Search papers, labs, and topics across Lattice.
Affiliation:
3
1
6
20
Visual insensitivity in multimodal LLMs can be effectively mitigated with a new framework that enhances alignment and reduces hallucinations.
RootMem transforms how personalized LLMs access critical logical memories, outperforming traditional methods by integrating structured decision logic into memory retrieval.
LLM-based recommendation gets a boost: initializing item embeddings with semantic keywords and aligning tokens to item clusters significantly improves performance.
