Nvidia's Nemotron-Cascade 2 wins math and coding gold medals with 3B active parameters — and its post-training recipe is now open-source

Nvidia's Nemotron-Cascade 2 is a 30B MoE model that activates only 3B parameters at inference time, yet achieved gold ...
IEEE

Dual Energy-Based Model with Open-World Uncertainty Estimation for Out-of-distribution Detection

Abstract: Out-of-distribution (OOD) detection is crucial for machine learning models deployed in open-world environments. However, existing methods often struggle with model over-confidence or rely ...
IEEE

Research on Cross-Language Speech Synthesis Based on Diffusion Transformer

Abstract: Cross-language speech synthesis still faces many challenges. The core difficulty lies in the significant language differences between the source language and the target language. To address ...