activity
20242026
collaborators

6 papers

cs.AI2026

Edit Knowledge, Not Just Facts via Multi-Step Reasoning over Background Stories

Ya Gao, Kalle Kujanpää, Pekka Marttinen +2

Enabling artificial intelligence systems, particularly large language models, to update knowledge and flexibly apply it during reasoning remains a central challenge. Existing knowl…

cs.HC2026

Tuning Qwen2.5-VL to Improve Its Web Interaction Skills

Alexandra Yakovleva, Henrik Pärssinen, Harri Valpola +2

Recent advances in vision-language models (VLMs) have sparked growing interest in using them to automate web tasks, yet their feasibility as independent agents that reason and act…

cs.CL2025

Efficient Knowledge Injection in LLMs via Self-Distillation

Kalle Kujanpää, Pekka Marttinen, Harri Valpola +1

In many practical applications, large language models (LLMs) need to acquire new knowledge not present in their pre-training data. Efficiently leveraging this knowledge usually rel…

cs.LG2025

Memento No More: Coaching AI Agents to Master Multiple Tasks via Hints Internalization

Minttu Alakuijala, Ya Gao, Georgy Ananov +4

As the general capabilities of artificial intelligence (AI) agents continue to evolve, their ability to learn to master multiple complex tasks through experience remains a key chal…

cs.LG2024

Diffusion models as probabilistic neural operators for recovering unobserved states of dynamical systems

Katsiaryna Haitsiukevich, Onur Poyraz, Pekka Marttinen +1

This paper explores the efficacy of diffusion-based generative models as neural operators for partial differential equations (PDEs). Neural operators are neural networks that learn…

cs.CL2024

Improved Compositional Generalization by Generating Demonstrations for Meta-Learning

Sam Spilsbury, Pekka Marttinen, Alexander Ilin

Meta-learning and few-shot prompting are viable methods to induce certain types of compositional behaviour. However, these methods can be very sensitive to the choice of support ex…