Pekka Marttinen

Xiang Li, Yazhou Zhang, Prayag Tiwari et al.

Emotion recognition technology through analyzing the EEG signal is currently an essential concept in Artificial Intelligence and holds great potential in emotional health care, human-computer interaction, multimedia content recommendation, etc. Though there have been several works devoted to reviewing EEG-based emotion recognition, the content of these reviews needs to be updated. In addition, those works are either fragmented in content or only focus on specific techniques adopted in this area but neglect the holistic perspective of the entire technical routes. Hence, in this paper, we review from the perspective of researchers who try to take the first step on this topic. We review the recent representative works in the EEG-based emotion recognition research and provide a tutorial to guide the researchers to start from the beginning. The scientific basis of EEG-based emotion recognition in the psychological and physiological levels is introduced. Further, we categorize these reviewed works into different technical routes and illustrate the theoretical basis and the research motivation, which will help the readers better understand why those techniques are studied and employed. At last, existing challenges and future investigations are also discussed in this paper, which guides the researchers to decide potential future research directions.

Joel Honkamaa, Pekka Marttinen

Deep learning has emerged as a strong alternative for classical iterative methods for deformable medical image registration, where the goal is to find a mapping between the coordinate systems of two images. Popular classical image registration methods enforce the useful inductive biases of symmetricity, inverse consistency, and topology preservation by construction. However, while many deep learning registration methods encourage these properties via loss functions, no earlier methods enforce all of them by construction. Here, we propose a novel registration architecture based on extracting multi-resolution feature representations which is by construction symmetric, inverse consistent, and topology preserving. We also develop an implicit layer for memory efficient inversion of the deformation fields. Our method achieves state-of-the-art registration accuracy on three datasets. The code is available at https://github.com/honkamj/SITReg.

Joel Honkamaa, Umair Khan, Sonja Koivukoski et al.

Cross-modality image synthesis is an active research topic with multiple medical clinically relevant applications. Recently, methods allowing training with paired but misaligned data have started to emerge. However, no robust and well-performing methods applicable to a wide range of real world data sets exist. In this work, we propose a generic solution to the problem of cross-modality image synthesis with paired but non-aligned data by introducing new deformation equivariance encouraging loss functions. The method consists of joint training of an image synthesis network together with separate registration networks and allows adversarial training conditioned on the input even with misaligned data. The work lowers the bar for new clinical applications by allowing effortless training of cross-modality image synthesis networks for more difficult data sets.

Arina Odnoblyudova, Çağlar Hizli, ST John et al.

In biomedical applications it is often necessary to estimate a physiological response to a treatment consisting of multiple components, and learn the separate effects of the components in addition to the joint effect. Here, we extend existing probabilistic nonparametric approaches to explicitly address this problem. We also develop a new convolution-based model for composite treatment-response curves that is more biologically interpretable. We validate our models by estimating the impact of carbohydrate and fat in meals on blood glucose. By differentiating treatment components, incorporating their dosages, and sharing statistical information across patients via a hierarchical multi-output Gaussian process, our method improves prediction accuracy over existing approaches, and allows us to interpret the different effects of carbohydrates and fat on the overall glucose response.

Shaoxiong Ji, Ya Gao, Pekka Marttinen

Adverse drug events (ADEs) are an important aspect of drug safety. Various texts such as biomedical literature, drug reviews, and user posts on social media and medical forums contain a wealth of information about ADEs. Recent studies have applied word embedding and deep learning -based natural language processing to automate ADE detection from text. However, they did not explore incorporating explicit medical knowledge about drugs and adverse reactions or the corresponding feature learning. This paper adopts the heterogenous text graph which describes relationships between documents, words and concepts, augments it with medical knowledge from the Unified Medical Language System, and proposes a concept-aware attention mechanism which learns features differently for the different types of nodes in the graph. We further utilize contextualized embeddings from pretrained language models and convolutional graph neural networks for effective feature representation and relational learning. Experiments on four public datasets show that our model achieves performance competitive to the recent advances and the concept-aware attention consistently outperforms other attention mechanisms.

Çağlar Hızlı, ST John, Anne Juuti et al.

Deciding on an appropriate intervention requires a causal model of a treatment, the outcome, and potential mediators. Causal mediation analysis lets us distinguish between direct and indirect effects of the intervention, but has mostly been studied in a static setting. In healthcare, data come in the form of complex, irregularly sampled time-series, with dynamic interdependencies between a treatment, outcomes, and mediators across time. Existing approaches to dynamic causal mediation analysis are limited to regular measurement intervals, simple parametric models, and disregard long-range mediator--outcome interactions. To address these limitations, we propose a non-parametric mediator--outcome model where the mediator is assumed to be a temporal point process that interacts with the outcome process. With this model, we estimate the direct and indirect effects of an external intervention on the outcome, showing how each of these affects the whole future trajectory. We demonstrate on semi-synthetic data that our method can accurately estimate direct and indirect effects. On real-world healthcare data, our model infers clinically meaningful direct and indirect effect trajectories for blood glucose after a surgery.

Çağlar Hızlı, ST John, Anne Juuti et al.

A treatment policy defines when and what treatments are applied to affect some outcome of interest. Data-driven decision-making requires the ability to predict what happens if a policy is changed. Existing methods that predict how the outcome evolves under different scenarios assume that the tentative sequences of future treatments are fixed in advance, while in practice the treatments are determined stochastically by a policy and may depend, for example, on the efficiency of previous treatments. Therefore, the current methods are not applicable if the treatment policy is unknown or a counterfactual analysis is needed. To handle these limitations, we model the treatments and outcomes jointly in continuous time, by combining Gaussian processes and point processes. Our model enables the estimation of a treatment policy from observational sequences of treatments and outcomes, and it can predict the interventional and counterfactual progression of the outcome after an intervention on the treatment policy (in contrast with the causal effect of a single treatment). We show with real-world and semi-synthetic data on blood glucose progression that our method can answer causal queries more accurately than existing alternatives.

