Search papers, labs, and topics across Lattice.
5
0
8
6
FLEXRec shows that compact LLMs can achieve state-of-the-art recommendation accuracy without the computational burden of larger models.
LLM-aligned variable-length identifiers can revolutionize generative recommendation by providing a more nuanced and efficient representation of item semantics.
You can boost LLM-based recommendations across completely disjoint domains without sacrificing user privacy by using semantic bridges and federated learning.
LLM agents can conquer complex Text-to-SQL by creating intermediate "agentic views" that break down queries and filter schemas, achieving state-of-the-art results on challenging benchmarks.
Unleashing the full reasoning potential of VLMs, AgentM3D adaptively scales test-time reasoning paths to achieve state-of-the-art zero-shot multi-modal misinformation detection.
