| O1 Replication Journey: A Strategic Progress Report -- Part 1 | Oct 8, 2024 | Mathscientific discovery | CodeCode Available | 7 |
| Synthesizing Interpretable Control Policies through Large Language Model Guided Search | Oct 7, 2024 | Combinatorial OptimizationEvolutionary Algorithms | CodeCode Available | 0 |
| ScienceAgentBench: Toward Rigorous Assessment of Language Agents for Data-Driven Scientific Discovery | Oct 7, 2024 | scientific discovery | CodeCode Available | 2 |
| Reasoning with Natural Language Explanations | Oct 5, 2024 | Natural Language Inferencescientific discovery | —Unverified | 0 |
| Geometric Representation Condition Improves Equivariant Molecule Generation | Oct 4, 2024 | Drug Designscientific discovery | CodeCode Available | 1 |
| SciDFM: A Large Language Model with Mixture-of-Experts for Science | Sep 27, 2024 | Language ModelingLanguage Modelling | —Unverified | 0 |
| Explainable AI needs formal notions of explanation correctness | Sep 22, 2024 | AttributeExplainable artificial intelligence | —Unverified | 0 |
| Smirk: An Atomically Complete Tokenizer for Molecular Foundation Models | Sep 19, 2024 | DiversityMolecular Property Prediction | —Unverified | 0 |
| PersonaFlow: Boosting Research Ideation with LLM-Simulated Expert Personas | Sep 19, 2024 | Language ModelingLanguage Modelling | —Unverified | 0 |
| SANE: Strategic Autonomous Non-Smooth Exploration for Multiple Optima Discovery in Multi-modal and Non-differentiable Black-box Functions | Sep 18, 2024 | Active LearningBayesian Optimization | —Unverified | 0 |
