Scholar
Minttu Alakuijala
Google Scholar ID: WmrdmjIAAAAJ
Aalto University
Citations & Impact
Citations
92
H-index
4
i10-index
3
Publications
9
Co-authors
18
list available
Publications
Resume (English only)
Academic Achievements
- Memento No More: Coaching AI Agents to Master Multiple Tasks via Hints Internalization, Under review, 2025
- Video-Language Critic: Transferable Reward Functions for Language-Conditioned Robotics, TMLR, 2025
- Generating Code World Models with Large Language Models Guided by Monte Carlo Tree Search, NeurIPS 2024
- Recursive Decomposition with Dependencies for Generic Divide-and-Conquer Reasoning, NeurIPS 2024 Workshop on System 2 Reasoning at Scale
- Learning Reward Functions for Robotic Manipulation by Observing Humans, ICRA 2023
Research Experience
- Currently a Postdoctoral Researcher at Aalto University, working with Samuel Kaski and Pekka Marttinen, and coordinating the Foundation models for language & reinforcement learning team at FCAI, the Finnish Center for Artificial Intelligence. Previously, a member of the Willow and Thoth teams at Inria.
Education
- PhD, December 2022, from Google Research (through the CIFRE scheme), Inria, and Ecole Normale Superieure in Paris. Advisors: Cordelia Schmid, Jean Ponce, and Julien Mairal. PhD research focused on RL and learning from demonstration for robotic manipulation.
Background
- Research interests: LLMs, reinforcement learning (RL), and structures for systematic thinking. Professional field: artificial intelligence, robotic manipulation.
