{"total":14,"rows":[{"id":"2312.14972","title":"Scaling Down to Scale Up: A Cost-Benefit Analysis of Replacing OpenAI's LLM with Open Source SLMs in Production","created":"2023-12-20","cited_by_count":21,"area":null},{"id":"2212.03414","title":"DREAM: A Dynamic Scheduler for Dynamic Real-time Multi-model ML Workloads","created":"2022-12-07","cited_by_count":8,"area":null},{"id":"2308.15368","title":"RED: A Systematic Real-Time Scheduling Approach for Robotic Environmental Dynamics","created":"2023-08-29","cited_by_count":6,"area":null},{"id":"2310.11096","title":"Sparse-DySta: Sparsity-Aware Dynamic and Static Scheduling for Sparse Multi-DNN Workloads","created":"2023-10-17","cited_by_count":6,"area":null},{"id":"2405.00790","title":"SCAR: Scheduling Multi-Model AI Workloads on Heterogeneous Multi-Chiplet Module Accelerators","created":"2024-05-01","cited_by_count":6,"area":null},{"id":"2308.12871","title":"IPA: Inference Pipeline Adaptation to Achieve High Accuracy and Cost-Efficiency","created":"2023-08-24","cited_by_count":2,"area":null},{"id":"2503.23644","title":"Uni-Render: A Unified Accelerator for Real-Time Rendering Across Diverse Neural Renderers","created":"2025-03-31","cited_by_count":2,"area":null},{"id":"2411.10013","title":"Efficient Depth Estimation for Unstable Stereo Camera Systems on AR Glasses","created":"2024-11-15","cited_by_count":1,"area":null},{"id":"2507.14715","title":"Exploring the Dynamic Scheduling Space of Real-Time Generative AI Applications on Emerging Heterogeneous Systems","created":"2025-07-19","cited_by_count":1,"area":null},{"id":"2312.09401","title":"Inter-Layer Scheduling Space Exploration for Multi-model Inference on Heterogeneous Chiplets","created":"2023-12-14","cited_by_count":0,"area":null},{"id":"2504.04535","title":"SnapPix: Efficient-Coding--Inspired In-Sensor Compression for Edge Vision","created":"2025-04-06","cited_by_count":0,"area":null},{"id":"2508.04102","title":"AR as an Evaluation Playground: Bridging Metrics and Visual Perception of Computer Vision Models","created":"2025-08-06","cited_by_count":0,"area":null},{"id":"2508.17764","title":"Puzzle: Scheduling Multiple Deep Learning Models on Mobile Device with Heterogeneous Processors","created":"2025-08-25","cited_by_count":0,"area":null},{"id":"2606.06818","title":"Terastal: Layer-Variant-based Scheduling for Real-Time Multi-DNN Workloads on Heterogeneous Accelerators","created":"2026-06-05","cited_by_count":0,"area":null}],"next_cursor":null}