Scholar
Massimo Caccia
Google Scholar ID: WaE4GicAAAAJ
ServiceNow Research
Citations & Impact
Citations
2,124
H-index
17
i10-index
17
Publications
20
Co-authors
21
list available
Publications
Resume (English only)
Academic Achievements
- Published multiple papers including:
- - Nevis'22, a large-scale continual learning benchmark, accepted at JMLR.
- - Task-agnostic continual RL, accepted at CoLLAs 2023.
- - A comparative study of large language models in continual learning, accepted at ICLR 2022.
- - Sparse-MAML, exploring gradient sparsity in meta and continual learning, accepted at NeurIPS 2021.
- - Local Model Composition, solving the task-inference problem in compositional continual learning, accepted at NeurIPS 2021.
- - DiVE, a counterfactual explanation method that goes beyond generating trivial counterfactuals, accepted at ICCV 2021.
- - OSAKA, proposing a new approach to continual learning, accepted at NeurIPS 2020.
- - Synbols, a synthetic dataset generator to probe different learning algorithms, accepted at NeurIPS 2020.
Research Experience
- Previously, I worked with DeepMind's Continual Learning team (led by Marc’Aurelio Ranzato), Amazon's team (under Alex Smola), and ElementAI (prior to its integration with ServiceNow). Currently, I am a Senior Research Scientist at ServiceNow Research, focusing on post-training methods for computer-use agents.
Education
- I completed my Ph.D. at the Quebec Artificial Intelligence Institute (Mila) under Professor Laurent Charlin. During my doctoral studies, I collaborated with DeepMind’s Continual Learning team led by Marc’Aurelio Ranzato, Amazon’s team under Alex Smola, and ElementAI prior to its integration with ServiceNow. My Ph.D. research focused on building agents capable of accumulating and transferring knowledge across tasks, drawing from continual learning, transfer learning, and meta-learning. My work explored applications in language, vision, and reinforcement learning, emphasizing improvements in data and compute efficiency.
Background
- I am a Senior Research Scientist at ServiceNow Research, specializing in post-training methods for computer-use agents. I see computer use as the ultimate playground for testing agents, thanks to its ubiquity and diversity. My research involves conducting large-scale empirical studies to systematically evaluate trade-offs among different approaches and to develop practical know-how, with reinforcement learning being a particular focus. As a core contributor to the web-agent research library ecosystem, I actively shape evaluation frameworks (BrowserGym, WorkArena) and development platforms (AgentLab). My goal is to bridge foundational research and scalable tools to advance the field.
