FCAI Community Event and NeurIPS 2024

One hundred and sixty members of the FCAI community gathered at Saha on the Aalto University campus on November 18 to share recent work, discuss a renewal of FCAI Teams and celebrate the submissions that are heading to NeurIPS — links to those are below. Here are a few photos from the event, which was also part of the Pre-NeurIPS Fest held throughout the ELLIS network.

Below are links to the papers from Finland that will be presented at NeurIPS, 10-15 December 2024. NeurIPS is a major forum for leading research in machine learning and computational sciences.

• ACE: Abstractions for Communicating Efficiently – Jonathan D. Thomas, Andrea Silvi, Devdatt Dubhashi, Vikas Garg, Moa Johansson

• Adaptation of Kruskal’s Uniqueness Conditions to multiview CP – Suleiman Khan, Muhammad Khan

• Algebraic Positional Encodings – Konstantinos Kogkalidis, Jean-Philippe Bernardy, Vikas Garg (Poster Session 1 East)

• Amortized Bayesian Experimental Design for Decision-Making – Daolang Huang, Yujia Guo, Luigi Acerbi, Samuel Kaski (Poster Session 5 East)

• Amortized Bayesian Workflow – Marvin Schmitt, Chengkun Li, Aki Vehtari, Luigi Acerbi, Paul-Christian Bürkner, Stefan T. Radev

• Applying Guidance in a Limited Interval Improves Sample and Distribution Quality in Diffusion Models  – Tuomas Kynkäänniemi, Miika Aittala, Tero Karras, Samuli Laine, Timo Aila, Jaakko Lehtinen

• Bayesian Optimization over Bounded Domains with Beta Product Kernels – Huy Hoang Nguyen, Han Zhou, Matthew Blaschko, Aleksei Tiulpin 

• Bayesian Similarity-Weighted Aggregation for Federated Brain Tumor Segmentation – Muhammad Khan, Suleiman Khan, Elina Kontio, Mojtaba Jafaritadi

• Can neural operators always be continuously discretized? – Takashi Furuya, Michael Puthawala, Matti Lassas, Maarten V. de Hoop (Poster Session 2 East)

• Compositional PAC-Bayes: Generalization of GNNs with persistence and beyond – Kirill Brilliantov, Amauri Souza, Vikas Garg (Poster Session 6 West)

• Computation-Aware Robust Gaussian Processes – Marshal Sinaga, Julien Martinelli, Samuel Kaski

• Differentially Private Continual Learning using Pre-Trained Models – Marlon Tobaben, Marcus Klasson, Rui Li, Arno Solin, Antti Honkela

• Diffusion Twigs with Loop Guidance for Conditional Graph Generation – Giangiacomo Mercatali, Yogesh Verma, Andre Freitas, Vikas Garg – (Poster Session 5 East)

• Diversity Progress for Goal Selection in Discriminability-Motivated RL – Erik M. Lintunen, Nadia Ady, Christian Guckelsberger

• Generating Code World Models with Large Language Models Guided by Monte Carlo Tree Search – Nicola Dainese, Matteo Merler, Minttu Alakuijala, Pekka Marttinen (Poster Session 4 West)

• Guiding a Diffusion Model with a Bad Version of Itself – Tero Karras, Miika Aittala, Tuomas Kynkäänniemi, Jaakko Lehtinen, Timo Aila, Samuli Laine (Oral Session 4B: Diffusion-based Models, Poster Session 4 East; * Runner Up for Best Paper Award)

• Human-Aided Discovery of Ancestral Graphs – Tiago Silva, Eliezer de Souza da Silva, Antonio Gois, Dominik Heider, Samuel Kaski, Diego Mesquita, Adele Ribeiro

• Improving robustness to corruptions with multiplicative weight perturbations – Quoc Trung Trinh, Markus Heinonen, Luigi Acerbi, Samuel Kaski (Poster Session 1 East)

• Kernel Language Entropy: Fine-grained Uncertainty Quantification for LLMs from Semantic Similarities – Alexander Nikitin, Jannik Kossen, Yarin Gal, Pekka Marttinen (Poster Session 5 East)

• Learning Structure-Aware Representations of Dependent Types – Konstantinos Kogkalidis, Orestis Melkonian, Jean-Philippe Bernardy (Poster Session 2 East)

