.09029","title":"Binary Early-Exit Network for Adaptive Inference on Low-Resource Devices","created":"2022-06-17","cited_by_count":1,"area":"inference"},{"id":"2312.07602","title":"Sense, Predict, Adapt, Repeat: A Blueprint for Design of New Adaptive AI-Centric Sensing Systems","created":"2023-12-11","cited_by_count":1,"area":null},{"id":"2505.08793","title":"Onboard Optimization and Learning: A Survey","created":"2025-05-07","cited_by_count":1,"area":null},{"id":"2507.19031","title":"ProGMLP: A Progressive Framework for GNN-to-MLP Knowledge Distillation with Efficient Trade-offs","created":"2025-07-25","cited_by_count":1,"area":"distill"},{"id":"2512.12448","title":"Optimized Architectures for Kolmogorov-Arnold Networks","created":"2025-12-13","cited_by_count":1,"area":null},{"id":"2109.13192","title":"Consistency Training of Multi-exit Architectures for Sensor Data","created":"2021-09-27","cited_by_count":0,"area":null},{"id":"2206.12420","title":"SCAI: A Spectral data Classification framework with Adaptive Inference for the IoT platform","created":"2022-06-24","cited_by_count":0,"area":null},{"id":"2308.15003","title":"Generative Model for Models: Rapid DNN Customization for Diverse Tasks and Resource Constraints","created":"2023-08-29","cited_by_count":0,"area":null},{"id":"2309.02022","title":"Early Exiting Predictive Coding Neural Networks for Edge AI","created":"2023-09-05","cited_by_count":0,"area":null},{"id":"2402.04359","title":"Adaptive Inference: Theoretical Limits and Unexplored Opportunities","created":"2024-02-06","cited_by_count":0,"area":null},{"id":"2402.06580","title":"SAE: Single Architecture Ensemble Neural Networks","created":"2024-02-09","cited_by_count":0,"area":null},{"id":"2402.07229","title":"Successive Refinement in Large-Scale Computation: Advancing Model Inference Applications","created":"2024-02-11","cited_by_count":0,"area":null},{"id":"2406.14593","title":"Enhancing Dropout-based Bayesian Neural Networks with Multi-Exit on FPGA","created":"2024-06-20","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":"2507.01695","title":"PERTINENCE: Input-based Opportunistic Neural Network Dynamic Execution","created":"2025-07-02","cited_by_count":0,"area":null},{"id":"2508.06551","title":"Slice or the Whole Pie? Utility Control for AI Models","created":"2025-08-06","cited_by_count":0,"area":null},{"id":"2509.08318","title":"CalexNet: Soft Cascade-Aligned Training and Calibration for Lightweight Early-Exit Branches","created":"2025-09-10","cited_by_count":0,"area":"inference"},{"id":"2509.22992","title":"T-TAMER: Provably Taming Trade-offs in ML Serving","created":"2025-09-26","cited_by_count":0,"area":"inference"},{"id":"2512.09313","title":"Hetero-SplitEE: Split Learning of Neural Networks with Early Exits for Heterogeneous IoT Devices","created":"2025-12-10","cited_by_count":0,"area":null},{"id":"2601.10015","title":"Federated Personalization of Early-Exit Networks","created":"2026-01-15","cited_by_count":0,"area":null},{"id":"2603.03146","title":"Channel-Adaptive Edge AI: Maximizing Inference Throughput by Adapting Computational Complexity to Channel States","created":"2026-03-03","cited_by_count":0,"area":null},{"id":"2604.18592","title":"Two-dimensional early exit optimisation of LLM inference","created":"2026-03-27","cited_by_count":0,"area":"inference"},{"id":"2605.07317","title":"Amortized-Precision Quantization for Early-Exit Vision Transformers","created":"2026-05-08","cited_by_count":0,"area":"inference"},{"id":"2608.00322","title":"Belief-Space Perception Routing under Coupled Sensor Faults and Compute Contention","created":"2026-07-31","cited_by_count":0,"area":null},{"id":"2609.10018","title":"Elastoformer: Enabling Dynamic Adaptivity via Elastic Model Transformation","created":"2026-09-09","cited_by_count":0,"area":null},{"id":"2609.12337","title":"Theoretical Guarantees for One-Shot Magnitude Pruning and Compute-Adaptive Early Exit","created":"2026-09-11","cited_by_count":0,"area":"inference"},{"id":"2609.29382","title":"Decoupled Early Exits for Task-Dependent Compute Allocation in Flow-Matching VLAs","created":"2026-09-24","cited_by_count":0,"area":"mllm"}],"next_cursor":null}