Search papers, labs, and topics across Lattice.
Affiliation:
7
0
6
Benchmark rankings for multilingual embedding models are severely compromised by dataset scarcity, with many relying on a single source, which could mislead evaluations.
Unsupervised multi-kernel clustering outperforms traditional supervised models in algorithm selection, revealing which landscape representations truly matter for optimization tasks.
AS models struggle to generalize across domains, revealing significant gaps in their reliability for real-world applications.
Stop wasting compute: Classifiers can predict the reliability of stochastic optimization run-number estimates, flagging potentially flawed benchmarks with high recall.
Forget relying on just ingredients: this method shows how fusing semantic, lexical, and nutritional aspects significantly improves recipe similarity estimation, aligning more closely with expert judgment.
Forget expensive fine-tuning: FoodOntoRAG links food entities with near SOTA accuracy while adapting to evolving ontologies using a clever RAG architecture with retrieval, selection, scoring, and synonym generation agents.
LLMs can drastically reduce manual effort for domain experts in accessing complex food and nutrition data via RAG, but still struggle with queries that exceed the representational scope of the metadata.
