Meta is working on adding latent space planning\/search to large language model AI.<\/p>\n
1\ufe0f\u20e3H-GAP (https:\/\/arxiv.org\/abs\/2312.02682)<\/a> Rumored OpenAI Q* Is Optimization in Abstract Representation Space<\/B><\/p>\n The innovation in Q* lies in its optimization process, conducted not within the space of possible text strings but in an abstract representation space. Here, thoughts or ideas are represented in a form that allows for the computational minimization of the EBM’s scalar output, akin to finding the path of least resistance in a landscape. This process involves gradient descent, a method for finding the minimum of a function, applied to iteratively refine these abstract representations towards those that yield the lowest energy in relation to the prompt.<\/p>\n
\n2\ufe0f\u20e3Diffusion World Model (https:\/\/arxiv.org\/abs\/2402.03570)<\/a>
\n3\ufe0f\u20e3TAP (https:\/\/arxiv.org\/abs\/2208.10291<\/a>)
\n4\ufe0f\u20e3LaMCTS (https:\/\/arxiv.org\/abs\/2007.00708<\/a>)
\n5\ufe0f\u20e3LaP3 (https:\/\/arxiv.org\/abs\/2106.10544<\/a>)
\n6\ufe0f\u20e3LaSynth (https:\/\/arxiv.org\/abs\/2107.00101<\/a>)
\n7\ufe0f\u20e3LaMOO (https:\/\/arxiv.org\/abs\/2110.03173<\/A>)<\/p>