AIConfPaper
← Search

Arno Solin

44 accepted papers

2026

Cross-View Splatter: Feed-Forward View Synthesis with Georeferenced Images

Matias Turkulainen, Akshay Krishnan, Filippo Aleotti, Mohamed Sayed, Guillermo Garcia-Hernando, Juho Kannala +3
CVPR 2026

We present Cross-View Splatter, a feed-forward method that predicts pixel-aligned Gaussian splats for outdoor scenes captured at ground level and by satellite. Faithful reconstructions require good camera coverage, but ground imagery is time-consuming and hard to capture at scale for large outdoor s

Cited by 0Source ↗code ↗Scholar ↗
2026

DiVeQ: Differentiable Vector Quantization Using the Reparameterization Trick

Mohammad Hassan Vali, Tom Bäckström, Arno Solin
ICLR 2026poster

Vector quantization is common in deep models, yet its hard assignments block gradients and hinder end-to-end training. We propose DiVeQ, which treats quantization as adding an error vector that mimics the quantization distortion, keeping the forward pass hard while letting gradients flow. We also pr…

Cited by 0Source ↗code ↗Scholar ↗
2026

Efficient Reinforcement Learning by Guiding World Models with Non-Curated Data

Yi Zhao, Aidan Scannell, Wenshuai Zhao, Yuxin Hou, Tianyu Cui, Le Chen +4
ICLR 2026poster

Leveraging offline data is a promising way to improve the sample efficiency of online reinforcement learning (RL). This paper expands the pool of usable data for offline-to-online RL by leveraging abundant non-curated data that is reward-free, of mixed quality, and collected across multiple embodime…

Cited by 0Source ↗code ↗Scholar ↗
2026

Exploiting Hankel-Toeplitz Structures for Fast Computation of Kernel Precision Matrices

Frida Viset, Anton Kullberg, Frederiek Wesel, Arno Solin
ICML 2026poster

The Hilbert-space Gaussian process (HGP) approach offers a hyperparameter-independent basis function approximation for speeding up Gaussian process (GP) inference by projecting the GP onto $M$ basis functions. These properties result in a favorable data-independent $\mathcal{O}(M^3)$ computational c…

Cited by 0Source ↗Scholar ↗
2026

Post-hoc Probabilistic Vision-Language Models

Anton Baumann, Rui Li, Marcus Klasson, Santeri Mentu, Shyamgopal Karthik, Zeynep Akata +2
ICLR 2026poster

Vision-language models (VLMs), such as CLIP and SigLIP, have found remarkable success in classification, retrieval, and generative tasks. For this, VLMs deterministically map images and text descriptions to a joint latent space in which their similarity is assessed using the cosine similarity. Howev…

Cited by 0Source ↗code ↗Scholar ↗
2026

PriorGuide: Test-Time Prior Adaptation for Simulation-Based Inference

Yang Yang, Severi Rissanen, Paul Edmund Chang, Nasrulloh Ratu Bagus Satrio Loka, Daolang Huang, Arno Solin +2
ICLR 2026poster

Amortized simulator-based inference offers a powerful framework for tackling Bayesian inference in computational fields such as engineering or neuroscience, increasingly leveraging modern generative methods like diffusion models to map observed data to model parameters or future predictions. These a…

Cited by 0Source ↗Scholar ↗
2025

DeSplat: Decomposed Gaussian Splatting for Distractor-Free Rendering

Yihao Wang, Marcus Klasson, Matias Turkulainen, Shuzhe Wang, Juho Kannala, Arno Solin
CVPR 2025poster

Gaussian splatting enables fast novel view synthesis in static 3D environments. However, reconstructing real-world environments remains challenging as distractors or occluders break the multi-view consistency assumption required for accurate 3D reconstruction. Most existing methods rely on external…

Cited by 2Source ↗PDF ↗code ↗Scholar ↗
2025

Discrete Codebook World Models for Continuous Control

Aidan Scannell, Mohammadreza Nakhaeinezhadfard, Kalle Kujanpää, Yi Zhao, Kevin Sebastian Luck, Arno Solin +1
ICLR 2025poster

