Search papers, labs, and topics across Lattice.
2
0
5
5
LLMs exhibit a quantifiable "Parametric Memory Law" during LoRA finetuning, where loss reduction scales predictably with effective parameters and sequence length, revealing fundamental limits on how much they can memorize.
Multimodal models can "see" the image but still fail at reasoning because the visual input distracts the routing mechanism from activating the right experts.
