| High-quality Panorama Stitching based on Asymmetric Bidirectional Optical Flow | Jun 1, 2020 | GPUOptical Flow Estimation | CodeCode Available | 1 | 5 |
| Mesh-Learner: Texturing Mesh with Spherical Harmonics | Apr 28, 2025 | 3D ReconstructionCPU | CodeCode Available | 1 | 5 |
| Rethinking Compression: Reduced Order Modelling of Latent Features in Large Language Models | Dec 12, 2023 | GPUModel Compression | CodeCode Available | 1 | 5 |
| ConsistNet: Enforcing 3D Consistency for Multi-view Images Diffusion | Oct 16, 2023 | Depth EstimationDepth Prediction | CodeCode Available | 1 | 5 |
| Mesorasi: Architecture Support for Point Cloud Analytics via Delayed-Aggregation | Aug 16, 2020 | Autonomous DrivingGPU | CodeCode Available | 1 | 5 |
| Meta-DAN: towards an efficient prediction strategy for page-level handwritten text recognition | Apr 4, 2025 | GPUHandwritten Text Recognition | CodeCode Available | 1 | 5 |
| Rethinking Training from Scratch for Object Detection | Jun 6, 2021 | GPUObject | CodeCode Available | 1 | 5 |
| Neural Architecture Search using Deep Neural Networks and Monte Carlo Tree Search | May 18, 2018 | GPUImage Captioning | CodeCode Available | 1 | 5 |
| Holistically-Attracted Wireframe Parsing | Mar 3, 2020 | GPULine Segment Detection | CodeCode Available | 1 | 5 |
| Reversible Vision Transformers | Feb 9, 2023 | GPUimage-classification | CodeCode Available | 1 | 5 |
| Edge-MoE: Memory-Efficient Multi-Task Vision Transformer Architecture with Task-level Sparsity via Mixture-of-Experts | May 30, 2023 | CPUGPU | CodeCode Available | 1 | 5 |
| EdgeNAT: Transformer for Efficient Edge Detection | Aug 20, 2024 | Edge DetectionGPU | CodeCode Available | 1 | 5 |
| Memory Efficient Meta-Learning with Large Images | Jul 2, 2021 | Few-Shot Image ClassificationGPU | CodeCode Available | 1 | 5 |
| Distributed Out-of-Memory NMF on CPU/GPU Architectures | Feb 19, 2022 | CPUDimensionality Reduction | CodeCode Available | 1 | 5 |
| Horizontally Fused Training Array: An Effective Hardware Utilization Squeezer for Training Novel Deep Learning Models | Feb 3, 2021 | GPU | CodeCode Available | 1 | 5 |
| BERTVision -- A Parameter-Efficient Approach for Question Answering | Feb 24, 2022 | GPUQuestion Answering | CodeCode Available | 1 | 5 |
| HPFF: Hierarchical Locally Supervised Learning with Patch Feature Fusion | Jul 8, 2024 | GPU | CodeCode Available | 1 | 5 |
| BESA: Pruning Large Language Models with Blockwise Parameter-Efficient Sparsity Allocation | Feb 18, 2024 | GPUQuestion Answering | CodeCode Available | 1 | 5 |
| EEEA-Net: An Early Exit Evolutionary Neural Architecture Search | Aug 13, 2021 | GPUImage Classification | CodeCode Available | 1 | 5 |
| Memory-Efficient Reversible Spiking Neural Networks | Dec 13, 2023 | GPU | CodeCode Available | 1 | 5 |
| Merak: An Efficient Distributed DNN Training Framework with Automated 3D Parallelism for Giant Foundation Models | Jun 10, 2022 | GPU | CodeCode Available | 1 | 5 |
| Conformer-Kernel with Query Term Independence for Document Retrieval | Jul 20, 2020 | GPUReranking | CodeCode Available | 1 | 5 |
| HRMedSeg: Unlocking High-resolution Medical Image segmentation via Memory-efficient Attention Modeling | Apr 8, 2025 | DecoderGPU | CodeCode Available | 1 | 5 |
| EfficientBioAI: Making Bioimaging AI Models Efficient in Energy, Latency and Representation | Jun 9, 2023 | CPUGPU | CodeCode Available | 1 | 5 |
| Edge and Identity Preserving Network for Face Super-Resolution | Aug 27, 2020 | GPUSuper-Resolution | CodeCode Available | 1 | 5 |
