670 citations · 984 across the 19 of their papers we have counts for
19 papers
MANZANO: A Simple and Scalable Unified Multimodal Model with a Hybrid Vision Tokenizer
Yanghao Li, Rui Qian, Bowen Pan +24
Unified multimodal Large Language Models (LLMs) that can both understand and generate visual content hold immense potential. However, existing open-source models often suffer from…
Neural Compression of Atmospheric States
Piotr Mirowski, David Warde-Farley, Mihaela Rosca +7
Atmospheric states derived from reanalysis comprise a substantial portion of weather and climate simulation outputs. Many stakeholders -- such as researchers, policy makers, and in…
Finding Increasingly Large Extremal Graphs with AlphaZero and Tabu Search
Abbas Mehrabian, Ankit Anand, Hyunjik Kim +16
This work studies a central extremal graph theory problem inspired by a 1975 conjecture of Erdős, which aims to find graphs with a given size (number of nodes) that maximize the nu…
Spatial Functa: Scaling Functa to ImageNet Classification and Generation
Matthias Bauer, Emilien Dupont, Andy Brock +3
Neural fields, also known as implicit neural representations, have emerged as a powerful means to represent complex signals of various modalities. Based on this Dupont et al. (2022…
When Does Re-initialization Work?
Sheheryar Zaidi, Tudor Berariu, Hyunjik Kim +4
Re-initializing a neural network during training has been observed to improve generalization in recent works. Yet it is neither widely adopted in deep learning practice nor is it o…
Pre-training via Denoising for Molecular Property Prediction
Sheheryar Zaidi, Michael Schaarschmidt, James Martens +6
Many important problems involving molecular property prediction from 3D structures have limited data, posing a generalization challenge for neural networks. In this paper, we descr…
Learning Instance-Specific Augmentations by Capturing Local Invariances
Ning Miao, Tom Rainforth, Emile Mathieu +4
We introduce InstaAug, a method for automatically learning input-specific augmentations from data. Previous methods for learning augmentations have typically assumed independence b…
From data to functa: Your data point is a function and you can treat it like one
Emilien Dupont, Hyunjik Kim, S. M. Ali Eslami +2
It is common practice in deep learning to represent a measurement of the world on a discrete grid, e.g. a 2D grid of pixels. However, the underlying signal represented by these mea…
Group Equivariant Subsampling
Jin Xu, Hyunjik Kim, Tom Rainforth +1
Subsampling is used in convolutional neural networks (CNNs) in the form of pooling or strided convolutions, to reduce the spatial dimensions of feature maps and to allow the recept…
LieTransformer: Equivariant self-attention for Lie Groups
Michael Hutchinson, Charline Le Lan, Sheheryar Zaidi +3
Group equivariant neural networks are used as building blocks of group invariant neural networks, which have been shown to improve generalisation performance and data efficiency th…
Conditional Set Generation with Transformers
Adam R Kosiorek, Hyunjik Kim, Danilo J Rezende
A set is an unordered collection of unique elements--and yet many machine learning models that generate sets impose an implicit or explicit ordering. Since model performance can de…
The Lipschitz Constant of Self-Attention
Hyunjik Kim, George Papamakarios, Andriy Mnih
Lipschitz constants of neural networks have been explored in various contexts in deep learning, such as provable adversarial robustness, estimating Wasserstein distance, stabilisin…
MetaFun: Meta-Learning with Iterative Functional Updates
Jin Xu, Jean-Francois Ton, Hyunjik Kim +2
We develop a functional encoder-decoder approach to supervised meta-learning, where labeled data is encoded into an infinite-dimensional functional representation rather than a fin…
Meta-Learning surrogate models for sequential decision making
Alexandre Galashov, Jonathan Schwarz, Hyunjik Kim +5
We introduce a unified probabilistic framework for solving sequential decision making problems ranging from Bayesian optimisation to contextual bandits and reinforcement learning.…
Attentive Neural Processes
Hyunjik Kim, Andriy Mnih, Jonathan Schwarz +5
Neural Processes (NPs) (Garnelo et al 2018a;b) approach regression by learning to map a context set of observed input-output pairs to a distribution over regression functions. Each…
Sequential Attend, Infer, Repeat: Generative Modelling of Moving Objects
Adam R. Kosiorek, Hyunjik Kim, Ingmar Posner +1
We present Sequential Attend, Infer, Repeat (SQAIR), an interpretable deep generative model for videos of moving objects. It can reliably discover and track objects throughout the…
Disentangling by Factorising
Hyunjik Kim, Andriy Mnih
We define and address the problem of unsupervised learning of disentangled representations on data generated from independent factors of variation. We propose FactorVAE, a method t…
Scaling up the Automatic Statistician: Scalable Structure Discovery using Gaussian Processes
Hyunjik Kim, Yee Whye Teh
Automating statistical modelling is a challenging problem in artificial intelligence. The Automatic Statistician takes a first step in this direction, by employing a kernel search…
Collaborative Filtering with Side Information: a Gaussian Process Perspective
Hyunjik Kim, Xiaoyu Lu, Seth Flaxman +1
We tackle the problem of collaborative filtering (CF) with side information, through the lens of Gaussian Process (GP) regression. Driven by the idea of using the kernel to explici…