FlowWM stochastic world modeling via flow matching in DINOv3 feature space, with the FuturePerception (Waymo) benchmark. - ...
The rapid expansion of artificial intelligence has sparked an explosion of generative media models, highlighted by advanced ...
Abstract: This study explores the fine-tuning of six versions of the Whisper model for speech translation from Moroccan Darija to Modern Standard Arabic (MSA). We focus on fine-tuning Whisper across ...
[2024-06-20]: Disable loading irrelvent packages when training individual models; update the instruction for DCR experiements; fix minor bugs in TabSyn's training script. [2024-05-14]: Add demo code ...
Nvidia’s NeMoTron 3.5 ASR represents a significant development in automatic speech recognition, offering robust multilingual capabilities and features designed for practical use cases. With 600 ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results