UQLM provides a suite of response-level scorers for quantifying the uncertainty of Large Language Model (LLM) outputs. Each scorer returns a confidence score between 0 and 1, where higher scores ...
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 ...
Abstract: Programming language source code vulnerability mining is crucial to improving the security of software systems, but current research is mostly focused on the C language field, with little ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results