Anna Aksenova, Boris Zverkov, Nicola Dainese et al.

Large language models are powerful but often limited by high computational cost, privacy concerns, and English-centric training. Recent progress demonstrates that small, efficient models with around one billion parameters can deliver strong results and enable on-device use. This paper introduces MiniLingua, a multilingual open-source LLM of one billion parameters trained from scratch for 13 European languages, designed to balance coverage and instruction-following capabilities. Based on evaluation results, the instruction-tuned version of MiniLingua outperforms EuroLLM, a model with a similar training approach but a larger training budget, on summarization, classification and both open- and closed-book question answering. Moreover, it remains competitive with more advanced state-of-the-art models on open-ended generation tasks. We release model weights, tokenizer and source code used for data processing and model training.

Shaoxiong Ji, Wei Sun, Pekka Marttinen

Many computational linguistic methods have been proposed to study the information content of languages. We consider two interesting research questions: 1) how is information distributed over long documents, and 2) how does content reduction, such as token selection and text summarization, affect the information density in long documents. We present four criteria for information density estimation for long documents, including surprisal, entropy, uniform information density, and lexical density. Among those criteria, the first three adopt the measures from information theory. We propose an attention-based word selection method for clinical notes and study machine summarization for multiple-domain documents. Our findings reveal the systematic difference in information density of long text in various domains. Empirical results on automated medical coding from long clinical notes show the effectiveness of the attention-based word selection method.

Vishnu Raj, Tianyu Cui, Markus Heinonen et al.

Bayesian neural networks (BNNs) can account for both aleatoric and epistemic uncertainty. However, in BNNs the priors are often specified over the weights which rarely reflects true prior knowledge in large and complex neural network architectures. We present a simple approach to incorporate prior knowledge in BNNs based on external summary information about the predicted classification probabilities for a given dataset. The available summary information is incorporated as augmented data and modeled with a Dirichlet process, and we derive the corresponding \emph{Summary Evidence Lower BOund}. The approach is founded on Bayesian principles, and all hyperparameters have a proper probabilistic interpretation. We show how the method can inform the model about task difficulty and class imbalance. Extensive experiments show that, with negligible computational overhead, our method parallels and in many cases outperforms popular alternatives in accuracy, uncertainty calibration, and robustness against corruptions with both balanced and imbalanced data.

Ya Gao, Kalle Kujanpää, Pekka Marttinen et al.

Enabling artificial intelligence systems, particularly large language models, to integrate new knowledge and flexibly apply it during reasoning remains a central challenge. Existing knowledge editing approaches emphasize atomic facts, improving factual recall but often failing to integrate new information into a coherent framework usable across contexts. In this work, we argue that knowledge internalization is fundamentally a reasoning problem rather than a memorization problem. Consequently, a model should be trained in situations where the new information is instrumental to solving a task, combined with pre-existing knowledge, and exercised through multi-step reasoning. Based on this insight, we propose a training strategy based on three principles. First, new knowledge is introduced as a coherent background story that contextualizes novel facts and explains their relation to existing knowledge. Second, models are trained using self-generated multi-hop questions that require multi-step reasoning involving the new information. Third, training is done using knowledge distillation, forcing a student model to internalize the teacher's reasoning behavior without access to the novel information. Experiments show that models trained with this strategy effectively leverage newly acquired knowledge during reasoning and achieve remarkable performance on challenging questions that require combining multiple new facts.

Ya Gao, Hans Moen, Saila Koivusalo et al.

Nursing notes, an important part of Electronic Health Records (EHRs), track a patient's health during a care episode. Summarizing key information in nursing notes can help clinicians quickly understand patients' conditions. However, existing summarization methods in the clinical setting, especially abstractive methods, have overlooked nursing notes and require reference summaries for training. We introduce QGSumm, a novel query-guided self-supervised domain adaptation approach for abstractive nursing note summarization. The method uses patient-related clinical queries for guidance, and hence does not need reference summaries for training. Through automatic experiments and manual evaluation by an expert clinician, we study our approach and other state-of-the-art Large Language Models (LLMs) for nursing note summarization. Our experiments show: 1) GPT-4 is competitive in maintaining information in the original nursing notes, 2) QGSumm can generate high-quality summaries with a good balance between recall of the original content and hallucination rate lower than other top methods. Ultimately, our work offers a new perspective on conditional text summarization, tailored to clinical applications.

Hung Nguyen, Hans Moen, Pekka Marttinen

Extracting insights from Electronic Health Record (EHR) databases often requires SQL expertise, creating a barrier for clinical decision-making and research. A promising approach is to use Large Language Models (LLMs) to translate natural language questions into SQL through Retrieval-Augmented Generation (RAG), where relevant question-SQL examples are retrieved to generate new queries via few-shot learning. However, adapting this method to the medical domain is non-trivial, as effective retrieval requires examples that align with both the logical structure of the question and its referenced entities (e.g., drug names, procedure titles). Standard single-step RAG struggles to optimize both aspects simultaneously and often relies on near-exact matches to generalize effectively. This issue is especially severe in healthcare, as questions often contain noisy and inconsistent medical jargon. To address this, we present CBR-to-SQL, a framework inspired by Case-based Reasoning theory that decomposes RAG's single-step retrieval into two explicit stages: one that focuses on retrieving structurally relevant examples, and one that aligns entities with the target database schema. Evaluated on two clinical benchmarks, CBR-to-SQL achieves competitive accuracies compared to fine-tuned methods. More importantly, it demonstrates considerably higher sample efficiency and robustness than the standard RAG approach, particularly under data scarcity and retrieval perturbations.

