Related papers: SynRXN: An Open Benchmark and Curated Dataset for …

Composable AI offers a scalable and effective paradigm for tackling complex AI tasks by decomposing them into sub-tasks and solving each sub-task using ready-to-use well-trained models. However, systematically evaluating methods under this…

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…

Computer-assisted surgical (CAS) systems enhance surgical execution and outcomes by providing advanced support to surgeons. These systems often rely on deep learning models trained on complex, challenging-to-annotate data. While synthetic…

Evaluating language models fairly is increasingly difficult as static benchmarks risk contamination by training data, obscuring whether models truly reason or recall. We introduce BeyondBench, an evaluation framework using algorithmic…

As LLM agents transition to autonomous digital coworkers, maintaining deterministic goal-directedness in non-linear multi-turn conversations emerged as an architectural bottleneck. We identify and formalize a systemic failure mode termed…

In materials discovery, the integration of first-principles calculations with machine learning techniques has been actively studied for two key tasks: crystal structure prediction, which searches for stable structures given a chemical…

Recent advances in learning-based perception systems have led to drastic improvements in the performance of robotic systems like autonomous vehicles and surgical robots. These perception systems, however, are hard to analyze and errors in…

Large language models (LLMs) have been widely adopted for synthetic data generation, significantly reducing annotation costs. However, most existing studies treat synthesis as a set of isolated tasks and overlook a more fundamental…

Analytical tools often require real-time responses for highly concurrent parameterized workloads. A common solution is to answer queries using materialized subexpressions, hence reducing processing at runtime. However, as queries are still…

Despite advances in data augmentation and transfer learning, convolutional neural networks (CNNs) difficultly generalise to unseen domains. When segmenting brain scans, CNNs are highly sensitive to changes in resolution and contrast: even…

A well-defined benchmark is essential for measuring and accelerating research progress of machine learning models. In this paper, we present a benchmark for high-level mathematical reasoning and study the reasoning capabilities of neural…

The Physics Analysis eXpert (PAX) is an open source toolkit for high energy physics analysis. The C++ class collection provided by PAX is deployed in a number of analyses with complex event topologies at Tevatron and LHC. In this article,…

As machine learning systems are increasingly deployed in high-stakes domains such as criminal justice, finance, and healthcare, the demand for interpretable and trustworthy models has intensified. Despite the proliferation of local…

We develop a nonparametric Bayesian modeling framework for clustered ordinal responses in developmental toxicity studies, which typically exhibit extensive heterogeneity. The primary focus of these studies is to examine the dose-response…

The chemical reaction network (CRN) is a widely used formalism to describe macroscopic behavior of chemical systems. Available tools for CRN modelling and simulation require local access, installation, and often involve local file storage,…

The integration of Multimodal Large Language Models (MLLMs) into chemistry promises to revolutionize scientific discovery, yet their ability to comprehend the dense, graphical language of reactions within authentic literature remains…

Current state-of-the-art synchrony-based models encode object bindings with complex-valued activations and compute with real-valued weights in feedforward architectures. We argue for the computational advantages of a recurrent architecture…

The constrained nature of synthesizable chemical space poses a significant challenge for sampling molecules that are both synthetically accessible and possess desired properties. In this work, we present PrexSyn, an efficient and…

We consider how to generate chemical reaction networks (CRNs) from functional specifications. We propose a two-stage approach that combines synthesis by satisfiability modulo theories and Markov chain Monte Carlo based optimisation. First,…

Existing approaches typically rely on large-scale fine-tuning to adapt LLMs for information reranking tasks, which is computationally expensive. In this work, we demonstrate that modern LLMs can be effectively adapted using only minimal,…