Research at aiXplain

We believe that active research contribution within the AI community is crucial for advancing our industry in proactive and beneficial ways. Throughout their careers, our team of AI scientists and engineers has consistently published their findings to actively participate in academic discourse.

  • 0

    researchers

  • 0

    publications

  • 0

    patents

  • 0

    awards

  • 0

    citations

Meet our research leaders

  • Hassan Sawaf Founder & CEO
  • Kareem Darwish aiXplain Scholar
  • Mohamed Elbadrashiny Director of Technology
  • Kamer Yuksel Distinguished Scientist

Publications from aiXplain

Agentic AI for Human Resources: LLM-Driven Candidate Assessment

System Demonstrations Track – EACL 2026

EvoArtist: A Visual LLM-Driven Agentic AI Framework for Autonomous Design Evolution

EvoMUSART 2026

EvoLiveDJ: A LLM-Based Agentic Framework for Interactive Evolutionary Live Music Performance

EvoMUSART 2026

AI Co-Artist: A LLM-Powered Framework for Interactive GLSL Shader Animation Evolution

EvoMUSART 2026

EvoLattice: Persistent Internal-Population Evolution through Multi-Alternative Quality-Diversity Graph Representations for LLM-Guided Program Discovery Read the research
LLM-Driven Active Listwise Tournaments for Portfolio Selection in Large Asset Universes Read the research
MediaMind: Revolutionizing Media Monitoring using Agentification Read the research
Efficient Machine Translation Corpus Generation: Integrating Human-in-the-Loop Post-Editing with Large Language Models Read the research
Emerging Multi-AI Agent Framework for Autonomous Agentic AI Solution Optimization

ICLR 2025

Read the research
ChameleonLLM: Batch-Aware Dynamic Low-Rank Adaptation via Inference-Time Clusters

ICLR 2025

Read the research
AlphaQuant: LLM-Driven Automated Robust Feature Engineering for Quantitative Finance

ICLR 2025

Read the research
AlphaPortfolio: Discovery of Portfolio Optimization and Allocation Methods Using LLMs

ICLR 2025

Read the research
AlphaSharpe: LLM-Driven Discovery of Robust Risk-Adjusted Metrics Read the research
Revisiting Early Detection of Sexual Predators via Turn-level Optimization

NAACL 2025

Read the research
Context-Phonetic Aware Named Entity Candidate Search for LLM-based Speech Recognition Error Correction
DyPCL: Dynamic Phoneme-level Contrastive Learning for Dysarthric Speech Recognition

NAACL 2025

Read the research
A Multi-AI Agent System for Autonomous Optimization of Agentic AI Solutions via Iterative Refinement and LLM-Driven Feedback Loops

REALM – ACL 2025

Read the research
Bel Esprit: Multi-Agent Framework for Building AI Model Pipelines

ACL 2025

Read the research
Guide-to-Explain for Controllable Summarization Read the research
HyperGAN-CLIP: A Unified Framework for Domain Adaptation, Image Synthesis and Manipulation

SIGGRAPH Asia 2024

Read the research
Cross-lingual Transfer for Automatic Question Generation by Learning Interrogative Structures in Target Languages

EMNLP 2024

Read the research
Cross-lingual Back-Parsing: Utterance Synthesis from Meaning Representation for Zero-Resource Semantic Parsing

EMNLP 2024

Read the research
AutoMode-ASR: Learning to Select ASR Systems for Better Quality and Cost

SPECOM 2024

Read the research
An Investigation Into Explainable Audio Hate Speech Detection

SIGDIAL – ACL 2024

Read the research
Creating Arabic LLM Prompts at Scale Read the research
aiXplain SDK: A High-Level and Standardized Toolkit for AI Assets

INLG 2024

Read the research
Key-Element-Informed sLLM Tuning for Document Summarization

INTERSPEECH 2024

Read the research
Multi-Dimensional Optimization for Text Summarization via Reinforcement Learning

ACL 2024

Read the research
KpopMT: Translation Dataset with Terminology for Kpop Fandom

LoResMT – ACL 2024

Read the research
Imaginary Numbers! Evaluating Numerical Referring Expressions by Neural End-to-End Surface Realization Systems

Insights – NAACL 2024

Read the research
An Automated End-to-End Open-Source Software for Generation for High-Quality Text-to-Speech Datasets

LREC-COLING 2024

Read the research
Arabic Diacritization Using Morphologically Informed Character-Level Model

LREC-COLING 2024

Read the research
Denoising Table-Text Retrieval for Open-Domain Question Answering

LREC-COLING 2024

Read the research
Explainable Multi-hop Question Generation: An End-to-End Approach without Intermediate Question Labeling

LREC-COLING 2024

Read the research
Leveraging the Interplay Between Syntactic and Acoustic Cues for Optimizing Korean TTS Pause Formation

LREC-COLING 2024

Read the research
LLM-based MT Data Creation: Dialectal to MSA Translation Shared Task

OSACT6 – LREC-COLING 2024

Read the research
OSACT6 Dialect to MSA Translation Shared Task Overview

OSACT6 – LREC-COLING 2024

Read the research
Enhancing Zero-Shot Multi-Speaker TTS with Negated Speaker Representations

AAAI 2024

Read the research
Autoregressive Score Generation for Multi-Trait Essay Scoring

EACL 2024

Read the research
Word-Level ASR Quality Estimation for Efficient Corpus Sampling and Post-Editing through Analyzing Attentions of a Reference-Free Metric

Satellite Workshops – ICASSP 2024

Read the research
SADA: Saudi Audio
 Dataset for Arabic

ICASSP 2024

Read the research
Generative Meta-Learning Robust Quality-Diversity Portfolio

GECCO 2023

Read the research
EvolveMT: An Ensemble MT Engine Improving Itself with Usage Only

Industry Track – ACL 2023

Read the research
A Reference-less Quality Metric for Automatic Speech Recognition via Contrastive-Learning of a Multi-Language Model with Self-Supervision

Satellite Workshops – ICASSP 2023

Read the research
Evaluating Multilingual Speech Translation Under Realistic Conditions with Resegmentation and Terminology

IWSLT – ACL 2023

Read the research
NoRefER: a Referenceless Quality Metric for Automatic Speech Recognition via Semi-Supervised Language Model Fine-Tuning with Contrastive Learning

INTERSPEECH 2023

Read the research
Semi-Supervised Co-Teaching for Monitoring Motor States of Parkinson’s Disease Patients

ECML PKDD 2023

Adversarial Text-to-Speech for Low-Resource Languages

WANLP – ACL 2022

Read the research
aiXplain at Arabic Hate Speech 2022: An Ensemble Based Approach to Detecting Offensive Tweets

OSACT5 2022

Read the research
Efficient Machine Translation Corpus Generation

AMTA – ACL 2022

Read the research
Gulf Arabic Diacritization: Guidelines, Initial Dataset, and Results

WANLP – ACL 2022

Read the research
MTLens: Debugging Machine Translation Systems Based on Their Output

LREC 2022

Read the research
A Retrieve and Refine Approach for RDF-to-Text

WeCNLP 2021

Read the research
Benchmark ’em All: A Unified Benchmarking Framework for Machine Translation

WeCNLP 2021

Read the research
Towards an Automated Approach for the Choice of Machine Translation Provider

WeCNLP 2021

Read the research

Join us at aiXplain!

Visit our Careers page to see career opportunities.
See open positions

aiXplain, Inc.

3031 Tisch Way #80
San Jose, CA 95128
United States