3 citations · 6 across the 5 of their papers we have counts for
5 papers
Nemotron 3 Super: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning
NVIDIA, :, Aakshita Chandiramani +544
We describe the pre-training, post-training, and quantization of Nemotron 3 Super, a 120 billion (active 12 billion) parameter hybrid Mamba-Attention Mixture-of-Experts model. Nemo…
Persistent Tri-State Message Passing
Yoonhyuk Choi, Jiho Choi, Chong-Kwon Kim +6
In stochastic message passing, an edge's sampled role changes the node states used to compute adaptive weights at later layers. Weight averaging therefore depends on whether edge r…
InstantFamily: Masked Attention for Zero-shot Multi-ID Image Generation
Chanran Kim, Jeongin Lee, Shichang Joung +2
In the field of personalized image generation, the ability to create images preserving concepts has significantly improved. Creating an image that naturally integrates multiple con…
StyLandGAN: A StyleGAN based Landscape Image Synthesis using Depth-map
Gunhee Lee, Jonghwa Yim, Chanran Kim +1
Despite recent success in conditional image synthesis, prevalent input conditions such as semantics and edges are not clear enough to express `Linear (Ridges)' and `Planar (Scale)'…
Data-Efficient Deep Learning Method for Image Classification Using Data Augmentation, Focal Cosine Loss, and Ensemble
Byeongjo Kim, Chanran Kim, Jaehoon Lee +2
In general, sufficient data is essential for the better performance and generalization of deep-learning models. However, lots of limitations(cost, resources, etc.) of data collecti…