Representation Learning

Opening — Why this matters now Large Language Models are increasingly invited into optimization workflows. They write solvers, generate heuristics, and occasionally bluff their way through mathematical reasoning. But a more uncomfortable question has remained largely unanswered: do LLMs actually understand optimization problems—or are they just eloquent impostors? This paper tackles that question head‑on. Instead of judging LLMs by what they say, it examines what they encode. And the results are quietly provocative. ...

Opening — Why this matters now Recommender systems have quietly hit an identity crisis. As item catalogs explode and user attention fragments, sequential recommendation models are being asked to do two incompatible things at once: memorize popular items with surgical precision and generalize intelligently to the long tail. Hash IDs do the former well. Semantic embeddings do the latter—sometimes too well. The paper “The Best of the Two Worlds: Harmonizing Semantic and Hash IDs for Sequential Recommendation” formalizes why these worlds keep colliding, and proposes a framework—H2Rec—that finally stops forcing us to choose sides. fileciteturn0file0 ...

Why this matters now Modern AI models are astonishingly good at pattern recognition—and dangerously bad at knowing which patterns matter. A neural network that labels birds can achieve 95% accuracy on paper yet collapse when the background changes from lake to desert. This fragility stems from spurious correlations—the model’s habit of linking labels to irrelevant cues like color, lighting, or background texture. The deeper the network, the deeper the bias embeds. ...