In reinforcement learning (RL), world models serve as internal simulators, enabling agents to predict environment dynamics and future outcomes in order to make informed decisions. While previous approaches leveraging discrete latent spaces, such as DreamerV3, have demonstrated strong performance in…

Cited by 0Source ↗PDF ↗code ↗Scholar ↗
2025

Equivariant Denoisers Cannot Copy Graphs: Align Your Graph Diffusion Models

Najwa Laabid, Severi Rissanen, Markus Heinonen, Arno Solin, Vikas Garg
ICLR 2025poster

Graph diffusion models, dominant in graph generative modeling, remain underexplored for graph-to-graph translation tasks like chemical reaction prediction. We demonstrate that standard permutation equivariant denoisers face fundamental limitations in these tasks due to their inability to break symme…

Cited by 0Source ↗PDF ↗code ↗Scholar ↗
2025

Free Hunch: Denoiser Covariance Estimation for Diffusion Models Without Extra Costs

Severi Rissanen, Markus Heinonen, Arno Solin
ICLR 2025poster

The covariance for clean data given a noisy observation is an important quantity in many training-free guided generation methods for diffusion models. Current methods require heavy test-time computation, altering the standard diffusion training process or denoiser architecture, or making heavy appro…

Cited by 0Source ↗PDF ↗Scholar ↗
2025

Progressive Tempering Sampler with Diffusion

Severi Rissanen, RuiKang OuYang, Jiajun He, Wenlin Chen, Markus Heinonen, Arno Solin +1
ICML 2025poster

Recent research has focused on designing neural samplers that amortize the process of sampling from unnormalized densities. However, despite significant advancements, they still fall short of the state-of-the-art MCMC approach, Parallel Tempering (PT), when it comes to the efficiency of target eval…

Cited by 0Source ↗PDF ↗code ↗Scholar ↗
2024

Function-space Parameterization of Neural Networks for Sequential Learning

Aidan Scannell, Riccardo Mereu, Paul Edmund Chang, Ella Tamir, Joni Pajarinen, Arno Solin
ICLR 2024poster

Sequential learning paradigms pose challenges for gradient-based deep learning due to difficulties incorporating new data and retaining prior knowledge. While Gaussian processes elegantly tackle these problems, they struggle with scalability and handling rich inputs, such as images. To address these…

Cited by 6Source ↗PDF ↗code ↗Scholar ↗
2024

Gaussian Splatting on the Move: Blur and Rolling Shutter Compensation for Natural Camera Motion

Otto Seiskari*, Jerry Ylilammi, Valtteri Kaatrasalo, Pekka Rantalankila, Matias Turkulainen, Juho Kannala +2
ECCV 2024poster

"High-quality scene reconstruction and novel view synthesis based on Gaussian Splatting (3DGS) typically require steady, high-quality photographs, often impractical to capture with handheld cameras. We present a method that adapts to camera motion and allows high-quality scene reconstruction with ha…

Cited by 16Source ↗PDF ↗code ↗Scholar ↗
2024

Physics-Informed Variational State-Space Gaussian Processes

Oliver Hamelijnck, Arno Solin, Theodoros Damoulas
NeurIPS 2024poster

Differential equations are important mechanistic models that are integral to many scientific and engineering applications. With the abundance of available data there has been a growing interest in data-driven physics-informed models. Gaussian processes (GPs) are particularly suited to this task as t…

Cited by 0Source ↗PDF ↗code ↗Scholar ↗
2024

Subtractive Mixture Models via Squaring: Representation and Learning

Lorenzo Loconte, Aleksanteri Mikulus Sladek, Stefan Mengel, Martin Trapp, Arno Solin, Nicolas Gillis +1
ICLR 2024spotlight

Mixture models are traditionally represented and learned by adding several distributions as components. Allowing mixtures to subtract probability mass or density can drastically reduce the number of components needed to model complex distributions. However, learning such subtractive mixtures while e…

Cited by 18Source ↗PDF ↗Scholar ↗
2023

Improving Hyperparameter Learning under Approximate Inference in Gaussian Process Models

Rui Li, S. T. John, Arno Solin
ICML 2023poster

Approximate inference in Gaussian process (GP) models with non-conjugate likelihoods gets entangled with the learning of the model hyperparameters. We improve hyperparameter learning in GP models and focus on the interplay between variational inference (VI) and the learning target. While VI's lower…

