| H2Learn: High-Efficiency Learning Accelerator for High-Accuracy Spiking Neural Networks | Jul 25, 2021 | GPUVocal Bursts Intensity Prediction | —Unverified | 0 |
| Self-Correcting Neural Networks For Safe Classification | Jul 23, 2021 | ClassificationGPU | CodeCode Available | 0 |
| DeepScale: Online Frame Size Adaptation for Multi-object Tracking on Smart Cameras and Edge Servers | Jul 22, 2021 | GPUMulti-Object Tracking | —Unverified | 0 |
| Small-Text: Active Learning for Text Classification in Python | Jul 21, 2021 | Active LearningClassification | —Unverified | 0 |
| Mastering Visual Continuous Control: Improved Data-Augmented Reinforcement Learning | Jul 20, 2021 | continuous-controlContinuous Control | CodeCode Available | 1 |
| Generative Video Transformer: Can Objects be the Words? | Jul 20, 2021 | GPUScene Understanding | —Unverified | 0 |
| Discriminator-Free Generative Adversarial Attack | Jul 20, 2021 | Adversarial AttackDisentanglement | CodeCode Available | 1 |
| A baseline model for computationally inexpensive speech recognition for Kazakh using the Coqui STT framework | Jul 19, 2021 | Automatic Speech RecognitionAutomatic Speech Recognition (ASR) | —Unverified | 0 |
| Face.evoLVe: A High-Performance Face Recognition Library | Jul 19, 2021 | Face AlignmentFace Recognition | CodeCode Available | 2 |
| Megaverse: Simulating Embodied Agents at One Million Experiences per Second | Jul 17, 2021 | GPUReinforcement Learning (RL) | CodeCode Available | 1 |
