Search papers, labs, and topics across Lattice.
Nanjing University
2
1
5
InfoMerge achieves an 85% reduction in visual tokens while retaining nearly all original performance, revolutionizing efficiency in Video-LLMs.
Compressing multi-dimensional human preferences into single binary labels severely degrades DPO training, but a semi-supervised approach can recover state-of-the-art performance without additional human annotation.
