S^2-Bench is a new one-to-many benchmark for natural language-driven molecule generation with three tasks, and OpenMolIns is an instruction dataset enabling Llama3.1-8B to outperform GPT-4o and Claude-3.5 on it.
Molgensurvey: A systematic survey in machine learning models for molecule design
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
verdicts
UNVERDICTED 3representative citing papers
Chemically meaningful steering for properties like cLogP and TPSA emerges in entangled Transformer-VAE latent spaces only after controlling for SELFIES representation confounds through residualization and decoded traversals.
Survey of automated scientific discovery covering equation discovery, symbolic regression, closed-loop systems like Adam, deep neural network roles, and autonomy levels up to level 5 with no human intervention.
citing papers explorer
-
Speak-to-Structure: Evaluating LLMs in Open-domain Natural Language-Driven Molecule Generation
S^2-Bench is a new one-to-many benchmark for natural language-driven molecule generation with three tasks, and OpenMolIns is an instruction dataset enabling Llama3.1-8B to outperform GPT-4o and Claude-3.5 on it.
-
Molecules Meet Language: Confound-Aware Representation Learning and Chemical Property Steering in Transformer-VAE Latent Spaces
Chemically meaningful steering for properties like cLogP and TPSA emerges in entangled Transformer-VAE latent spaces only after controlling for SELFIES representation confounds through residualization and decoded traversals.
-
Automated Scientific Discovery: From Equation Discovery to Autonomous Discovery Systems
Survey of automated scientific discovery covering equation discovery, symbolic regression, closed-loop systems like Adam, deep neural network roles, and autonomy levels up to level 5 with no human intervention.