Related papers: TempRe: Template generation for single and direct …

Data-driven generative models excel in language and vision, but diffusion models often fail in constrained planning and design tasks, exhibiting severe constraint violations in engineering inverse design, molecular generation, multi-robot…

Inductive program synthesis, from input/output examples, can provide an opportunity to automatically create programs from scratch without presupposing the algorithmic form of the solution. For induction of general programs with loops (as…

While inorganic retrosynthesis planning is essential in the field of chemical science, the application of machine learning in this area has been notably less explored compared to organic retrosynthesis planning. In this paper, we propose…

We present a novel framework, SoftSRV, that is used to generate targeted synthetic fine-tuning data for improving task-specific model performance. Given a sample from a target distribution, our proposed framework uses a data-driven loss…

Sequential dependencies present a fundamental bottleneck in deploying large-scale autoregressive models, particularly for real-time applications. While traditional optimization approaches like pruning and quantization often compromise model…

Most deep learning approaches for text-to-SQL generation are limited to the WikiSQL dataset, which only supports very simple queries. Recently, template-based and sequence-to-sequence approaches were proposed to support complex queries,…

Existing large language models have to run K times to generate a sequence of K tokens. In this paper, we present RecycleGPT, a generative language model with fast decoding speed by recycling pre-generated model states without running the…

Retrosynthesis analysis is a critical task in organic chemistry central to many important industries. Previously, various machine learning approaches have achieved promising results on this task by representing output molecules as strings…

Generative models hold great promise for small molecule discovery, significantly increasing the size of search space compared to traditional in silico screening libraries. However, most existing machine learning methods for small molecule…

Relational Foundation Models (RFMs) facilitate data-driven decision-making by learning from complex multi-table databases. However, the diverse relational databases needed to train such models are rarely public due to privacy constraints.…

We discuss temporal efficiency of template-directed polymer synthesis, such as DNA replication and transcription, under a given template string. To weigh the synthesis speed and accuracy on the same scale, we propose a template-directed…

Synthetic high-quality multi-step reasoning data can significantly enhance the performance of large language models on various tasks. However, most existing methods rely on rejection sampling, which generates trajectories independently and…

Program synthesis with Genetic Programming searches for a correct program that satisfies the input specification, which is usually provided as input-output examples. One particular challenge is how to effectively handle loops and recursion…

While pretrained language models (PLMs) have greatly improved text generation, they have also been known to produce unfaithful or inappropriate content. In contrast, classic template-based systems provide strong guarantees of faithfulness…

Identifying reliable synthesis pathways in materials chemistry is a complex task, particularly in polymer science, due to the intricate and often non-unique nomenclature of macromolecules. To address this challenge, we propose an agent…

Controlling the behavior of text-to-image generative models is critical for safe and practical deployment. Existing safety approaches typically rely on model fine-tuning or curated datasets, which can degrade generation quality or limit…

Hydrogen is vital for sectors like chemicals and others, driven by the need to reduce carbon emissions. Proton Electrolyte Membrane Water Electrolysis (PEMWE) is a key technology for the production of green hydrogen under fluctuating…

Generative modeling over discrete structures underpins applications across deep learning, from biological sequence design and code generation to large language models, yet generation often remains sequential, relying on autoregressive…

Molecular-scale computation is crucial for smart materials and nanoscale devices, yet creating single-molecule systems capable of complex computations remains challenging. We present a theoretical framework for a single-molecule computer…

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…