相关论文: Retrosynthesis prediction enhanced by in-silico re…

Accurate predictions of reactive mixing are critical for many Earth and environmental science problems. To investigate mixing dynamics over time under different scenarios, a high-fidelity, finite-element-based numerical model is built to…

Machine learning (ML)-based cyber-physical systems (CPSs) have been extensively developed to improve the print quality of additive manufacturing (AM). However, the reproducibility of these systems, as presented in published research, has…

Large Language Models (LLMs) have exhibited strong mathematical reasoning prowess, tackling tasks ranging from basic arithmetic to advanced competition-level problems. However, frequently occurring subtle yet critical errors, such as…

Test-Time Scaling enhances the reasoning capabilities of Large Language Models by allocating additional inference compute to broaden the exploration of the solution space. However, existing search strategies typically treat rollouts as…

Large Language Models (LLMs) show great promise in complex reasoning, with Reinforcement Learning with Verifiable Rewards (RLVR) being a key enhancement strategy. However, a prevalent issue is ``superficial self-reflection'', where models…

Machine-learning models are increasingly used to predict properties of atoms in chemical systems. There have been major advances in developing descriptors and regression frameworks for this task, typically starting from (relatively) small…

Structured chemical reaction information plays a vital role for chemists engaged in laboratory work and advanced endeavors such as computer-aided drug design. Despite the importance of extracting structured reactions from scientific…

Retrosynthesis is a technique to plan the chemical synthesis of organic molecules, for example drugs, agro- and fine chemicals. In retrosynthesis, a search tree is built by analysing molecules recursively and dissecting them into simpler…

Retrosynthetic planning is a fundamental task in organic chemistry, yet remains challenging due to its combinatorial complexity. To address this, conventional approaches typically rely on hybrid frameworks that combine single-step…

Data center (DC) infrastructure serves as the backbone to support the escalating demand for computing capacity. Traditional design methodologies that blend human expertise with specialized simulation tools scale poorly with the increasing…

Protein inverse folding, the design of an amino acid sequence based on a target protein structure, is a fundamental problem of computational protein engineering. Existing methods either generate sequences without leveraging external…

High-quality pretraining data is the fossil fuel of large language models (LLMs), yet its reserves are running low for frontier models. In this paper, we introduce RePro, a novel web recycling method that trains a relatively small LM with…

Simulation is increasingly being used for generating large labelled datasets in many machine learning problems. Recent methods have focused on adjusting simulator parameters with the goal of maximising accuracy on a validation task, usually…

Template based single step retrosynthesis predicts reactants by selecting and applying an explicit reaction template, making each prediction traceable to a chemical transformation rule. This is useful for synthesis planning, but template…

Training data plays a crucial role in Large Language Models (LLM) scaling, yet high quality data is of limited supply. Synthetic data techniques offer a potential path toward sidestepping these limitations. We conduct a large-scale…

Co-pyrolysis of biomass feedstocks with polymeric wastes is a promising strategy for improving the quantity and quality parameters of the resulting liquid fuel. Numerous experimental measurements are typically conducted to find the optimal…

While large language models hold promise for complex medical applications, their development is hindered by the scarcity of high-quality reasoning data. To address this issue, existing approaches typically distill chain-of-thought reasoning…

Model-Agnostic Meta-Learning (MAML) and its variants are popular few-shot classification methods. They train an initializer across a variety of sampled learning tasks (also known as episodes) such that the initialized model can adapt…

Synthetic data has been increasingly used to train frontier generative models. However, recent studies raise key concerns that iteratively retraining a generative model on its self-generated synthetic data may keep deteriorating model…

Quantitative understanding of rare earth element (REE) mineralization mechanisms, crucial for improving industrial separation, remains limited. This study leverages 1239 hydrothermal synthesis datapoints from material science as a surrogate…