Basic Intelligence Lab
The Basic Intelligence Lab (BIL) at Aalto University is dedicated to advancing the fundamental understanding and capabilities of artificial intelligence and machine learning. Our mission is to develop theories, algorithms, and systems that push the boundaries of what intelligent systems can achieve.
At BIL, we combine theoretical insights with practical applications, collaborating across disciplines to ensure our research contributes both to the foundations of AI and its real-world impact.
Our work is positioned at the intersection of machine learning theory, generative modeling, and intelligent systems, striving to understand and build AI that is robust, controllable, and aligned with human needs.
At BIL, we combine theoretical insights with practical applications, collaborating across disciplines to ensure our research contributes both to the foundations of AI and its real-world impact.
Our work is positioned at the intersection of machine learning theory, generative modeling, and intelligent systems, striving to understand and build AI that is robust, controllable, and aligned with human needs.
PI
Postdocs
Phd Students
Yilin Chen
ELLIS PhD student
Co-supervised with Samuel Kaski and Simon Olsson (Chalmers University of Technology).
Research Focus
Our research spans several core areas of AI:
- Next-Generation Generative AI:
- Controllable and adaptive generative models
- Reasoning for self-verification
- Theoretical foundations for compositionality
- generation diversity, and sampling efficiency Applications in scientific discovery, robotics, and other interdisciplinary domains
- Scientific Foundation Models with Human-in-the-Loop
- Trustworthy AI: Robustness, privacy, and security in AI systems
- Transfer Learning: In the context of reinforcement learning and generative models
Latest publications
Generalization in VAE and Diffusion Models : A Unified Information-Theoretic Analysis
Qi Chen, Jierui Zhu, Florian Shkurti
2025
13th International Conference on Learning Representations, ICLR 2025
ProxEdit: Improving Tuning-Free Real Image Editing With Proximal Guidance
Ligong Han, Song Wen, Qi Chen, Zhixing Zhang, Kunpeng Song, Mengwei Ren, Ruijiang Gao, Anastasis Stathopoulos, Xiaoxiao He, Yuxiao Chen, Di Liu, Qilong Zhangli, Jindong Jiang, Zhaoyang Xia, Akash Srivastava, Dimitris Metaxas
2024
Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)
Intersectional Unfairness Discovery
Gezheng Xu, Qi Chen, Charles Ling, Boyu Wang, Changjian Shui, Zico Kolter, Adrian Weller, Nuria Oliver
2024
Proceedings of the 41st International Conference on Machine Learning
Towards Understanding Evolving Patterns in Sequential Data
Qiuhao Zeng, Long-Kai Huang, Qi Chen, Charles Ling, Boyu Wang, A. Fan
2024
Advances in Neural Information Processing Systems
Algorithm-Dependent Bounds for Representation Learning of Multi-Source Domain Adaptation
Qi Chen, Mario Marchand, Francisco Ruiz
2023
Proceedings of The 26th International Conference on Artificial Intelligence and Statistics
On the Stability-Plasticity Dilemma in Continual Meta-Learning: Theory and Algorithm
Qi CHEN, Changjian Shui, Ligong Han, Mario Marchand
2023
Advances in Neural Information Processing Systems
Improving negative-prompt inversion via proximal guidance
Ligong Han, Song Wen, Qi Chen, Zhixing Zhang, Kunpeng Song, Mengwei Ren, Ruijiang Gao, Yuxiao Chen, Di Liu, Qilong Zhangli, Jindong Jiang, Zhaoyang Xia, Akash Srivastava, Dimitris Metaxas
2023
arXiv.org
A novel domain adaptation theory with Jensen–Shannon divergence
Changjian Shui, Qi Chen, Jun Wen, Fan Zhou, Christian Gagné, Boyu Wang
2022
Knowledge-Based Systems
Fair Representation Learning through Implicit Path Alignment
Changjian Shui, Qi Chen, Jiaqi Li, Boyu Wang, Christian Gagné
2022
Proceedings of Machine Learning Research