Onur Poyraz, Pekka Marttinen

Analysis of multivariate healthcare time series data is inherently challenging: irregular sampling, noisy and missing values, and heterogeneous patient groups with different dynamics violating exchangeability. In addition, interpretability and quantification of uncertainty are critically important. Here, we propose a novel class of models, a mixture of coupled hidden Markov models (M-CHMM), and demonstrate how it elegantly overcomes these challenges. To make the model learning feasible, we derive two algorithms to sample the sequences of the latent variables in the CHMM: samplers based on (i) particle filtering and (ii) factorized approximation. Compared to existing inference methods, our algorithms are computationally tractable, improve mixing, and allow for likelihood estimation, which is necessary to learn the mixture model. Experiments on challenging real-world epidemiological and semi-synthetic data demonstrate the advantages of the M-CHMM: improved data fit, capacity to efficiently handle missing and noisy measurements, improved prediction accuracy, and ability to identify interpretable subsets in the data.

Matteo Merler, Nicola Dainese, Minttu Alakuijala et al.

Integrating Large Language Models with symbolic planners is a promising direction for obtaining verifiable and grounded plans compared to planning in natural language, with recent works extending this idea to visual domains using Vision-Language Models (VLMs). However, rigorous comparison between VLM-grounded symbolic approaches and methods that plan directly with a VLM has been hindered by a lack of common environments, evaluation protocols and model coverage. We introduce ViPlan, the first open-source benchmark for Visual Planning with symbolic predicates and VLMs. ViPlan features a series of increasingly challenging tasks in two domains: a visual variant of the classic Blocksworld planning problem and a simulated household robotics environment. We benchmark nine open-source VLM families across multiple sizes, along with selected closed models, evaluating both VLM-grounded symbolic planning and using the models directly to propose actions. We find symbolic planning to outperform direct VLM planning in Blocksworld, where accurate image grounding is crucial, whereas the opposite is true in the household robotics tasks, where commonsense knowledge and the ability to recover from errors are beneficial. Finally, we show that across most models and methods, there is no significant benefit to using Chain-of-Thought prompting, suggesting that current VLMs still struggle with visual reasoning.

Zhengtao Zou, Ya Gao, Jiarui Guan et al.

Large Vision-Language Models (LVLMs) often suffer from object hallucination, generating text inconsistent with visual inputs, which can critically undermine their reliability. Existing inference-time interventions to mitigate this issue present a challenging trade-off: while methods that steer internal states or adjust output logits can be effective, they often incur substantial computational overhead, typically requiring extra forward passes. This efficiency bottleneck can limit their practicality for real-world, latency-sensitive deployments. In this work, we aim to address this trade-off with Residual-Update Directed DEcoding Regulation (RUDDER), a low-overhead framework that steers LVLMs towards visually-grounded generation. RUDDER is built on two key innovations: (1) Contextual Activation Residual Direction (CARD) vector, a per-sample visual evidence vector extracted from the residual update of a self-attention layer during a single, standard forward pass. (2) A Bayesian-inspired adaptive gate that performs token-wise injection, applying a corrective signal whose strength is conditioned on the model's deviation from the visual context. Extensive experiments on key hallucination benchmarks, including POPE and CHAIR, indicate that RUDDER achieves performance comparable to state-of-the-art methods while introducing negligible computational latency, validating RUDDER as a pragmatic and effective approach for improving LVLMs' reliability without a significant compromise on efficiency.

Antti Pöllänen, Pekka Marttinen

In some causal inference scenarios, the treatment variable is measured inaccurately, for instance in epidemiology or econometrics. Failure to correct for the effect of this measurement error can lead to biased causal effect estimates. Previous research has not studied methods that address this issue from a causal viewpoint while allowing for complex nonlinear dependencies and without assuming access to side information. For such a scenario, this study proposes a model that assumes a continuous treatment variable that is inaccurately measured. Building on existing results for measurement error models, we prove that our model's causal effect estimates are identifiable, even without side information and knowledge of the measurement error variance. Our method relies on a deep latent variable model in which Gaussian conditionals are parameterized by neural networks, and we develop an amortized importance-weighted variational objective for training the model. Empirical results demonstrate the method's good performance with unknown measurement error. More broadly, our work extends the range of applications in which reliable causal inference can be conducted.

Shaoxiong Ji, Shirui Pan, Erik Cambria et al.

Human knowledge provides a formal understanding of the world. Knowledge graphs that represent structural relations between entities have become an increasingly popular research direction towards cognition and human-level intelligence. In this survey, we provide a comprehensive review of knowledge graph covering overall research topics about 1) knowledge graph representation learning, 2) knowledge acquisition and completion, 3) temporal knowledge graph, and 4) knowledge-aware applications, and summarize recent breakthroughs and perspective directions to facilitate future research. We propose a full-view categorization and new taxonomies on these topics. Knowledge graph embedding is organized from four aspects of representation space, scoring function, encoding models, and auxiliary information. For knowledge acquisition, especially knowledge graph completion, embedding methods, path inference, and logical rule reasoning, are reviewed. We further explore several emerging topics, including meta relational learning, commonsense reasoning, and temporal knowledge graphs. To facilitate future research on knowledge graphs, we also provide a curated collection of datasets and open-source libraries on different tasks. In the end, we have a thorough outlook on several promising research directions.

Zhiyuan Li, Rongzhen Zhao, Wenyan Yang et al.

