2 citations · 3 across the 14 of their papers we have counts for
14 papers
Stochasticity in Tokenisation Improves Robustness
Sophie Steger, Rui Li, Sofiane Ennadir +4
The widespread adoption of large language models (LLMs) has increased concerns about their robustness. Vulnerabilities in perturbations of tokenisation of the input indicate that m…
Softly Constrained Denoisers for Diffusion Models Applied to Partial Differential Equations
Victor M. Yeom-Song, Severi Rissanen, Arno Solin +2
Diffusion models have become a powerful generative prior for solutions of partial differential equations (PDEs). Existing approaches enforce physical constraints either by adding t…
Smol-GS: Compact Representations for Abstract 3D Gaussian Splatting
Haishan Wang, Mohammad Hassan Vali, Arno Solin
We present Smol-GS, a novel method for learning compact representations for 3D Gaussian Splatting (3DGS). Our approach learns highly efficient splat-wise features to model 3D space…
Self-Attention Decomposition For Training Free Diffusion Editing
Tharun Anand, Mohammad Hassan Vali, Arno Solin +2
Diffusion models achieve remarkable fidelity in image synthesis, yet precise control over their outputs for targeted editing remains challenging. A key step toward controllability…
PriorGuide: Test-Time Prior Adaptation for Simulation-Based Inference
Yang Yang, Severi Rissanen, Paul E. Chang +5
Amortized simulator-based inference offers a powerful framework for tackling Bayesian inference in computational fields such as engineering or neuroscience, increasingly leveraging…
DiVeQ: Differentiable Vector Quantization Using the Reparameterization Trick
Mohammad Hassan Vali, Tom Bäckström, Arno Solin
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 erro…
Distant Object Localisation from Noisy Image Segmentation Sequences
Julius Pesonen, Arno Solin, Eija Honkavaara
3D object localisation based on a sequence of camera measurements is essential for safety-critical surveillance tasks, such as drone-based wildfire monitoring. Localisation of obje…
Progressive Tempering Sampler with Diffusion
Severi Rissanen, RuiKang OuYang, Jiajun He +4
Recent research has focused on designing neural samplers that amortize the process of sampling from unnormalized densities. However, despite significant advancements, they still fa…
Heterophily-informed Message Passing
Haishan Wang, Arno Solin, Vikas Garg
Graph neural networks (GNNs) are known to be vulnerable to oversmoothing due to their implicit homophily assumption. We mitigate this problem with a novel scheme that regulates the…
Compressing 3D Gaussian Splatting by Noise-Substituted Vector Quantization
Haishan Wang, Mohammad Hassan Vali, Arno Solin
3D Gaussian Splatting (3DGS) has demonstrated remarkable effectiveness in 3D reconstruction, achieving high-quality results with real-time radiance field rendering. However, a key…
Free Hunch: Denoiser Covariance Estimation for Diffusion Models Without Extra Costs
Severi Rissanen, Markus Heinonen, Arno Solin
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…
Exploiting Hankel-Toeplitz Structures for Fast Computation of Kernel Precision Matrices
Frida Viset, Anton Kullberg, Frederiek Wesel +1
The Hilbert-space Gaussian Process (HGP) approach offers a hyperparameter-independent basis function approximation for speeding up Gaussian Process (GP) inference by projecting the…
Improving Discrete Diffusion Models via Structured Preferential Generation
Severi Rissanen, Markus Heinonen, Arno Solin
In the domains of image and audio, diffusion models have shown impressive performance. However, their application to discrete data types, such as language, has often been suboptima…
Equivariant Denoisers Cannot Copy Graphs: Align Your Graph Diffusion Models
Najwa Laabid, Severi Rissanen, Markus Heinonen +2
Graph diffusion models, dominant in graph generative modeling, remain underexplored for graph-to-graph translation tasks like chemical reaction prediction. We demonstrate that stan…