arXiv:2608. 14734v1 Announce Type: cross Abstract: Deep learning models of nanocrystal synthesis enable the prediction of size and shape by encoding precursors and reaction conditions.
arXiv:2601. 02424v2 Announce Type: replace-cross Abstract: The synthesis of nanocrystals has been highly dependent on trial-and-error, due to the complex correlation between synthesis parameters and physicochemical properties.
arXiv:2606. 30170v1 Announce Type: cross Abstract: Generative molecular design is shaped by simple proxy benchmarks for drug-like properties and models pretrained on large pharmaceutical datasets.
arXiv:2607. 17033v1 Announce Type: new Abstract: Forecasting the outcomes of transition-metal-catalyzed reactions is notoriously complex due to the interplay of diverse physical and chemical variables.
The paper introduces Competitive Dimerization Networks (CDNs) as a chemical learning framework where molecular species bind reversibly to form dimers, with binding affinities acting as tunable synaptic weights. Through a directed evolution protocol involving mutation, selection, and amplification of DNA-based components, CDNs can be trained in vitro to perform complex tasks such as multiclass classification, achieving strong output contrast and high mutual information. Comparative studies with in silico gradient descent show closely correlated performance, positioning CDNs as a promising platform for analog physical computation that bridges synthetic biology and machine learning.
PGFS++ is a synthesis‑aware reinforcement learning framework that improves molecular properties such as drug‑likeness or binding affinity while ensuring the resulting molecules can be synthesized and remain structurally similar to the input. It builds on PGFS+ by using trainable embedding lookup tables for reaction templates and second reactants, a more effective scoring function, and a refined RL algorithm. The method addresses a reward‑hacking failure mode by treating each input molecule as the start of a forward‑synthesis trajectory, applying learned reaction templates with in‑stock building blocks, and producing diverse, high‑quality outputs with explicit synthesis routes.
arXiv:2608. 14076v1 Announce Type: cross Abstract: Transition-state (TS) structures define the energetic barriers and mechanistic pathways of elementary chemical reactions, yet their identification remains computationally demanding because conventional saddle-point searches require expensive quantum-mechanical calculations.
arXiv:2607. 17910v1 Announce Type: cross Abstract: Generative artificial intelligence is rapidly transforming materials design by enabling de novo exploration of immense chemical spaces.
arXiv:2606. 02507v1 Announce Type: cross Abstract: Inverse materials design is shifting materials discovery from forward prediction to targeted proposal of candidates that satisfy objectives under physical constraints.
PGFS++ is a synthesis‑aware reinforcement learning framework that improves molecular properties while ensuring the resulting molecules can be synthesized and remain structurally similar to the input. It builds on PGFS+ by using trainable embedding lookup tables for reaction templates and second reactants, a more effective scoring function, and a refined RL algorithm. Experiments demonstrate that PGFS++ enhances target properties and preserves high output diversity, overcoming the reward‑hacking failure mode seen in earlier versions.
The article discusses how the rapid development of artificial intelligence (AI) and machine learning (ML) is transforming chemical engineering by influencing problem formulation, analysis, and solution across a wide range of applications, from atomic-scale simulations to industrial operations. It highlights recent methodological advances and representative uses, noting a shift from purely black-box models to hybrid and physics-informed frameworks that incorporate conservation laws, thermodynamic consistency, and structural constraints. These integrated approaches enhance robustness, reliability, and human-AI collaboration, ultimately amplifying rather than replacing core chemical engineering principles.
The paper introduces Align-React, a chemical reaction representation learning framework that incorporates atomic correspondence between reactants and products, an adapter for embedding reaction conditions, and a Reaction-Center-Aware attention mechanism. These components enable the model to capture precise molecular transformations and focus on critical functional groups, leading to improved performance across a variety of organic reaction tasks. The framework outperforms existing architectures on most benchmark datasets.
arXiv:2606. 24999v1 Announce Type: new Abstract: High-dimensional partial differential equations (PDEs) with unknown coefficients arise widely in scientific machine learning, including continuous-time reinforcement learning, yet solving them efficiently in a data-driven way remains challenging.