@insanekrishnaa Interested. Recent M.S. graduate in Artificial Intelligence Systems from the University of Florida with hands-on experience in LLMs, multimodal AI, agentic RAG systems, computer vision, and building production-ready AI and full-stack applications.
@TheSuranaverse Hi Subham,
This is Shree. I graduated this May (2026) with a Master's in Artificial Intelligence Systems from the University of Florida. I have 0–1 years of experience and am available to start after August 10th. I meet all the system requirements.
https://t.co/ImKiFuhdVU
We took a 30B model and split it in two to write tokens in parallel instead of one at a time.
Introducing Nemotron-Labs-TwoTower: a diffusion language model from NVIDIA Research adapted from Nemotron-3-Nano-30B-A3B. Here’s how it works: one half holds the context, the other writes the tokens, with both reusing the pretrained model instead of training a new one from scratch.
We found it kept 98.7% of the original model’s quality at 2.42× faster generation.
“Agentic kernel optimization is the future of on-device inference”
@xenovacom used Fable 5 to write kernels that pushed Gemma 4 to a massive 255 tok/s on WebGPU with M4. He shared the demo, so you can try in your browser!!
Show the world that nothing is impossible when we view the impossibilities with different angle. People with persistence and creativeness can dare to deliver their dreams into reality!!!! #Dream