Cited by 5Source ↗PDF ↗code ↗Scholar ↗
2023

Memory-Based Dual Gaussian Processes for Sequential Learning

Paul Edmund Chang, Prakhar Verma, S. T. John, Arno Solin, Mohammad Emtiyaz Khan
ICML 2023oral

Sequential learning with Gaussian processes (GPs) is challenging when access to past data is limited, for example, in continual and active learning. In such cases, errors can accumulate over time due to inaccuracies in the posterior, hyperparameters, and inducing points, making accurate learning cha…

Cited by 6Source ↗PDF ↗code ↗Scholar ↗
2023

MixupE: Understanding and improving Mixup from directional derivative perspective

Yingtian Zou, Vikas Verma, Sarthak Mittal, Wai Hoh Tang, Hieu Pham, Juho Kannala +3
UAI 2023poster

Mixup is a popular data augmentation technique for training deep neural networks where additional samples are generated by linearly interpolating pairs of inputs and their labels. This technique is known to improve the generalization performance in many learning paradigms and applications. In this w…

Cited by 11Source ↗PDF ↗code ↗Scholar ↗
2022

Non-separable Spatio-temporal Graph Kernels via SPDEs

Alexander V. Nikitin, St John, Arno Solin, Samuel Kaski
AISTATS 2022poster

Gaussian processes (GPs) provide a principled and direct approach for inference and learning on graphs. However, the lack of justified graph kernels for spatio-temporal modelling has held back their use in graph problems. We leverage an explicit link between stochastic partial differential equations…

Cited by 23Source ↗PDF ↗Scholar ↗
2022

Uncertainty-Guided Source-Free Domain Adaptation

Subhankar Roy, Martin Trapp, Andrea Pilzer, Juho Kannala, Nicu Sebe, Elisa Ricci +1
ECCV 2022poster

"Source-free domain adaptation (SFDA) aims to adapt a classifier to an unlabelled target data set by only using a pre-trained source model. However, the absence of the source data and the domain shift makes the predictions on the target data unreliable. We propose quantifying the uncertainty in the…

Cited by 90Source ↗PDF ↗code ↗Scholar ↗
2021

Combining pseudo-point and state space approximations for sum-separable Gaussian Processes

Will Tebbutt, Arno Solin, Richard E. Turner
UAI 2021poster

Gaussian processes (GPs) are important probabilistic tools for inference and learning in spatio-temporal modelling problems such as those in climate science and epidemiology. However, existing GP approximations do not simultaneously support large numbers of off-the-grid spatial data-points and long…

Cited by 11Source ↗PDF ↗code ↗Scholar ↗
2021

Dual Parameterization of Sparse Variational Gaussian Processes

Vincent ADAM, Paul Edmund Chang, Mohammad Emtiyaz Khan, Arno Solin
NeurIPS 2021poster

Sparse variational Gaussian process (SVGP) methods are a common choice for non-conjugate Gaussian process inference because of their computational benefits. In this paper, we improve their computational efficiency by using a dual parameterization where each data example is assigned dual parameters,…

Cited by 30Source ↗PDF ↗code ↗Scholar ↗
2021

Scalable Inference in SDEs by Direct Matching of the Fokker–Planck–Kolmogorov Equation

Arno Solin, Ella Maija Tamir, Prakhar Verma
NeurIPS 2021poster

Simulation-based techniques such as variants of stochastic Runge–Kutta are the de facto approach for inference with stochastic differential equations (SDEs) in machine learning. These methods are general-purpose and used with parametric and non-parametric models, and neural SDEs. Stochastic Runge–Ku…

Cited by 23Source ↗PDF ↗code ↗Scholar ↗
2021

Spatio-Temporal Variational Gaussian Processes

Oliver Hamelijnck, William J. Wilkinson, Niki Andreas Loppi, Arno Solin, Theo Damoulas
NeurIPS 2021poster

We introduce a scalable approach to Gaussian process inference that combines spatio-temporal filtering with natural gradient variational inference, resulting in a non-conjugate GP method for multivariate data that scales linearly with respect to time. Our natural gradient approach enables applicatio…

