activity
20242026
collaborators

8 papers

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…

cs.LG2025

NovoMolGen: Rethinking Molecular Language Model Pretraining

Kamran Chitsaz, Roshan Balaji, Quentin Fournier +2

Designing de-novo molecules with desired property profiles requires efficient exploration of the vast chemical space ranging from to possible synthesizable cand…

cs.CL2025

Small Encoders Can Rival Large Decoders in Detecting Groundedness

Istabrak Abbes, Gabriele Prato, Quentin Fournier +4

Augmenting large language models (LLMs) with external context significantly improves their performance in natural language processing (NLP) tasks. However, LLMs struggle to answer…

cs.LG2025

Manifold Metric: A Loss Landscape Approach for Predicting Model Performance

Pranshu Malviya, Jerry Huang, Aristide Baratin +2

Determining the optimal model for a given task often requires training multiple models from scratch, which becomes impractical as dataset and model sizes grow. A more efficient alt…

cs.CL2025

NeoBERT: A Next-Generation BERT

Lola Le Breton, Quentin Fournier, Mariam El Mezouar +2

Recent innovations in architecture, pre-training, and fine-tuning have led to the remarkable in-context learning and reasoning abilities of large auto-regressive language models su…

cs.AI2025

Combining Domain and Alignment Vectors to Achieve Better Knowledge-Safety Trade-offs in LLMs

Megh Thakkar, Quentin Fournier, Matthew Riemer +4

There is a growing interest in training domain-expert LLMs that excel in specific technical fields compared to their general-purpose instruction-tuned counterparts. However, these…