The de facto approach in video object-centric learning maintains temporal consistency through learned dynamics modules that predict future object representations, called slots. We demonstrate that these predictors function as expensive approximations of discrete correspondence problems. Modern self-supervised vision backbones already encode instance-discriminative features that distinguish objects reliably. Exploiting these features eliminates the need for learned temporal prediction. We introduce Grounded Correspondence, a framework that replaces learned transition functions with deterministic bipartite matching. Slots initialize from salient regions in frozen backbone features. Frame-to-frame identity is maintained through Hungarian matching on slot representations. The approach requires zero learnable parameters for temporal modeling yet achieves competitive performance on MOVi-D, MOVi-E, and YouTube-VIS. Project page: https://magenta-sherbet-85b101.netlify.app/

Zhiyuan Li, Wenyan Yang, Wenshuai Zhao et al.

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 challenge. Existing approaches often produce entangled representations, where task-relevant information is coupled with human-specific kinematics, limiting their adaptability. We propose a generative framework for cross-embodiment video editing that directly addresses this by learning explicitly disentangled task and embodiment representations. Our method factorizes a demonstration video into two orthogonal latent spaces by enforcing a dual contrastive objective: it minimizes mutual information between the spaces to ensure independence while maximizing intra-space consistency to create stable representations. A parameter-efficient adapter injects these latent codes into a frozen video diffusion model, enabling the synthesis of a coherent robot execution video from a single human demonstration, without requiring paired cross-embodiment data. Experiments show our approach generates temporally consistent and morphologically accurate robot demonstrations, offering a scalable solution to leverage internet-scale human video for robot learning.

Matteo Merler, Katsiaryna Haitsiukevich, Nicola Dainese et al.

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, we introduce the first comprehensive framework that utilizes LLMs for the task of SR. We propose In-Context Symbolic Regression (ICSR), an SR method which iteratively refines a functional form with an LLM and determines its coefficients with an external optimizer. ICSR leverages LLMs' strong mathematical prior both to propose an initial set of possible functions given the observations and to refine them based on their errors. Our findings reveal that LLMs are able to successfully find symbolic equations that fit the given data, matching or outperforming the overall performance of the best SR baselines on four popular benchmarks, while yielding simpler equations with better out of distribution generalization.

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 multi-modal medical imaging analysis, notably data scarcity and the "modality gap" -- a significant disparity between image and text embeddings that diminishes the quality of representations and hampers cross-modal interoperability. eCLIP integrates a heatmap processor and leverages mixup augmentation to efficiently utilize the scarce expert annotations, thus boosting the model's learning effectiveness. eCLIP is designed to be generally applicable to any variant of CLIP without requiring any modifications of the core architecture. Through detailed evaluations across several tasks, including zero-shot inference, linear probing, cross-modal retrieval, and Retrieval Augmented Generation (RAG) of radiology reports using a frozen Large Language Model, eCLIP showcases consistent improvements in embedding quality. The outcomes reveal enhanced alignment and uniformity, affirming eCLIP's capability to harness high-quality annotations for enriched multi-modal analysis in the medical imaging domain.

Nicola Dainese, Matteo Merler, Minttu Alakuijala et al.

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 code instead of LLMs for planning has potential to be more precise, reliable, interpretable, and extremely efficient. However, writing appropriate Code World Models requires the ability to understand complex instructions, to generate exact code with non-trivial logic and to self-debug a long program with feedback from unit tests and environment trajectories. To address these challenges, we propose Generate, Improve and Fix with Monte Carlo Tree Search (GIF-MCTS), a new code generation strategy for LLMs. To test our approach in an offline RL setting, we introduce the Code World Models Benchmark (CWMB), a suite of program synthesis and planning tasks comprised of 18 diverse RL environments paired with corresponding textual descriptions and curated trajectories. GIF-MCTS surpasses all baselines on the CWMB and two other benchmarks, and we show that the Code World Models synthesized with it can be successfully used for planning, resulting in model-based RL agents with greatly improved sample efficiency and inference speed.

Mihriban Kocak Balik, Pekka Marttinen, Negar Safinianaini

Integrating different molecular layers, i.e., multiomics data, is crucial for unraveling the complexity of diseases; yet, most deep generative models either prioritize predictive performance at the expense of interpretability or enforce interpretability by linearizing the decoder, thereby weakening the network's nonlinear expressiveness. To overcome this tradeoff, we introduce POEMS: Product Of Experts for Interpretable Multiomics Integration using Sparse Decoding, an unsupervised probabilistic framework that preserves predictive performance while providing interpretability. POEMS provides interpretability without linearizing any part of the network by 1) mapping features to latent factors using sparse connections, which directly translates to biomarker discovery, 2) allowing for cross-omic associations through a shared latent space using product of experts model, and 3) reporting contributions of each omic by a gating network that adaptively computes their influence in the representation learning. Additionally, we present an efficient sparse decoder. In a cancer subtyping case study, POEMS achieves competitive clustering and classification performance while offering our novel set of interpretations, demonstrating that biomarker based insight and predictive accuracy can coexist in multiomics representation learning.

Kalle Kujanpää, Pekka Marttinen, Harri Valpola et al.

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 relies on supervised fine-tuning or retrieval-augmented generation (RAG). Although RAG has emerged as the industry standard for knowledge injection, fine-tuning has not yet achieved comparable success. This paper proposes utilizing prompt distillation, a self-distillation-based method previously explored primarily for style alignment and instruction tuning, to internalize new factual knowledge from free-form documents. Unlike prior methods, our approach requires neither larger teacher models nor structured knowledge formats. Across multiple LLM sizes and model families, we show that prompt distillation outperforms standard supervised fine-tuning and can even surpass RAG. We analyze the key factors contributing to prompt distillation's effectiveness and examine how it scales.

