Scholar
Emanuele Rodolà
Google Scholar ID: -EH4wBYAAAAJ
Professor of Computer Science, Sapienza University of Rome
Citations & Impact
Citations
10,031
H-index
41
i10-index
95
Publications
20
Co-authors
188
list available
Publications
Resume (English only)
Academic Achievements
- Awarded Google Research Award "FairGeometry".
- Received ERC StG 2018 "SPECGEO" grant.
- Received FIS 2023 "NeXuS" grant.
- Multiple papers accepted at top-tier conferences, including:
- - NeurIPS 2025: "Implicit-ARAP: Efficient Handle-Guided Neural Field Deformation via Local Patch Meshing"
- - ISMIR 2025: "STAGE: Stemmed Accompaniment Generation through Prefix-Based Conditioning" and "LoopGen: Training-Free Loopable Music Generation"
- - ACL 2025 System Demo: "Mergenetic: a Simple Evolutionary Model Merging Library"
- - ICML 2025: "MERGE3: Efficient Evolutionary Merging on Consumer-grade GPUs" and "Update Your Transformer to the Latest Release: Re-Basin of Task Vectors"
- - CVPR 2025: "Task Singular Vectors: Reducing Task Interference in Model Merging" and "Escaping Plato’s Cave: Towards the Alignment of 3D and Text Latent Spaces"
- - ICLR 2024 (top 1.2%, oral): "Multi-Source Diffusion Models for Simultaneous Music Generation and Separation"
- - NeurIPS 2023: "ASIF: Coupled Data Turns Unimodal Models to Multimodal Without Training"
- - ACL 2023: "Accelerating Transformer Inference for Translation via Parallel Decoding"
Background
- GLADIA research lab is based at the Department of Computer Science, Sapienza University of Rome.
- The team consists of computer scientists, physicists, engineers, and mathematicians passionate about AI.
- Core research areas include model merging, model steering, training-free stitching, multimodal learning, neural model reuse, and compositionality.
- Aims to reduce the time required to create new models with novel capabilities from months to seconds.
- Also passionate about generative models for music, seeking to revolutionize music creation and enjoyment.
