Search papers, labs, and topics across Lattice.
Seoul National University
3
0
6
3
Even advanced LLMs struggle to replicate human researchers' ability to find inspiring prior work, highlighting a significant gap in AI's scientific intuition.
Existing multimodal retrievers are blind to diverse perspectives, but SPIN can significantly enhance their performance on multifaceted queries.
Diversity-based visual token pruning in LVLMs might be increasing hallucination, as it often fails to preserve feature diversity and struggles with simple images compared to attention-based methods.
