47 citations · 171 across the 19 of their papers we have counts for
19 papers
Language Agents Meet Causality -- Bridging LLMs and Causal World Models
John Gkountouras, Matthias Lindemann, Phillip Lippe +2
Large Language Models (LLMs) have recently shown great promise in planning and reasoning applications. These tasks demand robust systems, which arguably require a causal understand…
NARAIM: Native Aspect Ratio Autoregressive Image Models
Daniel Gallo Fernández, Robert van der Klis, Răzvan-Andrei Matişan +4
While vision transformers are able to solve a wide variety of computer vision tasks, no pre-training method has yet demonstrated the same scaling laws as observed in language model…
Towards the Reusability and Compositionality of Causal Representations
Davide Talon, Phillip Lippe, Stuart James +2
Causal Representation Learning (CRL) aims at identifying high-level causal factors and their relationships from high-dimensional observations, e.g., images. While most CRL works fo…
How to Train Neural Field Representations: A Comprehensive Study and Benchmark
Samuele Papa, Riccardo Valperga, David Knigge +4
Neural fields (NeFs) have recently emerged as a versatile method for modeling signals of various modalities, including images, shapes, and scenes. Subsequently, a number of works h…
PDE-Refiner: Achieving Accurate Long Rollouts with Neural PDE Solvers
Phillip Lippe, Bastiaan S. Veeling, Paris Perdikaris +2
Time-dependent partial differential equations (PDEs) are ubiquitous in science and engineering. Recently, mostly due to the high computational cost of traditional solution techniqu…
BISCUIT: Causal Representation Learning from Binary Interactions
Phillip Lippe, Sara Magliacane, Sindy Löwe +3
Identifying the causal variables of an environment and how to intervene on them is of core value in applications such as robotics and embodied AI. While an agent can commonly inter…
Rotating Features for Object Discovery
Sindy Löwe, Phillip Lippe, Francesco Locatello +1
The binding problem in human cognition, concerning how the brain represents and connects objects within a fixed network of neural connections, remains a subject of intense debate.…
Mesh Neural Networks for SE(3)-Equivariant Hemodynamics Estimation on the Artery Wall
Julian Suk, Pim de Haan, Phillip Lippe +2
Computational fluid dynamics (CFD) is a valuable asset for patient-specific cardiovascular-disease diagnosis and prognosis, but its high computational demands hamper its adoption i…
Differentiable Mathematical Programming for Object-Centric Representation Learning
Adeel Pervez, Phillip Lippe, Efstratios Gavves
We propose topology-aware feature partitioning into disjoint partitions for given scene features as a method for object-centric representation learning. To this end, we propose…
Causal Representation Learning for Instantaneous and Temporal Effects in Interactive Systems
Phillip Lippe, Sara Magliacane, Sindy Löwe +3
Causal representation learning is the task of identifying the underlying causal variables and their relations from high-dimensional observations, such as images. Recent work has sh…
Complex-Valued Autoencoders for Object Discovery
Sindy Löwe, Phillip Lippe, Maja Rudolph +1
Object-centric representations form the basis of human perception, and enable us to reason about the world and to systematically generalize to new settings. Currently, most works o…
Weakly supervised causal representation learning
Johann Brehmer, Pim de Haan, Phillip Lippe +1
Learning high-level causal representations together with a causal model from unstructured low-level data such as pixels is impossible from observational data alone. We prove under…
CITRIS: Causal Identifiability from Temporal Intervened Sequences
Phillip Lippe, Sara Magliacane, Sindy Löwe +3
Understanding the latent causal factors of a dynamical system from visual observations is considered a crucial step towards agents reasoning in complex environments. In this paper,…
Mesh convolutional neural networks for wall shear stress estimation in 3D artery models
Julian Suk, Pim de Haan, Phillip Lippe +2
Computational fluid dynamics (CFD) is a valuable tool for personalised, non-invasive evaluation of hemodynamics in arteries, but its complexity and time-consuming nature prohibit l…
Efficient Neural Causal Discovery without Acyclicity Constraints
Phillip Lippe, Taco Cohen, Efstratios Gavves
Learning the structure of a causal graphical model using both observational and interventional data is a fundamental problem in many scientific fields. A promising direction is con…
Meta-Learning for Fast Cross-Lingual Adaptation in Dependency Parsing
Anna Langedijk, Verna Dankers, Phillip Lippe +4
Meta-learning, or learning to learn, is a technique that can help to overcome resource scarcity in cross-lingual NLP problems, by enabling fast adaptation to new tasks. We apply mo…
A Multimodal Framework for the Detection of Hateful Memes
Phillip Lippe, Nithin Holla, Shantanu Chandra +4
An increasingly common expression of online hate speech is multimodal in nature and comes in the form of memes. Designing systems to automatically detect hateful content is of para…
Diversifying Task-oriented Dialogue Response Generation with Prototype Guided Paraphrasing
Phillip Lippe, Pengjie Ren, Hinda Haned +2
Existing methods for Dialogue Response Generation (DRG) in Task-oriented Dialogue Systems (TDSs) can be grouped into two categories: template-based and corpus-based. The former pre…
Categorical Normalizing Flows via Continuous Transformations
Phillip Lippe, Efstratios Gavves
Despite their popularity, to date, the application of normalizing flows on categorical data stays limited. The current practice of using dequantization to map discrete data to a co…