{"total":21,"rows":[{"id":"2303.17951","title":"FP8 versus INT8 for efficient deep learning inference","created":"2023-03-31","cited_by_count":31,"area":null},{"id":"2205.14550","title":"Machine Learning for Microcontroller-Class Hardware: A Review","created":"2022-05-29","cited_by_count":28,"area":null},{"id":"2302.05397","title":"A Practical Mixed Precision Algorithm for Post-Training Quantization","created":"2023-02-10","cited_by_count":24,"area":null},{"id":"2308.10814","title":"Jumping through Local Minima: Quantization in the Loss Landscape of Vision Transformers","created":"2023-08-21","cited_by_count":18,"area":null},{"id":"2310.01258","title":"MobileNVC: Real-time 1080p Neural Video Compression on a Mobile Device","created":"2023-10-02","cited_by_count":13,"area":null},{"id":"2211.16912","title":"Quadapter: Adapter for GPT-2 Quantization","created":"2022-11-30","cited_by_count":10,"area":null},{"id":"2306.05691","title":"DIFT: Dynamic Iterative Field Transforms for Memory Efficient Optical Flow","created":"2023-06-09","cited_by_count":7,"area":null},{"id":"2308.07350","title":"Efficient Neural PDE-Solvers using Quantization Aware Training","created":"2023-08-14","cited_by_count":6,"area":null},{"id":"2404.09918","title":"EdgeRelight360: Text-Conditioned 360-Degree HDR Image Generation for Real-Time On-Device Video Portrait Relighting","created":"2024-04-15","cited_by_count":5,"area":null},{"id":"2210.09188","title":"Sub-8-bit quantization for on-device speech recognition: a regularization-free approach","created":"2022-10-17","cited_by_count":4,"area":null},{"id":"2303.04336","title":"QuickSRNet: Plain Single-Image Super-Resolution Architecture for Faster Inference on Mobile Platforms","created":"2023-03-08","cited_by_count":4,"area":null},{"id":"2306.06152","title":"EfficientBioAI: Making Bioimaging AI Models Efficient in Energy, Latency and Representation","created":"2023-06-09","cited_by_count":2,"area":null},{"id":"2404.08135","title":"SciFlow: Empowering Lightweight Optical Flow Models with Self-Cleaning Iterations","created":"2024-04-11","cited_by_count":2,"area":null},{"id":"2404.16898","title":"How to Parameterize Asymmetric Quantization Ranges for Quantization-Aware Training","created":"2024-04-25","cited_by_count":2,"area":null},{"id":"2511.18474","title":"Adaptive Mesh-Quantization for Neural PDE Solvers","created":"2025-11-23","cited_by_count":2,"area":null},{"id":"2405.01775","title":"Torch2Chip: An End-to-end Customizable Deep Neural Network Compression and Deployment Toolkit for Prototype Hardware Accelerator Design","created":"2024-05-02","cited_by_count":1,"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":"2606.06034","title":"When Good Enough Is Optimal: Multiplication-Only Matrix Inversion Approximation for Quantized Gated DeltaNet","created":"2026-06-04","cited_by_count":1,"area":null},{"id":"2305.06640","title":"Speaker Diaphragm Excursion Prediction: deep attention and online adaptation","created":"2023-05-11","cited_by_count":0,"area":null},{"id":"2507.12196","title":"A Selective Quantization Tuner for ONNX Models","created":"2025-07-16","cited_by_count":0,"area":null},{"id":"2510.24787","title":"ESCA: Enabling Seamless Codec Avatar Execution through Algorithm and Hardware Co-Optimization for Virtual Reality","created":"2025-10-27","cited_by_count":0,"area":null}],"next_cursor":null}