Oded Ovadia
YOU?
Author Swipe
Knowledge-Instruct: Effective Continual Pre-training from Limited Data using Instructions Open
While Large Language Models (LLMs) acquire vast knowledge during pre-training, they often lack domain-specific, new, or niche information. Continual pre-training (CPT) attempts to address this gap but suffers from catastrophic forgetting a…
SECQUE: A Benchmark for Evaluating Real-World Financial Analysis Capabilities Open
We introduce SECQUE, a comprehensive benchmark for evaluating large language models (LLMs) in financial analysis tasks. SECQUE comprises 565 expert-written questions covering SEC filings analysis across four key categories: comparison anal…
Mixing It Up: The Cocktail Effect of Multi-Task Fine-Tuning on LLM Performance -- A Case Study in Finance Open
The application of large language models (LLMs) in domain-specific contexts, including finance, has expanded rapidly. Domain-specific LLMs are typically evaluated based on their performance in various downstream tasks relevant to the domai…
Fine-Tuning or Retrieval? Comparing Knowledge Injection in LLMs Open
Large language models (LLMs) encapsulate a vast amount of factual information within their pre-trained weights, as evidenced by their ability to answer diverse questions across different domains. However, this knowledge is inherently limit…
Real-time Inference and Extrapolation via a Diffusion-inspired Temporal Transformer Operator (DiTTO) Open
Extrapolation remains a grand challenge in deep neural networks across all application domains. We propose an operator learning method to solve time-dependent partial differential equations (PDEs) continuously and with extrapolation in tim…
Understanding the Efficacy of U-Net & Vision Transformer for Groundwater Numerical Modelling Open
This paper presents a comprehensive comparison of various machine learning models, namely U-Net, U-Net integrated with Vision Transformers (ViT), and Fourier Neural Operator (FNO), for time-dependent forward modelling in groundwater system…
ViTO: Vision Transformer-Operator Open
We combine vision transformers with operator learning to solve diverse inverse problems described by partial differential equations (PDEs). Our approach, named ViTO, combines a U-Net based architecture with a vision transformer. We apply V…
A Convolutional Dispersion Relation Preserving Scheme for the Acoustic Wave Equation Open
We propose an accurate numerical scheme for approximating the solution of the two dimensional acoustic wave problem. We use machine learning to find a stencil suitable even in the presence of high wavenumbers. The proposed scheme incorpora…
Detection of Infectious Disease Outbreaks in Search Engine Time Series Using Non-Specific Syndromic Surveillance with Effect-Size Filtering Open
Novel infectious disease outbreaks, including most recently that of the COVID-19 pandemic, could be detected by non-specific syndromic surveillance systems. Such systems, utilizing a variety of data sources ranging from Electronic Health R…
Cyclizing Painkillers: Development of Backbone-Cyclic TAPS Analogs Open
Painkillers are commonly used medications. Native peptide painkillers suffer from various pharmacological disadvantages, while small molecule painkillers like morphine are highly addictive. We present a general approach aimed to use backbo…