Junyu Chen, Shuwen Wei, Joel Honkamaa et al.

Medical image challenges have played a transformative role in advancing the field, catalyzing algorithmic innovation and establishing new performance standards across diverse clinical applications. Image registration, a foundational task in neuroimaging pipelines, has similarly benefited from the Learn2Reg initiative. Building on this foundation, we introduce the Large-scale Unsupervised Brain MRI Image Registration (LUMIR) challenge, a next-generation benchmark designed to assess and advance unsupervised brain MRI registration. Distinct from prior challenges that leveraged anatomical label maps for supervision, LUMIR removes this dependency by providing over 4,000 preprocessed T1-weighted brain MRIs for training without any label maps, encouraging biologically plausible deformation modeling through self-supervision. In addition to evaluating performance on 590 held-out test subjects, LUMIR introduces a rigorous suite of zero-shot generalization tasks, spanning out-of-domain imaging modalities (e.g., FLAIR, T2-weighted, T2*-weighted), disease populations (e.g., Alzheimer's disease), acquisition protocols (e.g., 9.4T MRI), and species (e.g., macaque brains). A total of 1,158 subjects and over 4,000 image pairs were included for evaluation. Performance was assessed using both segmentation-based metrics (Dice coefficient, 95th percentile Hausdorff distance) and landmark-based registration accuracy (target registration error). Across both in-domain and zero-shot tasks, deep learning-based methods consistently achieved state-of-the-art accuracy while producing anatomically plausible deformation fields. The top-performing deep learning-based models demonstrated diffeomorphic properties and inverse consistency, outperforming several leading optimization-based methods, and showing strong robustness to most domain shifts, the exception being a drop in performance on out-of-domain contrasts.

Katsiaryna Haitsiukevich, Onur Poyraz, Pekka Marttinen et al.

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 a mapping from the parameter space to the solution space of PDEs from data, and they can also solve the inverse problem of estimating the parameter from the solution. Diffusion models excel in many domains, but their potential as neural operators has not been thoroughly explored. In this work, we show that diffusion-based generative models exhibit many properties favourable for neural operators, and they can effectively generate the solution of a PDE conditionally on the parameter or recover the unobserved parts of the system. We propose to train a single model adaptable to multiple tasks, by alternating between the tasks during training. In our experiments with multiple realistic dynamical systems, diffusion models outperform other neural operators. Furthermore, we demonstrate how the probabilistic diffusion model can elegantly deal with systems which are only partially identifiable, by producing samples corresponding to the different possible solutions.

Minttu Alakuijala, Ya Gao, Georgy Ananov et al.

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 challenge. Current LLM agents, particularly those based on proprietary language models, typically rely on prompts to incorporate knowledge about the target tasks. This approach does not allow the agent to internalize this information and instead relies on ever-expanding prompts to sustain its functionality in diverse scenarios. This resembles a system of notes used by a person affected by anterograde amnesia, the inability to form new memories. In this paper, we propose a novel method to train AI agents to incorporate knowledge and skills for multiple tasks without the need for either cumbersome note systems or prior high-quality demonstration data. Our approach employs an iterative process where the agent collects new experiences, receives corrective feedback from humans in the form of hints, and integrates this feedback into its weights via a context distillation training procedure. We demonstrate the efficacy of our approach by implementing it in a Llama-3-based agent that, after only a few rounds of feedback, outperforms advanced models GPT-4o and DeepSeek-V3 in tasksets requiring correct sequencing of information retrieval, tool use, and question answering.

Sergio Hernández-Gutiérrez, Minttu Alakuijala, Alexander V. Nikitin et al.

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 such as chain-of-thought and least-to-most prompting, these approaches still do not effectively scale to complex problems in either their performance or execution time. Moreover, they often require additional supervision for each new task, such as in-context examples. In this work, we introduce Recursive Decomposition with Dependencies (RDD), a scalable divide-and-conquer method for solving reasoning problems that requires less supervision than prior approaches. Our method can be directly applied to a new problem class even in the absence of any task-specific guidance. Furthermore, RDD supports sub-task dependencies, allowing for ordered execution of sub-tasks, as well as an error recovery mechanism that can correct mistakes made in previous steps. We evaluate our approach on two benchmarks with six difficulty levels each and in two in-context settings: one with task-specific examples and one without. Our results demonstrate that RDD outperforms other methods in a compute-matched setting as task complexity increases, while also being more computationally efficient.

Hans Moen, Vishnu Raj, Andrius Vabalas et al.

Health registers contain rich information about individuals' health histories. Here our interest lies in understanding how individuals' health trajectories evolve in a nationwide longitudinal dataset with coded features, such as clinical codes, procedures, and drug purchases. We introduce a straightforward approach for training a Transformer-based deep learning model in a way that lets us analyze how individuals' trajectories change over time. This is achieved by modifying the training objective and by applying a causal attention mask. We focus here on a general task of predicting the onset of a range of common diseases in a given future forecast interval. However, instead of providing a single prediction about diagnoses that could occur in this forecast interval, our approach enable the model to provide continuous predictions at every time point up until, and conditioned on, the time of the forecast period. We find that this model performs comparably to other models, including a bi-directional transformer model, in terms of basic prediction performance while at the same time offering promising trajectory modeling properties. We explore a couple of ways to use this model for analyzing health trajectories and aiding in early detection of events that forecast possible later disease onsets. We hypothesize that this method may be helpful in continuous monitoring of peoples' health trajectories and enabling interventions in ongoing health trajectories, as well as being useful in retrospective analyses.

