"We utilize the last hidden state of the LLM as a representation of the reasoning state (termed "continuous thought")."
Could someone explain the last hidden state of the LLM ? What it shape is and how it is normally used - and why it hasn't been used yet to augment the next input? (which seems logical)
Could someone explain the last hidden state of the LLM ? What it shape is and how it is normally used - and why it hasn't been used yet to augment the next input? (which seems logical)