3 papers
cs.CL2026
Probabilistic Calibration Is a Trainable Capability in Language Models
Davide Baldelli, Sruthi Kuriakose, Maryam Hashemzadeh +2
Language models are increasingly used in settings where outputs must satisfy user-specified randomness constraints, yet their generation probabilities are often poorly calibrated t…
cs.CL2026
LLMs Can't Play Hangman: On the Necessity of a Private Working Memory for Language Agents
Davide Baldelli, Ali Parviz, Amal Zouaq +1
As LLMs move from text completion toward autonomous agents, they remain constrained by the standard chat interface, which lacks private working memory. This raises a fundamental qu…
cs.GR2026
CADmium: Fine-Tuning Code Language Models for Text-Driven Sequential CAD Design
Prashant Govindarajan, Davide Baldelli, Jay Pathak +2
Computer-aided design (CAD) is the digital construction of 2D and 3D objects, and is central to a wide range of engineering and manufacturing applications like automobile and aviat…