works on

From the 2 of 42 linked papers with an AI index.

activity
20242026
most citedHumanity's Last Exam

18 citations · 25 across the 14 of their papers we have counts for

collaborators
Showing cs.LGShow all

15 papers · 1 filter

cs.LG2026

Bi-semantic Chemical Embedder for Joint Representation Learning of SMILES and Natural Language

David Ming Segura, Jeremy Goumaz, Joshua W. Sin +3

Transformer models have revolutionized natural language processing (NLP), and text-based molecular representations like SMILES have successfully extended these architectures to che…

cs.LG2026

Sample Efficient Generative Optimization for Molecular Design

Sarina Kopf, Cristina Nevado, Philippe Schwaller

The paper proposes SEGO, a Bayesian optimization framework that steers a generative model to propose molecules, achieving strong molecular design performance with far fewer expensi…

cs.LG20261 cited

Teaching Language Models Mechanistic Explainability Through MechSMILES

Théo A. Neukomm, Zlatko Jončev, Philippe Schwaller

Chemical reaction mechanisms are the foundation of how chemists evaluate reactivity and feasibility, yet current Computer-Assisted Synthesis Planning (CASP) systems operate without…

cs.LG202618 cited

Humanity's Last Exam

Long Phan, Alice Gatti, Ziwen Han +1144

Benchmarks are important tools for tracking the rapid advancements in large language model (LLM) capabilities. However, benchmarks are not keeping pace in difficulty: LLMs now achi…

cs.LG2026

MiST: Understanding the Role of Mid-Stage Scientific Training in Developing Chemical Reasoning Models

Andres M Bran, Tong Xie, Shai Pranesh +9

Large Language Models can develop reasoning capabilities through online fine-tuning with rule-based rewards. However, recent studies reveal a critical constraint: reinforcement lea…

cs.LG2025

Large language models as uncertainty-calibrated optimizers for experimental discovery

Bojana Ranković, Ryan-Rhys Griffiths, Philippe Schwaller

Scientific discovery increasingly depends on efficient experimental optimization to navigate vast design spaces under time and resource constraints. Traditional approaches often re…