• Logical characterizations of recurrent graph neural networks with reals and floats – Veeti Ahvonen, Damian Heiman, Antti Kuusisto, Carsten Lutz (Poster Session 1 East)

• LoRANN: Low-Rank Matrix Factorization for Approximate Nearest Neighbor Search – Elias Jääsaari, Ville Hyvönen, Teemu Roos  (Poster Session 1 East)

• MassSpecGym: A benchmark for the discovery and identification of molecules – Roman Bushuiev, Anton Bushuiev, Niek de Jonge, Adamo Young, Fleming Kretschmer, Raman Samusevich, Janne Heirman, Fei Wang, Luke Zhang, Kai Dührkop, Marcus Ludwig, Nils Haupt, Apurva Kalia, Corinna Brungs, Robin Schmid, Russell Greiner, Bo Wang, David Wishart, Liping Liu, Juho Rousu, Wout Bittremieux, Hannes Rost, Tytus Mak, Soha Hassoun, Florian Huber, Justin J.J. van der Hooft, Michael Stravs, Sebastian Böcker, Josef Sivic, Tomáš Pluskal (Poster Session 6 West)

• NanoBaseLib: A Multi-Task Benchmark Dataset for Nanopore Sequencing – Guangzhao Cheng, Chengbo Fu, Lu Cheng (Poster Session 6 East)

• Navigating Extremes: Dynamic Sparsity in Large Output Spaces – Nasibullah Nasibullah, Erik Schultheis, Michael Lasby, Yani Ioannou, Rohit Babbar (Poster Session 6 East)

• Noise-Aware Differentially Private Regression via Meta-Learning – Ossi Räisä, Stratis Markou, Matthew Ashman, Wessel Bruinsma, Marlon Tobaben, Antti Honkela, Richard Turner (Poster Session 3 West)

• Non-geodesically-convex optimization in the Wasserstein space – Hoang Phuc Hau Luu, Hanlin Yu, Bernardo Williams, Petrus Mikkola, Marcelo Hartmann, Kai Puolamäki, Arto Klami (Poster Session 6 West)

• Physics-Informed Variational State-Space Gaussian Processes – Oliver Hamelijnck, Arno Solin, Theodoros Damoulas  (Poster Session 1 East)

• Posterior Inferred, Now What? Streamlining Prediction in Bayesian Deep Learning – Rui Li, Marcus Klasson, Arno Solin, Martin Trapp

• Preference Learning of Latent Decision Utilities with a Human-like Model of Preferential Choice – Sebastiaan De Peuter, Shibei Zhu, Yujia Guo, Andrew Howes, Samuel Kaski (Poster Session 1 West)

• Preferential Normalizing Flows – Petrus Mikkola, Luigi Acerbi, Arto Klami (Poster Session 1 East)

• Probabilistic Active Few-Shot Learning in Vision-Language Models – Anton Baumann, Marcus Klasson,  Rui Li,  Arno Solin,  Martin Trapp

• Recursive Decomposition with Dependencies for Generic Divide-and-Conquer Reasoning – Sergio Hernández-Gutiérrez, Minttu Alakuijala, Alexander Nikitin, Pekka Marttinen

• Recursive Nested Filtering for Efficient Amortized Bayesian Experimental Design – Sahel Mohammad Iqbal, Hany Abdulsamad, Sara Perez-Vieites, Simo Sarkka, Adrien Corenflos

• Regional Ocean Forecasting with Hierarchical Graph Neural Networks – Daniel Holmberg, Emanuela Clementi, Teemu Roos

• SARDet-100K: Towards Open-Source Benchmark and ToolKit for Large-Scale SAR Object Detection – Yuxuan Li, Xiang Li, Weijie Li, Qibin Hou, Li Liu, Ming-Ming Cheng, Jian Yang (Poster Session 3 East)

• TSGM: A Flexible Framework for Generative Modeling of Synthetic Time Series – Alexander Nikitin, Letizia Iannucci, Samuel Kaski  (Poster Session 5 East)

• What do Graph Neural Networks learn? Insights from Tropical Geometry – Tuan Anh Pham, Vikas Garg (Poster Session 1 East)