Cited by 43Source ↗PDF ↗code ↗Scholar ↗
2020

Scalable Exact Inference in Multi-Output Gaussian Processes

Wessel Bruinsma, Eric Perim, William Tebbutt, Scott Hosking, Arno Solin, Richard Turner
ICML 2020poster

Multi-output Gaussian processes (MOGPs) leverage the flexibility and interpretability of GPs while capturing structure across outputs, which is desirable, for example, in spatio-temporal modelling. The key problem with MOGPs is their computational scaling $O(n^3 p^3)$, which is cubic in the number o…

Cited by 44Source ↗PDF ↗code ↗Scholar ↗
2020

State Space Expectation Propagation: Efficient Inference Schemes for Temporal Gaussian Processes

William Wilkinson, Paul Chang, Michael Andersen, Arno Solin
ICML 2020poster

We formulate approximate Bayesian inference in non-conjugate temporal and spatio-temporal Gaussian process models as a simple parameter update rule applied during Kalman smoothing. This viewpoint encompasses most inference schemes, including expectation propagation (EP), the classical (Extended, Uns…

Cited by 19Source ↗PDF ↗code ↗Scholar ↗
2020

Stationary Activations for Uncertainty Calibration in Deep Learning

Lassi Meronen, Christabella Irwanto, Arno Solin
NeurIPS 2020poster

We introduce a new family of non-linear neural network activation functions that mimic the properties induced by the widely-used Mat\'ern family of kernels in Gaussian process (GP) models. This class spans a range of locally stationary models of various degrees of mean-square differentiability. We…

Cited by 27Source ↗PDF ↗code ↗Scholar ↗
2019

End-to-End Probabilistic Inference for Nonstationary Audio Analysis

William Wilkinson, Michael Andersen, Joshua D. Reiss, Dan Stowell, Arno Solin
ICML 2019oral

A typical audio signal processing pipeline includes multiple disjoint analysis stages, including calculation of a time-frequency representation followed by spectrogram-based feature analysis. We show how time-frequency analysis and nonnegative matrix factorisation can be jointly formulated as a spec…

Cited by 10Source ↗PDF ↗Scholar ↗
2019

Know Your Boundaries: Constraining Gaussian Processes by Variational Harmonic Features

Arno Solin, Manon Kok
AISTATS 2019poster

Gaussian processes (GPs) provide a powerful framework for extrapolation, interpolation, and noise removal in regression and classification. This paper considers constraining GPs to arbitrarily-shaped domains with boundary conditions. We solve a Fourier-like generalised harmonic feature representatio…

Cited by 50Source ↗PDF ↗code ↗Scholar ↗
2019

Unifying Probabilistic Models for Time-frequency Analysis

William J. Wilkinson, Michael Riis Andersen, Joshua D. Reiss, Dan Stowell, Arno Solin
ICASSP 2019accepted

In audio signal processing, probabilistic time-frequency models have many benefits over their non-probabilistic counterparts. They adapt to the incoming signal, quantify uncertainty, and measure correlation between the signal’s amplitude and phase information, making time domain resynthesis straight…

Cited by 0Source ↗Scholar ↗
2018

ADVIO: An Authentic Dataset for Visual-Inertial Odometry

Santiago Cortes, Arno Solin, Esa Rahtu, Juho Kannala
ECCV 2018poster

The lack of realistic and open benchmarking datasets for pedestrian visual-inertial odometry has made it hard to pinpoint differences in published methods. Existing datasets either lack a full six degree-of-freedom ground-truth or are limited to small spaces with optical tracking systems. We take ad…

Cited by 123Source ↗PDF ↗code ↗Scholar ↗
2016

Computationally Efficient Bayesian Learning of Gaussian Process State Space Models

Andreas Svensson, Arno Solin, Simo Särkkä, Thomas Schön
AISTATS 2016poster

Gaussian processes allow for flexible specification of prior assumptions of unknown dynamics in state space models. We present a procedure for efficient Bayesian learning in Gaussian process state space models, where the representation is formed by projecting the problem onto a set of approximate ei…

Cited by 68Source ↗PDF ↗Scholar ↗