151 citations · 392 across the 20 of their papers we have counts for
20 papers
Lacuna: A Research Map for Machine Learning
Martin Weiss, Miles Q. Li, Alejandro H. Artiles +4
Lacuna is a research map for machine learning that uses LLMs to turn papers and scholarly metadata into markdown summaries, concept elements, research directions, and research prop…
The Alien Space of Science: Sampling Coherent but Cognitively Unavailable Research Directions
Alejandro H. Artiles, Martin Weiss, Levin Brinkmann +6
Scientific discovery is constrained not only by what is true, but by what is cognitively available to researchers. Many directions are coherent in light of the literature yet unlik…
Cultural Alien Sampler: Open-ended art generation balancing originality and coherence
Alejandro H. Artiles, Hiromu Yakura, Levin Brinkmann +6
In open-ended domains like art, autonomous agents must generate ideas that are both original and internally coherent, yet current Large Language Models (LLMs) either default to fam…
Alien Recombination: Exploring Concept Blends Beyond Human Cognitive Availability in Visual Art
Alejandro Hernandez, Levin Brinkmann, Ignacio Serna +6
While AI models have demonstrated remarkable capabilities in constrained domains like game strategy, their potential for genuine creativity in open-ended domains like art remains d…
Language Models Can Reduce Asymmetry in Information Markets
Nasim Rahaman, Martin Weiss, Manuel Wüthrich +4
This work addresses the buyer's inspection paradox for information markets. The paradox is that buyers need to access information to determine its value, while sellers need to limi…
The Expressive Leaky Memory Neuron: an Efficient and Expressive Phenomenological Neuron Model Can Solve Long-Horizon Tasks
Aaron Spieler, Nasim Rahaman, Georg Martius +2
Biological cortical neurons are remarkably sophisticated computational devices, temporally integrating their vast synaptic input over an intricate dendritic tree, subject to comple…
A General Purpose Neural Architecture for Geospatial Systems
Nasim Rahaman, Martin Weiss, Frederik Träuble +6
Geospatial Information Systems are used by researchers and Humanitarian Assistance and Disaster Response (HADR) practitioners to support a wide variety of important applications. H…
Neural Attentive Circuits
Nasim Rahaman, Martin Weiss, Francesco Locatello +5
Recent work has seen the development of general purpose neural architectures that can be trained to perform tasks across diverse data modalities. General purpose models typically m…
Discrete Key-Value Bottleneck
Frederik Träuble, Anirudh Goyal, Nasim Rahaman +4
Deep neural networks perform well on classification tasks where data streams are i.i.d. and labeled data is abundant. Challenges emerge with non-stationary training data streams su…
Dynamic Inference with Neural Interpreters
Nasim Rahaman, Muhammad Waleed Gondal, Shruti Joshi +4
Modern neural network architectures can leverage large amounts of data to generalize well within the training distribution. However, they are less capable of systematic generalizat…
Coordination Among Neural Modules Through a Shared Global Workspace
Anirudh Goyal, Aniket Didolkar, Alex Lamb +7
Deep learning has seen a movement away from representing examples with a monolithic hidden state towards a richly structured state. For example, Transformers segment by position, a…
COVI-AgentSim: an Agent-based Model for Evaluating Methods of Digital Contact Tracing
Prateek Gupta, Tegan Maharaj, Martin Weiss +26
The rapid global spread of COVID-19 has led to an unprecedented demand for effective methods to mitigate the spread of the disease, and various digital contact tracing (DCT) method…
Predicting Infectiousness for Proactive Contact Tracing
Yoshua Bengio, Prateek Gupta, Tegan Maharaj +20
The COVID-19 pandemic has spread rapidly worldwide, overwhelming manual contact tracing in many countries and resulting in widespread lockdowns for emergency containment. Large-sca…
Function Contrastive Learning of Transferable Meta-Representations
Muhammad Waleed Gondal, Shruti Joshi, Nasim Rahaman +3
Meta-learning algorithms adapt quickly to new tasks that are drawn from the same task distribution as the training tasks. The mechanism leading to fast adaptation is the conditioni…
S2RMs: Spatially Structured Recurrent Modules
Nasim Rahaman, Anirudh Goyal, Muhammad Waleed Gondal +5
Capturing the structure of a data-generating process by means of appropriate inductive biases can help in learning models that generalize well and are robust to changes in the inpu…
COVI White Paper
Hannah Alsdurf, Edmond Belliveau, Yoshua Bengio +21
The SARS-CoV-2 (Covid-19) pandemic has caused significant strain on public health institutions around the world. Contact tracing is an essential tool to change the course of the Co…
Learning the Arrow of Time
Nasim Rahaman, Steffen Wolf, Anirudh Goyal +2
We humans seem to have an innate understanding of the asymmetric progression of time, which we use to efficiently and safely perceive and manipulate our environment. Drawing inspir…
The Mutex Watershed and its Objective: Efficient, Parameter-Free Graph Partitioning
Steffen Wolf, Alberto Bailoni, Constantin Pape +4
Image partitioning, or segmentation without semantics, is the task of decomposing an image into distinct segments, or equivalently to detect closed contours. Most prior work either…
A Meta-Transfer Objective for Learning to Disentangle Causal Mechanisms
Yoshua Bengio, Tristan Deleu, Nasim Rahaman +5
We propose to meta-learn causal structures based on how fast a learner adapts to new distributions arising from sparse distributional changes, e.g. due to interventions, actions of…
On the Spectral Bias of Neural Networks
Nasim Rahaman, Aristide Baratin, Devansh Arpit +5
Neural networks are known to be a class of highly expressive functions able to fit even random input-output mappings with accuracy. In this work, we present properties of n…