Search Results for author:
Found 35 papers, 17 papers with code
Learning to encode spatial relations from natural language
Natural language processing has made significant inroads into learning the semantics of words through distributional approaches, however representations learnt via these methods fail to capture certain kinds of information implicit in the real world.
Advancing Multimodal Medical Capabilities of Gemini
Building upon Gemini's multimodal models, we develop several models within the new Med-Gemini family that inherit core capabilities of Gemini and are optimized for medical use via fine-tuning with 2D and 3D radiology, histopathology, ophthalmology, dermatology and genomic data.
Capabilities of Gemini Models in Medicine
We evaluate Med-Gemini on 14 medical benchmarks, establishing new state-of-the-art (SoTA) performance on 10 of them, and surpass the GPT-4 model family on every benchmark where a direct comparison is viable, often by a wide margin.
Ranked #1 on
Question Answering
on MedQA
(using extra training data)
Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context
In this report, we introduce the Gemini 1. 5 family of models, representing the next generation of highly compute-efficient multimodal models capable of recalling and reasoning over fine-grained information from millions of tokens of context, including multiple long documents and hours of video and audio.
Ranked #1 on
Visual Question Answering
on MM-Vet
Self-supervised video pretraining yields human-aligned visual representations
Humans learn powerful representations of objects and scenes by observing how they evolve over time.
From data to functa: Your data point is a function and you can treat it like one
A powerful continuous alternative is then to represent these measurements using an implicit neural representation, a neural function trained to output the appropriate measurement value for any input spatial location.
Multimodal Few-Shot Learning with Frozen Language Models
When trained at sufficient scale, auto-regressive language models exhibit the notable ability to learn a new language task after being prompted with just a few examples.
Ranked #11 on
Visual Question Answering (VQA)
on VQA v2 val
From Motor Control to Team Play in Simulated Humanoid Football
In a sequence of stages, players first learn to control a fully articulated body to perform realistic, human-like movements such as running and turning; they then acquire mid-level football skills such as dribbling and shooting; finally, they develop awareness of others and play as a team, bridging the gap between low-level motor control at a timescale of milliseconds, and coordinated goal-directed behaviour as a team at the timescale of tens of seconds.
Generative Art Using Neural Visual Grammars and Dual Encoders
Whilst there are perhaps only a few scientific methods, there seem to be almost as many artistic methods as there are artists.
Contrastive Training for Improved Out-of-Distribution Detection
Reliable detection of out-of-distribution (OOD) inputs is increasingly understood to be a precondition for deployment of machine learning systems.
Ranked #12 on
Out-of-Distribution Detection
on CIFAR-100 vs CIFAR-10
Out-of-Distribution Detection
Out of Distribution (OOD) Detection
PolyGen: An Autoregressive Generative Model of 3D Meshes
Polygon meshes are an efficient representation of 3D geometry, and are of central importance in computer graphics, robotics and games development.
Unsupervised Doodling and Painting with Improved SPIRAL
We investigate using reinforcement learning agents as generative models of images (extending arXiv:1804. 01118).
A Hierarchical Probabilistic U-Net for Modeling Multi-Scale Ambiguities
Medical imaging only indirectly measures the molecular identity of the tissue within each voxel, which often produces only ambiguous image evidence for target measures of interest, like semantic segmentation.
Data-Efficient Image Recognition with Contrastive Predictive Coding
Human observers can learn to recognize new categories of images from a handful of examples, yet doing so with artificial ones remains an open challenge.
Ranked #6 on
Contrastive Learning
on imagenet-1k
Consistent Jumpy Predictions for Videos and Scenes
These models typically generate future frames in an autoregressive fashion, which is slow and requires the input and output frames to be consecutive.
Meta-Learning surrogate models for sequential decision making
We introduce a unified probabilistic framework for solving sequential decision making problems ranging from Bayesian optimisation to contextual bandits and reinforcement learning.
Consistent Generative Query Networks
These models typically generate future frames in an autoregressive fashion, which is slow and requires the input and output frames to be consecutive.
Learning models for visual 3D localization with implicit mapping
We consider learning based methods for visual localization that do not require the construction of explicit maps in the form of point clouds or voxels.
Encoding Spatial Relations from Natural Language
Natural language processing has made significant inroads into learning the semantics of words through distributional approaches, however representations learnt via these methods fail to capture certain kinds of information implicit in the real world.
Conditional Neural Processes
Deep neural networks excel at function approximation, yet they are typically trained from scratch for each new function.
Neural Processes
A neural network (NN) is a parameterised function that can be tuned via gradient descent to approximate a labelled collection of data with high precision.
A Probabilistic U-Net for Segmentation of Ambiguous Images
To this end we propose a generative segmentation model based on a combination of a U-Net with a conditional variational autoencoder that is capable of efficiently producing an unlimited number of plausible hypotheses.
Generative Temporal Models with Spatial Memory for Partially Observed Environments
In model-based reinforcement learning, generative and temporal models of environments can be leveraged to boost agent performance, either by tuning the agent's representations during training or via use as part of an explicit planning mechanism.
Synthesizing Programs for Images using Reinforced Adversarial Learning
Advances in deep generative networks have led to impressive results in recent years.
Kickstarting Deep Reinforcement Learning
Our method places no constraints on the architecture of the teacher or student agents, and it regulates itself to allow the students to surpass their teachers in performance.
Machine Theory of Mind
We design a Theory of Mind neural network -- a ToMnet -- which uses meta-learning to build models of the agents it encounters, from observations of their behaviour alone.
Learning and Querying Fast Generative Models for Reinforcement Learning
A key challenge in model-based reinforcement learning (RL) is to synthesize computationally efficient and accurate environment models.
Learning Dynamic State Abstractions for Model-Based Reinforcement Learning
A key challenge in model-based reinforcement learning (RL) is to synthesize computationally efficient and accurate environment models.
Few-shot Autoregressive Density Estimation: Towards Learning to Learn Distributions
Deep autoregressive models have shown state-of-the-art performance in density estimation for natural images on large-scale datasets such as ImageNet.
Emergence of Locomotion Behaviours in Rich Environments
The reinforcement learning paradigm allows, in principle, for complex behaviours to be learned directly from simple reward signals.
Unsupervised Learning of 3D Structure from Images
A key goal of computer vision is to recover the underlying 3D structure from 2D observations of the world.
Attend, Infer, Repeat: Fast Scene Understanding with Generative Models
We present a framework for efficient inference in structured image models that explicitly reason about objects.
Kernel-Based Just-In-Time Learning for Passing Expectation Propagation Messages
We propose an efficient nonparametric strategy for learning a message operator in expectation propagation (EP), which takes as input the set of incoming messages to a factor node, and produces an outgoing message as output.
Just-In-Time Learning for Fast and Flexible Inference
Much of research in machine learning has centered around the search for inference algorithms that are both general-purpose and efficient.
Consensus Message Passing for Layered Graphical Models
Generative models provide a powerful framework for probabilistic reasoning.
