M. Hamza Mughal
Scholar

M. Hamza Mughal

Google Scholar ID: 3Lu0s40AAAAJ
Max Planck Institute for Informatics, Saarland Informatics Campus
Computer VisionMulti-modal Machine LearningVision and Language
Citations & Impact
All-time
Citations
350
 
H-index
3
 
i10-index
3
 
Publications
6
 
Co-authors
9
list available
Resume (English only)
Academic Achievements
  • Enhancing Spoken Discourse Modeling in Language Models Using Gestural Cues, ACL 2025 (Oral presentation, top 8%)
  • Retrieving Semantics from the Deep: an RAG Solution for Gesture Synthesis, CVPR 2025
  • ConvoFusion: Multi-Modal Conversational Diffusion for Co-Speech Gesture Synthesis, CVPR 2024
  • MoFusion: A Framework for Denoising-Diffusion-based Motion Synthesis, CVPR 2023 (Highlight paper, top 10%)
  • Assisting UAV Localization Via Deep Contextual Image Matching, IEEE JSTARS 2021
Research Experience
  • 2024–Present: Ph.D. Student, MPII, Germany
  • 2022–2023: Research Assistant, MPII, Germany
  • 2020–2021: Machine Learning Lead, Scribe Audio, Pakistan
  • 2019–2020: Computer Vision Engineer, VisionX, Pakistan
  • Member of RTG 2853 “Neuroexplicit Models of Language, Vision, and Action”