12 citations · 21 across the 15 of their papers we have counts for
16 papers
Beyond On-Policy vs. Off-Policy: At What Level Should LLM Agent Distillation Follow the Student?
Ya Gao, Zhengtao Zou, Pekka Marttinen
Distilling interactive LLM agents requires choosing between teacher-generated demonstrations and student-generated experience, corresponding broadly to off-policy and on-policy dis…
Bridging the Embodiment Gap: Disentangled Cross-Embodiment Video Editing
Zhiyuan Li, Wenyan Yang, Wenshuai Zhao +4
Learning robotic manipulation from human videos is a promising solution to the data bottleneck in robotics, but the distribution shift between humans and robots remains a critical…
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…
MiniLingua: A Small Open-Source LLM for European Languages
Anna Aksenova, Boris Zverkov, Nicola Dainese +2
Large language models are powerful but often limited by high computational cost, privacy concerns, and English-centric training. Recent progress demonstrates that small, efficient…
Recursive Decomposition with Dependencies for Generic Divide-and-Conquer Reasoning
Sergio Hernández-Gutiérrez, Minttu Alakuijala, Alexander V. Nikitin +1
Reasoning tasks are crucial in many domains, especially in science and engineering. Although large language models (LLMs) have made progress in reasoning tasks using techniques suc…
ViPlan: A Benchmark for Visual Planning with Symbolic Predicates and Vision-Language Models
Matteo Merler, Nicola Dainese, Minttu Alakuijala +5
Integrating Large Language Models with symbolic planners is a promising direction for obtaining verifiable and grounded plans, with recent works extending this idea to visual domai…
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…
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…
Kernel Language Entropy: Fine-grained Uncertainty Quantification for LLMs from Semantic Similarities
Alexander Nikitin, Jannik Kossen, Yarin Gal +1
Uncertainty quantification in Large Language Models (LLMs) is crucial for applications where safety and reliability are important. In particular, uncertainty can be used to improve…
Video-Language Critic: Transferable Reward Functions for Language-Conditioned Robotics
Minttu Alakuijala, Reginald McLean, Isaac Woungang +4
Natural language is often the easiest and most convenient modality for humans to specify tasks for robots. However, learning to ground language to behavior typically requires impra…
Generating Code World Models with Large Language Models Guided by Monte Carlo Tree Search
Nicola Dainese, Matteo Merler, Minttu Alakuijala +1
In this work we consider Code World Models, world models generated by a Large Language Model (LLM) in the form of Python code for model-based Reinforcement Learning (RL). Calling c…
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…
In-Context Symbolic Regression: Leveraging Large Language Models for Function Discovery
Matteo Merler, Katsiaryna Haitsiukevich, Nicola Dainese +1
State of the art Symbolic Regression (SR) methods currently build specialized models, while the application of Large Language Models (LLMs) remains largely unexplored. In this work…
Improving Medical Multi-modal Contrastive Learning with Expert Annotations
Yogesh Kumar, Pekka Marttinen
We introduce eCLIP, an enhanced version of the CLIP model that integrates expert annotations in the form of radiologist eye-gaze heatmaps. It tackles key challenges in contrastive…
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…
SANSformers: Self-Supervised Forecasting in Electronic Health Records with Attention-Free Models
Yogesh Kumar, Alexander Ilin, Henri Salo +3
Despite the proven effectiveness of Transformer neural networks across multiple domains, their performance with Electronic Health Records (EHR) can be nuanced. The unique, multidim…