相关论文: Texo: Formula Recognition within 20M Parameters

Prompt engineering can significantly improve the performance of large language models (LLMs), with automated prompt optimization (APO) gaining significant attention due to the time-consuming and laborious nature of manual prompt design.…

This paper presents Tiny-toxic-detector, a compact transformer-based model designed for toxic content detection. Despite having only 2.1 million parameters, Tiny-toxic-detector achieves competitive performance on benchmark datasets, with…

Despite recent advances in regularisation theory, the issue of parameter selection still remains a challenge for most applications. In a recent work the framework of statistical learning was used to approximate the optimal Tikhonov…

Molecular representation learning is pivotal for various molecular property prediction tasks related to drug discovery. Robust and accurate benchmarks are essential for refining and validating current methods. Existing molecular property…

Property prediction accuracy has long been a key parameter of machine learning in materials informatics. Accordingly, advanced models showing state-of-the-art performance turn into highly parameterized black boxes missing interpretability.…

Learning high-quality feature embeddings efficiently and effectively is critical for the performance of web-scale machine learning systems. A typical model ingests hundreds of features with vocabularies on the order of millions to billions…

Background: Pharmacokinetic evaluation is one of the key processes in drug discovery and development. However, current absorption, distribution, metabolism, excretion prediction models still have limited accuracy. Aim: This study aims to…

We propose a numerical technique for parameter inference in Markov models of biological processes. Based on time-series data of a process we estimate the kinetic rate constants by maximizing the likelihood of the data. The computation of…

We propose an efficient knowledge transfer approach for model-based reinforcement learning, addressing the challenge of deploying large world models in resource-constrained environments. Our method distills a high-capacity multi-task agent…

Meta-learning hyperparameter optimization (HPO) algorithms from prior experiments is a promising approach to improve optimization efficiency over objective functions from a similar distribution. However, existing methods are restricted to…

As particle accelerators increase their collision rates, and deep learning solutions prove their viability, there is a growing need for lightweight and fast neural network architectures for low-latency tasks such as triggering. We examine…

The large-scale visual pretraining has significantly improve the performance of large vision models. However, we observe the \emph{low FLOPs pitfall} that the existing low-FLOPs models cannot benefit from large-scale pretraining. In this…

Extracting dense representations for terms and phrases is a task of great importance for knowledge discovery platforms targeting highly-technical fields. Dense representations are used as features for downstream components and have multiple…

Parameterized tight-binding models fit to first principles calculations can provide an efficient and accurate quantum mechanical method for predicting properties of molecules and solids. However, well-tested parameter sets are generally…

We introduce TQCompressor, a novel method for neural network model compression with improved tensor decompositions. We explore the challenges posed by the computational and storage demands of pre-trained language models in NLP tasks and…

Seismic phase picking is fundamental for microseismic monitoring and subsurface imaging. Manual processing is impractical for real-time applications and large sensor arrays, motivating the use of deep learning-based pickers trained on…

This paper presents a systematic overview of parameter-efficient fine-tuning methods, covering over 50 papers published between early 2019 and mid-2024. These methods aim to address the challenges of fine-tuning large language models by…

We propose a novel framework for producing a class of parameter and compute efficient models called AttentionLitesuitable for resource-constrained applications. Prior work has primarily focused on optimizing models either via knowledge…

This contribution presents a parameter identification methodology for the accurate and fast estimation of model parameters in a pseudo-two-dimensional (P2D) battery model. The methodology consists of three key elements. First, the data for…

This work presents a sparse-attention Transformer architecture for modeling documents that contain large tables. Tables are ubiquitous on the web, and are rich in information. However, more than 20% of relational tables on the web have 20…