Search papers, labs, and topics across Lattice.
3
0
5
Untangling multilayer networks just got easier: T-GINEE uses tensors to explicitly model cross-layer dependencies, outperforming methods that treat layers independently.
Aligning LLM reasoning with a dedicated recommendation head via reinforcement learning yields state-of-the-art recommendation performance in real-world systems.
Stop relying on LLMs to "hallucinate" reasoning paths – SEARCH-R uses a fine-tuned Llama3.1-8B model and dependency tree-based retrieval to navigate multi-hop question answering more reliably.