Joel Honkamaa, Pekka Marttinen

Deep learning based deformable registration methods have become popular in recent years. However, their ability to generalize beyond training data distribution can be poor, significantly hindering their usability. LUMIR brain registration challenge for Learn2Reg 2025 aims to advance the field by evaluating the performance of the registration on contrasts and modalities different from those included in the training set. Here we describe our submission to the challenge, which proposes a very simple idea for significantly improving robustness by transforming the images into MIND feature space before feeding them into the model. In addition, a special ensembling strategy is proposed that shows a small but consistent improvement.

Lasse Hansen, Wiebke Heyer, Christoph Großbröhmer et al.

Medical image registration is critical for clinical applications, and fair benchmarking of different methods is essential for monitoring ongoing progress. To date, the Learn2Reg 2020-2023 challenges have released several complementary datasets and established metrics for evaluations. However, these editions did not capture all aspects of the registration problem, particularly in terms of modality diversity and task complexity. To address these limitations, the 2024 edition introduces three new tasks, including large-scale multi-modal registration and unsupervised inter-subject brain registration, as well as the first microscopy-focused benchmark within Learn2Reg. The new datasets also inspired new method developments, including invertibility constraints, pyramid features, keypoints alignment and instance optimisation.

Çağlar Hızlı, Çağatay Yıldız, Pekka Marttinen

State-of-the-art vision pretraining methods rely on image-level self-distillation from object-centric datasets such as ImageNet, implicitly assuming each image contains a single object. This assumption does not always hold: many ImageNet images already contain multiple objects. Further, it limits scalability to scene-centric datasets that better mirror real-world complexity. We address these challenges by introducing Object-level Self-DIStillation (ODIS), a pretraining approach that shifts the self-distillation granularity from whole images to individual objects. Using object-aware cropping and masked attention, ODIS isolates object-specific regions, guiding the transformer toward semantically meaningful content and transforming a noisy, scene-level task into simpler object-level sub-tasks. We show that this approach improves visual representations both at the image and patch levels. Using masks at inference time, our method achieves an impressive $82.6\%$ $k$-NN accuracy on ImageNet1k with ViT-Large.

Joel Honkamaa, Pekka Marttinen

The deformable registration of images of different modalities, essential in many medical imaging applications, remains challenging. The main challenge is developing a robust measure for image overlap despite the compared images capturing different aspects of the underlying tissue. Here, we explore similarity metrics based on functional dependence between intensity values of registered images. Although functional dependence is too restrictive on the global scale, earlier work has shown competitive performance in deformable registration when such measures are applied over small enough contexts. We confirm this finding and further develop the idea by modeling local functional dependence via the linear basis function model with the basis functions learned jointly with the deformation. The measure can be implemented via convolutions, making it efficient to compute on GPUs. We release the method as an easy-to-use tool and show good performance on three datasets compared to well-established baseline and earlier functional dependence-based methods.

Çağlar Hızlı, Çağatay Yıldız, Matthias Bethge et al.

This work aims to improve generalization and interpretability of dynamical systems by recovering the underlying lower-dimensional latent states and their time evolutions. Previous work on disentangled representation learning within the realm of dynamical systems focused on the latent states, possibly with linear transition approximations. As such, they cannot identify nonlinear transition dynamics, and hence fail to reliably predict complex future behavior. Inspired by the advances in nonlinear ICA, we propose a state-space modeling framework in which we can identify not just the latent states but also the unknown transition function that maps the past states to the present. We introduce a practical algorithm based on variational auto-encoders and empirically demonstrate in realistic synthetic settings that we can (i) recover latent state dynamics with high accuracy, (ii) correspondingly achieve high future prediction accuracy, and (iii) adapt fast to new environments.

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 examples used. Choosing good supports from the training data for a given test query is already a difficult problem, but in some cases solving this may not even be enough. We consider a grounded language learning problem (gSCAN) where good support examples for certain test splits might not even exist in the training data, or would be infeasible to search for. We design an agent which instead generates possible supports which are relevant to the test query and current state of the world, then uses these supports via meta-learning to solve the test query. We show substantially improved performance on a previously unsolved compositional behaviour split without a loss of performance on other splits. Further experiments show that in this case, searching for relevant demonstrations even with an oracle function is not sufficient to attain good performance when using meta-learning.

Manish Bhatia, Balram Meena, Vipin Kumar Rathi et al.

The shape of erythrocytes or red blood cells is altered in several pathological conditions. Therefore, identifying and quantifying different erythrocyte shapes can help diagnose various diseases and assist in designing a treatment strategy. Machine Learning (ML) can be efficiently used to identify and quantify distorted erythrocyte morphologies. In this paper, we proposed a customized deep convolutional neural network (CNN) model to classify and quantify the distorted and normal morphology of erythrocytes from the images taken from the blood samples of patients suffering from Sickle cell disease ( SCD). We chose SCD as a model disease condition due to the presence of diverse erythrocyte morphologies in the blood samples of SCD patients. For the analysis, we used 428 raw microscopic images of SCD blood samples and generated the dataset consisting of 10, 377 single-cell images. We focused on three well-defined erythrocyte shapes, including discocytes, oval, and sickle. We used 18 layered deep CNN architecture to identify and quantify these shapes with 81% accuracy, outperforming other models. We also used SHAP and LIME for further interpretability. The proposed model can be helpful for the quick and accurate analysis of SCD blood samples by the clinicians and help them make the right decision for better management of SCD.

Tianyu Cui, Yogesh Kumar, Pekka Marttinen et al.

