Search papers, labs, and topics across Lattice.
5
0
7
13
CFALR outperforms traditional methods by seamlessly integrating collaborative filtering with large language models for personalized fashion recommendations.
Achieving 400x faster inference without sacrificing semantic accuracy, AIR transforms cross-domain recommendations into a practical reality for e-commerce.
LLM-based recommendation systems can now dynamically adjust the granularity of knowledge graph retrieval, boosting performance by adapting to the complexity of user queries.
By respecting the intrinsic geometric constraints of molecules, GO-Flow generates more realistic 3D conformations with fewer computational steps, outperforming existing diffusion and flow matching models.
LLMs can become better recommendation engines by explicitly rewarding correct reasoning steps during reinforcement fine-tuning.
