Nvidia's new open weights Nemotron 3 super combines three different architectures to beat gpt-oss and Qwen in throughput

But today, Nvidia sought to help solve this problem with the release of Nemotron 3 Super, a 120-billion-parameter hybrid model, with weights posted on Hugging Face. By merging disparate architectural ...
GitHub

Cognautic CLI

Cognautic CLI supports one-shot speech-to-text to quickly prefill your prompt. Cognautic CLI now includes built-in vim editor integration, allowing you to edit files directly from the chat interface ...
GitHub

Z80-μLM: A Retrocomputing Micro Language Model

Z80-μLM is a 'conversational AI' that generates short character-by-character sequences, with quantization-aware training (QAT) to run on a Z80 processor with 64kb of ram. The root behind this project ...
IEEE

A Behavioral Decision-Making Model of Learning and Memory for Mobile Robot Triggered by Curiosity

Abstract: Learning and memorizing behavioral decision in the process of environmental cognition to guide future decision is an important aspect of research and application in mobile robotics.
IEEE

Memory Robot Design: A New Perspective From Human Brain Model and Large Language Model

Abstract: With the spread of generative AI, the study proposed a memory-based cognitive robot architecture by using a Large Language Model (LLM), inspired by the working memory of the human brain ...