Similarity metrics such as representational similarity analysis (RSA) and centered kernel alignment (CKA) have been used to compare layer-wise representations between neural networks. However, these metrics are confounded by the population structure of data items in the input space, leading to spuriously high similarity for even completely random neural networks and inconsistent domain relations in transfer learning. We introduce a simple and generally applicable fix to adjust for the confounder with covariate adjustment regression, which retains the intuitive invariance properties of the original similarity measures. We show that deconfounding the similarity metrics increases the resolution of detecting semantically similar neural networks. Moreover, in real-world applications, deconfounding improves the consistency of representation similarities with domain similarities in transfer learning, and increases correlation with out-of-distribution accuracy.

Shaoxiong Ji, Wei Sun, Xiaobo Li et al.

Automated medical coding, an essential task for healthcare operation and delivery, makes unstructured data manageable by predicting medical codes from clinical documents. Recent advances in deep learning and natural language processing have been widely applied to this task. However, deep learning-based medical coding lacks a unified view of the design of neural network architectures. This review proposes a unified framework to provide a general understanding of the building blocks of medical coding models and summarizes recent advanced models under the proposed framework. Our unified framework decomposes medical coding into four main components, i.e., encoder modules for text feature extraction, mechanisms for building deep encoder architectures, decoder modules for transforming hidden representations into medical codes, and the usage of auxiliary information. Finally, we introduce the benchmarks and real-world usage and discuss key research challenges and future directions.

Shaoxiong Ji, Pekka Marttinen

Multitask deep learning has been applied to patient outcome prediction from text, taking clinical notes as input and training deep neural networks with a joint loss function of multiple tasks. However, the joint training scheme of multitask learning suffers from inter-task interference, and diagnosis prediction among the multiple tasks has the generalizability issue due to rare diseases or unseen diagnoses. To solve these challenges, we propose a hypernetwork-based approach that generates task-conditioned parameters and coefficients of multitask prediction heads to learn task-specific prediction and balance the multitask learning. We also incorporate semantic task information to improves the generalizability of our task-conditioned multitask model. Experiments on early and discharge notes extracted from the real-world MIMIC database show our method can achieve better performance on multitask patient outcome prediction than strong baselines in most cases. Besides, our method can effectively handle the scenario with limited information and improve zero-shot prediction on unseen diagnosis categories.

Wei Sun, Shaoxiong Ji, Erik Cambria et al.

Human coders assign standardized medical codes to clinical documents generated during patients' hospitalization, which is error-prone and labor-intensive. Automated medical coding approaches have been developed using machine learning methods such as deep neural networks. Nevertheless, automated medical coding is still challenging because of the imbalanced class problem, complex code association, and noise in lengthy documents. To solve these issues, we propose a novel neural network called Multitask Balanced and Recalibrated Neural Network. Significantly, the multitask learning scheme shares the relationship knowledge between different code branches to capture the code association. A recalibrated aggregation module is developed by cascading convolutional blocks to extract high-level semantic features that mitigate the impact of noise in documents. Also, the cascaded structure of the recalibrated module can benefit the learning from lengthy notes. To solve the class imbalanced problem, we deploy the focal loss to redistribute the attention of low and high-frequency medical codes. Experimental results show that our proposed model outperforms competitive baselines on a real-world clinical dataset MIMIC-III.

Yogesh Kumar, Alexander Ilin, Henri Salo et al.

Despite the proven effectiveness of Transformer neural networks across multiple domains, their performance with Electronic Health Records (EHR) can be nuanced. The unique, multidimensional sequential nature of EHR data can sometimes make even simple linear models with carefully engineered features more competitive. Thus, the advantages of Transformers, such as efficient transfer learning and improved scalability are not always fully exploited in EHR applications. Addressing these challenges, we introduce SANSformer, an attention-free sequential model designed with specific inductive biases to cater for the unique characteristics of EHR data. In this work, we aim to forecast the demand for healthcare services, by predicting the number of patient visits to healthcare facilities. The challenge amplifies when dealing with divergent patient subgroups, like those with rare diseases, which are characterized by unique health trajectories and are typically smaller in size. To address this, we employ a self-supervised pretraining strategy, Generative Summary Pretraining (GSP), which predicts future summary statistics based on past health records of a patient. Our models are pretrained on a health registry of nearly one million patients, then fine-tuned for specific subgroup prediction tasks, showcasing the potential to handle the multifaceted nature of EHR data. In evaluation, SANSformer consistently surpasses robust EHR baselines, with our GSP pretraining method notably amplifying model performance, particularly within smaller patient subgroups. Our results illuminate the promising potential of tailored attention-free models and self-supervised pretraining in refining healthcare utilization predictions across various patient demographics.

Lang He, Mingyue Niu, Prayag Tiwari et al.

With the acceleration of the pace of work and life, people have to face more and more pressure, which increases the possibility of suffering from depression. However, many patients may fail to get a timely diagnosis due to the serious imbalance in the doctor-patient ratio in the world. Promisingly, physiological and psychological studies have indicated some differences in speech and facial expression between patients with depression and healthy individuals. Consequently, to improve current medical care, many scholars have used deep learning to extract a representation of depression cues in audio and video for automatic depression detection. To sort out and summarize these works, this review introduces the databases and describes objective markers for automatic depression estimation (ADE). Furthermore, we review the deep learning methods for automatic depression detection to extract the representation of depression from audio and video. Finally, this paper discusses challenges and promising directions related to automatic diagnosing of depression using deep learning technologies.

Wei Sun, Shaoxiong Ji, Erik Cambria et al.

Medical coding translates professionally written medical reports into standardized codes, which is an essential part of medical information systems and health insurance reimbursement. Manual coding by trained human coders is time-consuming and error-prone. Thus, automated coding algorithms have been developed, building especially on the recent advances in machine learning and deep neural networks. To solve the challenges of encoding lengthy and noisy clinical documents and capturing code associations, we propose a multitask recalibrated aggregation network. In particular, multitask learning shares information across different coding schemes and captures the dependencies between different medical codes. Feature recalibration and aggregation in shared modules enhance representation learning for lengthy notes. Experiments with a real-world MIMIC-III dataset show significantly improved predictive performance.

