{"total":29,"rows":[{"id":"2106.04426","title":"Hash Layers For Large Sparse Models","created":"2021-06-08","cited_by_count":237,"area":null},{"id":"2105.01879","title":"MOS: Towards Scaling Out-of-distribution Detection for Large Semantic Space","created":"2021-05-05","cited_by_count":233,"area":null},{"id":"2203.14216","title":"Efficient and Degradation-Adaptive Network for Real-World Image Super-Resolution","created":"2022-03-27","cited_by_count":96,"area":null},{"id":"2405.11157","title":"Towards Modular LLMs by Building and Reusing a Library of LoRAs","created":"2024-05-18","cited_by_count":72,"area":null},{"id":"2303.14177","title":"Scaling Expert Language Models with Unsupervised Domain Discovery","created":"2023-03-24","cited_by_count":60,"area":null},{"id":"2207.10430","title":"The Neural Race Reduction: Dynamics of Abstraction in Gated Networks","created":"2022-07-21","cited_by_count":37,"area":null},{"id":"2306.00008","title":"Brainformers: Trading Simplicity for Efficiency","created":"2023-05-29","cited_by_count":31,"area":null},{"id":"2311.15436","title":"Learning to Skip for Language Modeling","created":"2023-11-26","cited_by_count":19,"area":null},{"id":"2211.11747","title":"NEVIS'22: A Stream of 100 Tasks Sampled from 30 Years of Computer Vision Research","created":"2022-11-15","cited_by_count":18,"area":null},{"id":"2401.10731","title":"Removal then Selection: A Coarse-to-Fine Fusion Perspective for RGB-Infrared Object Detection","created":"2024-01-19","cited_by_count":16,"area":null},{"id":"2401.02151","title":"Frequency-Adaptive Pan-Sharpening with Mixture of Experts","created":"2024-01-04","cited_by_count":13,"area":null},{"id":"2109.09690","title":"Trust Your Robots! Predictive Uncertainty Estimation of Neural Networks with Sparse Gaussian Processes","created":"2021-09-20","cited_by_count":12,"area":null},{"id":"2310.11031","title":"Domain Generalization Using Large Pretrained Models with Mixture-of-Adapters","created":"2023-10-17","cited_by_count":11,"area":null},{"id":"2410.07901","title":"Semi-Supervised Video Desnowing Network via Temporal Decoupling Experts and Distribution-Driven Contrastive Regularization","created":"2024-10-10","cited_by_count":11,"area":null},{"id":"2403.10616","title":"DiPaCo: Distributed Path Composition","created":"2024-03-15","cited_by_count":10,"area":null},{"id":"2508.05038","title":"HAMoBE: Hierarchical and Adaptive Mixture of Biometric Experts for Video-based Person ReID","created":"2025-08-07","cited_by_count":10,"area":null},{"id":"2410.03529","title":"No Need to Talk: Asynchronous Mixture of Language Models","created":"2024-10-04","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":"2105.11373","title":"Large-Scale Attribute-Object Compositions","created":"2021-05-24","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":"2106.12475","title":"Mixtures of Deep Neural Experts for Automated Speech Scoring","created":"2021-06-23","cited_by_count":3,"area":null},{"id":"2204.08899","title":"Towards Efficient Single Image Dehazing and Desnowing","created":"2022-04-19","cited_by_count":3,"area":null},{"id":"2212.10066","title":"RepMode: Learning to Re-parameterize Diverse Experts for Subcellular Structure Prediction","created":"2022-12-20","cited_by_count":3,"area":null},{"id":"2502.01804","title":"Soup-of-Experts: Pretraining Specialist Models via Parameters Averaging","created":"2025-02-03","cited_by_count":3,"area":null},{"id":"2301.05865","title":"Gated Self-supervised Learning For Improving Supervised Learning","created":"2023-01-14","cited_by_count":1,"area":null},{"id":"2606.18105","title":"OmniPlan: An Adaptive Framework for Timely and Near-Optimal Network Planning Optimization","created":"2026-06-16","cited_by_count":1,"area":null},{"id":"2303.04115","title":"Predicted Embedding Power Regression for Large-Scale Out-of-Distribution Detection","created":"2023-03-07","cited_by_count":0,"area":null},{"id":"2504.18241","title":"Switch-Based Multi-Part Neural Network","created":"2025-04-25","cited_by_count":0,"area":null},{"id":"2510.27182","title":"SERFLOW: A Cross-Service Cost Optimization Framework for SLO-Aware Dynamic ML Inference","created":"2025-10-31","cited_by_count":0,"area":null}],"next_cursor":null}