Informing Acquisition Functions via Foundation Models for Molecular Discovery
cs.LG, cs.AI, q-bio.QM
Submitted: 2025-12-15
Updated: 2026-11-07
Terminology
Sources
- A Tutorial on Bayesian Optimization
- BoGrape: Bayesian optimization over graphs with shortest-path encoded
- A Sober Look at LLMs for Material Discovery: Are They Actually Good for Bayesian Optimization Over Molecules?
- LoRA: Low-Rank Adaptation of Large Language Models
- Bayesian Optimization of Catalysis With In-Context Learning
- Unifying Molecular and Textual Representations via Multi-task Language Modelling
- What can Large Language Models do in chemistry? A comprehensive benchmark on eight tasks
- Language models can generate molecules, materials, and protein binding sites directly in three dimensions as XYZ, CIF, and PDB files
- Efficient Evolutionary Search Over Chemical Space with Large Language Models
- The Impact of Large Language Models on Scientific Discovery: a Preliminary Study using GPT-4
- Prefix-Tuning: Optimizing Continuous Prompts for Generation
- Gaussian Process Optimization in the Bandit Setting: No Regret and Experimental Design
- BORE: Bayesian Optimization by Density-Ratio Estimation
- A General Recipe for Likelihood-free Bayesian Optimization
- Language models in molecular discovery
- On First-Order Meta-Learning Algorithms
- Large-Scale Chemical Language Representations Capture Molecular Structure and Properties
- Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
- Llama 2: Open Foundation and Fine-Tuned Chat Models
- Query-Dependent Prompt Evaluation and Optimization with Offline Inverse RL
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis