Viewing profile — skelts

Building effective recommendation and search systems means going beyond simply predicting relevance. Modern users expect personalized experiences that cater to a wide range of need…

Recommender system benchmarks are less reliable than they seem—this study shows that changing data splitting strategies can significantly alter model rankings. Evaluating 17 state-…

Traditional recommendation systems struggle with long-term user modeling and scalability. EmbSum leverages LLM-driven summarization to precompute rich user and content embeddings, …

Google Research’s "Titans" introduces a neural long-term memory module that dynamically learns to memorize and retrieve context during inference, addressing Transformers' limitatio…

What if your next job application was evaluated not just by qualifications but by an AI that explains its decision better than most hiring managers? The future of AI-driven job rec…

Netflix and Cornell University researchers have exposed significant flaws in cosine similarity. Their study reveals that regularization in linear matrix factorization models introd…

Recommender systems often overfocus on dominant interests, neglecting diversity. Shaped introduces a method to calibrate recommendations using minimum-cost flow optimization, ensur…

[flagged]

i've tried a couple and probably prefer Marqo to the rest. definitely the most user-friendly pick of the bunch.

+1 to Marqo. It's documents in documents out rather than vectors in vectors out. Much easier end to end.