Search papers, labs, and topics across Lattice.
3
0
4
PriFT achieves state-of-the-art performance in supervised fine-tuning by leveraging a stable token reweighting signal from a frozen pretrained model, drastically improving generalization.
LoRaQ achieves superior generative performance with fully quantized architectures, challenging the necessity of high-precision branches in low-rank approximation.
Achieve state-of-the-art image and NeRF reconstruction with a parameter-efficient implicit neural representation inspired by classical subtractive synthesis.
