4 papers
Do You Even Need More Data? Rethinking LLM Deployment for Label-Scarce Tabular Classification with TabLens
Daria Grushina, Kseniia Kuvshinova, Alina Kostromina +3
Every tabular classification task requires sufficient labeled data. When labels are scarce, practitioners can collect more examples, encode domain expertise into features, or accep…
Shape: A Self-Supervised 3D Geometry Foundation Model for Industrial CAD Analysis
Bayangmbe Mounmo, Sam Chien, Mile Mitrovic
Industrial CAD workflows require robust, generalizable 3D geometric representations supporting accuracy and explainability. We introduce Shape, a self-supervised foundation model c…
LightAutoDS-Tab: Multi-AutoML Agentic System for Tabular Data
Aleksey Lapin, Igor Hromov, Stanislav Chumakov +4
AutoML has advanced in handling complex tasks using the integration of LLMs, yet its efficiency remains limited by dependence on specific underlying tools. In this paper, we introd…
ALIEN: Aligned Entropy Head for Improving Uncertainty Estimation of LLMs
Artem Zabolotnyi, Roman Makarov, Mile Mitrovic +4
Uncertainty estimation remains a key challenge when adapting pre-trained language models to downstream classification tasks, with overconfidence often observed for difficult inputs…