3 citations · 15 across the 28 of their papers we have counts for
30 papers
Think Before You Paint: Recursive Latent Reasoning for Diffusion Models
Paweł Skierś, Małgorzata Grzanka, Wojciech Masarczyk +2
Diffusion models generate realistic images but often fail on visual reasoning tasks, such as filling in a Sudoku or drawing the path through a maze. When a discrete symbolic repres…
LiFT: Loop Flow Transformers
Mohammad Mahdi Derakhshani, Pedro M. P. Curvo, Gertjan J. Burghouts +2
We introduce Loop Flow Transformers (LiFT), a family of looped generative models that scales computation by repeatedly applying a shared Diffusion Transformer (DiT) core, with only…
Follow the Mean: Reference-Guided Flow Matching
Pedro M. P. Curvo, Maksim Zhdanov, Floor Eijkelboom +1
Existing approaches to controllable generation typically rely on fine-tuning, auxiliary networks, or test-time search. We show that flow matching admits a different control interfa…
Kernel-Gradient Drifting Models
Maria Esteban-Casadevall, Jorge Carrasco-Pollo, Max Welling +3
We propose kernel-gradient drifting, a one-step generative modeling framework that replaces the fixed Euclidean displacement direction in drifting models with directions induced by…
Crystalite: A Lightweight Transformer for Efficient Crystal Modeling
Tin Hadži Veljković, Joshua Rosenthal, Ivor Lončarić +1
Generative models for crystalline materials often rely on equivariant graph neural networks, which capture geometric structure well but are costly to train and slow to sample. We p…
Pawsterior: Variational Flow Matching for Structured Simulation-Based Inference
Jorge Carrasco-Pollo, Floor Eijkelboom, Jan-Willem van de Meent
We introduce Pawsterior, a variational flow-matching framework for improved and extended simulation-based inference (SBI). Many SBI problems involve posteriors constrained by struc…
CORDS: Continuous Representations of Discrete Structures
Tin Hadži Veljković, Erik Bekkers, Michael Tiemann +1
Many learning problems require predicting sets of objects when the number of objects is not known beforehand. Examples include object detection, molecular modeling, and scientific…
Discovering Symmetry Groups with Flow Matching
Yuxuan Chen, Jung Yeon Park, Floor Eijkelboom +4
Symmetry is fundamental to understanding physical systems and can improve performance and sample efficiency in machine learning. Both pursuits require knowledge of the underlying s…
MSPT: Efficient Large-Scale Physical Modeling via Parallelized Multi-Scale Attention
Pedro M. P. Curvo, Jan-Willem van de Meent, Maksim Zhdanov
A key scalability challenge in neural solvers for industrial-scale physics simulations is efficiently capturing both fine-grained local interactions and long-range global dependenc…
Purrception: Variational Flow Matching for Vector-Quantized Image Generation
Răzvan-Andrei Matişan, Vincent Tao Hu, Grigory Bartosh +6
We introduce Purrception, a variational flow matching approach for vector-quantized image generation that provides explicit categorical supervision while maintaining continuous tra…
Controlled Generation with Equivariant Variational Flow Matching
Floor Eijkelboom, Heiko Zimmermann, Sharvaree Vadgama +4
We derive a controlled generation objective within the framework of Variational Flow Matching (VFM), which casts flow matching as a variational inference problem. We demonstrate th…
Exponential Family Variational Flow Matching for Tabular Data Generation
Andrés Guzmán-Cordero, Floor Eijkelboom, Jan-Willem van de Meent
While denoising diffusion and flow matching have driven major advances in generative modeling, their application to tabular data remains limited, despite its ubiquity in real-world…
Riemannian Variational Flow Matching for Material and Protein Design
Olga Zaghen, Floor Eijkelboom, Alison Pouplin +4
We present Riemannian Gaussian Variational Flow Matching (RG-VFM), a geometric extension of Variational Flow Matching (VFM) for generative modeling on manifolds. Motivated by the b…
On-Robot Reinforcement Learning with Goal-Contrastive Rewards
Ondrej Biza, Thomas Weng, Lingfeng Sun +6
Reinforcement Learning (RL) has the potential to enable robots to learn from their own actions in the real world. Unfortunately, RL can be prohibitively expensive, in terms of on-r…
Entropy Coding of Unordered Data Structures
Julius Kunze, Daniel Severo, Giulio Zani +2
We present shuffle coding, a general method for optimal compression of sequences of unordered objects using bits-back coding. Data structures that can be compressed using shuffle c…
Variational Flow Matching for Graph Generation
Floor Eijkelboom, Grigory Bartosh, Christian Andersson Naesseth +2
We present a formulation of flow matching as variational inference, which we refer to as variational flow matching (VFM). Based on this formulation we develop CatFlow, a flow match…
Towards Reducing Diagnostic Errors with Interpretable Risk Prediction
Denis Jered McInerney, William Dickinson, Lucy C. Flynn +4
Many diagnostic errors occur because clinicians cannot easily access relevant information in patient Electronic Health Records (EHRs). In this work we propose a method to use LLMs…
Topological Obstructions and How to Avoid Them
Babak Esmaeili, Robin Walters, Heiko Zimmermann +1
Incorporating geometric inductive biases into models can aid interpretability and generalization, but encoding to a specific geometric structure can be challenging due to the impos…
One-shot Imitation Learning via Interaction Warping
Ondrej Biza, Skye Thompson, Kishore Reddy Pagidi +7
Imitation learning of robot policies from few demonstrations is crucial in open-ended applications. We propose a new method, Interaction Warping, for learning SE(3) robotic manipul…
CHiLL: Zero-shot Custom Interpretable Feature Extraction from Clinical Notes with Large Language Models
Denis Jered McInerney, Geoffrey Young, Jan-Willem van de Meent +1
We propose CHiLL (Crafting High-Level Latents), an approach for natural-language specification of features for linear models. CHiLL prompts LLMs with expert-crafted queries to gene…
Verified Reversible Programming for Verified Lossless Compression
James Townsend, Jan-Willem van de Meent
Lossless compression implementations typically contain two programs, an encoder and a decoder, which are required to be inverse to one another. We observe that a significant class…
That's the Wrong Lung! Evaluating and Improving the Interpretability of Unsupervised Multimodal Encoders for Medical Data
Denis Jered McInerney, Geoffrey Young, Jan-Willem van de Meent +1
Pretraining multimodal models on Electronic Health Records (EHRs) provides a means of learning representations that can transfer to downstream tasks with minimal supervision. Recen…
Binding Actions to Objects in World Models
Ondrej Biza, Robert Platt, Jan-Willem van de Meent +2
We study the problem of binding actions to objects in object-factored world models using action-attention mechanisms. We propose two attention mechanisms for binding actions to obj…
Factored World Models for Zero-Shot Generalization in Robotic Manipulation
Ondrej Biza, Thomas Kipf, David Klee +3
World models for environments with many objects face a combinatorial explosion of states: as the number of objects increases, the number of possible arrangements grows exponentiall…