Shaoxiong Ji, Matti Hölttä, Pekka Marttinen

Unsupervised pretraining is an integral part of many natural language processing systems, and transfer learning with language models has achieved remarkable results in many downstream tasks. In the clinical application of medical code assignment, diagnosis and procedure codes are inferred from lengthy clinical notes such as hospital discharge summaries. However, it is not clear if pretrained models are useful for medical code prediction without further architecture engineering. This paper conducts a comprehensive quantitative analysis of various contextualized language models' performance, pretrained in different domains, for medical code assignment from clinical notes. We propose a hierarchical fine-tuning architecture to capture interactions between distant words and adopt label-wise attention to exploit label information. Contrary to current trends, we demonstrate that a carefully trained classical CNN outperforms attention-based models on a MIMIC-III subset with frequent codes. Our empirical findings suggest directions for improving the medical code assignment application.

Severi Rissanen, Pekka Marttinen

Using deep latent variable models in causal inference has attracted considerable interest recently, but an essential open question is their ability to yield consistent causal estimates. While they have demonstrated promising results and theory exists on some simple model formulations, we also know that causal effects are not even identifiable in general with latent variables. We investigate this gap between theory and empirical results with analytical considerations and extensive experiments under multiple synthetic and real-world data sets, using the causal effect variational autoencoder (CEVAE) as a case study. While CEVAE seems to work reliably under some simple scenarios, it does not estimate the causal effect correctly with a misspecified latent variable or a complex data distribution, as opposed to its original motivation. Hence, our results show that more attention should be paid to ensuring the correctness of causal estimates with deep latent variable models.

Shaoxiong Ji, Shirui Pan, Pekka Marttinen

Medical code assignment from clinical text is a fundamental task in clinical information system management. As medical notes are typically lengthy and the medical coding system's code space is large, this task is a long-standing challenge. Recent work applies deep neural network models to encode the medical notes and assign medical codes to clinical documents. However, these methods are still ineffective as they do not fully encode and capture the lengthy and rich semantic information of medical notes nor explicitly exploit the interactions between the notes and codes. We propose a novel method, gated convolutional neural networks, and a note-code interaction (GatedCNN-NCI), for automatic medical code assignment to overcome these challenges. Our methods capture the rich semantic information of the lengthy clinical text for better representation by utilizing embedding injection and gated information propagation in the medical note encoding module. With a novel note-code interaction design and a graph message passing mechanism, we explicitly capture the underlying dependency between notes and codes, enabling effective code prediction. A weight sharing scheme is further designed to decrease the number of trainable parameters. Empirical experiments on real-world clinical datasets show that our proposed model outperforms state-of-the-art models in most cases, and our model size is on par with light-weighted baselines.

Shaoxiong Ji, Erik Cambria, Pekka Marttinen

Medical code assignment, which predicts medical codes from clinical texts, is a fundamental task of intelligent medical information systems. The emergence of deep models in natural language processing has boosted the development of automatic assignment methods. However, recent advanced neural architectures with flat convolutions or multi-channel feature concatenation ignore the sequential causal constraint within a text sequence and may not learn meaningful clinical text representations, especially for lengthy clinical notes with long-term sequential dependency. This paper proposes a Dilated Convolutional Attention Network (DCAN), integrating dilated convolutions, residual connections, and label attention, for medical code assignment. It adopts dilated convolutions to capture complex medical patterns with a receptive field which increases exponentially with dilation size. Experiments on a real-world clinical dataset empirically show that our model improves the state of the art.

Tianyu Cui, Aki Havulinna, Pekka Marttinen et al.

Encoding domain knowledge into the prior over the high-dimensional weight space of a neural network is challenging but essential in applications with limited data and weak signals. Two types of domain knowledge are commonly available in scientific applications: 1. feature sparsity (fraction of features deemed relevant); 2. signal-to-noise ratio, quantified, for instance, as the proportion of variance explained (PVE). We show how to encode both types of domain knowledge into the widely used Gaussian scale mixture priors with Automatic Relevance Determination. Specifically, we propose a new joint prior over the local (i.e., feature-specific) scale parameters that encodes knowledge about feature sparsity, and a Stein gradient optimization to tune the hyperparameters in such a way that the distribution induced on the model's PVE matches the prior distribution. We show empirically that the new prior improves prediction accuracy, compared to existing neural network priors, on several publicly available datasets and in a genetics application where signals are weak and sparse, often outperforming even computationally intensive cross-validation for hyperparameter tuning.

Marko Järvenpää, Aki Vehtari, Pekka Marttinen

The computational efficiency of approximate Bayesian computation (ABC) has been improved by using surrogate models such as Gaussian processes (GP). In one such promising framework the discrepancy between the simulated and observed data is modelled with a GP which is further used to form a model-based estimator for the intractable posterior. In this article we improve this approach in several ways. We develop batch-sequential Bayesian experimental design strategies to parallellise the expensive simulations. In earlier work only sequential strategies have been used. Current surrogate-based ABC methods also do not fully account the uncertainty due to the limited budget of simulations as they output only a point estimate of the ABC posterior. We propose a numerical method to fully quantify the uncertainty in, for example, ABC posterior moments. We also provide some new analysis on the GP modelling assumptions in the resulting improved framework called Bayesian ABC and discuss its connection to Bayesian quadrature (BQ) and Bayesian optimisation (BO). Experiments with toy and real-world simulation models demonstrate advantages of the proposed techniques.