Search Results for author:
Found 21 papers, 9 papers with code
Stochastic natural gradient descent draws posterior samples in function space
Recent work has argued that stochastic gradient descent can approximate the Bayesian uncertainty in model parameters near local minima.
The Importance of Generation Order in Language Modeling
Neural language models are a critical component of state-of-the-art systems for machine translation, summarization, audio transcription, and other tasks.
Parallel Scheduled Sampling
Experimentally, we find the proposed technique leads to equivalent or better performance on image generation, summarization, dialog generation, and translation compared to teacher-forced training.
Taskmaster-1: Toward a Realistic and Diverse Dialog Dataset
A significant barrier to progress in data-driven approaches to building dialog systems is the lack of high quality, goal-oriented conversational data.
Neural Assistant: Joint Action Prediction, Response Generation, and Latent Knowledge Reasoning
In this paper, we develop Neural Assistant: a single neural network model that takes conversation history and an external knowledge source as input and jointly produces both text response and action to be taken by the system as output.
Automatic Detection of Generated Text is Easiest when Humans are Fooled
Recent advancements in neural language modelling make it possible to rapidly generate vast amounts of human-sounding text.
Invertible Convolutional Flow
We show that these transforms allow more effective normalizing flow models to be developed for generative image models.
Trading Off Diversity and Quality in Natural Language Generation
For open-ended language generation tasks such as storytelling and dialogue, choosing the right decoding algorithm is critical to controlling the tradeoff between generation quality and diversity.
NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collections
We present a learning-based method for synthesizing novel views of complex scenes using only unstructured collections of in-the-wild photographs.
Whitening and second order optimization both make information in the dataset unusable during training, and can reduce or prevent generalization
We show that both data whitening and second order optimization can harm or entirely prevent generalization.
Whitening and second order optimization both destroy information about the dataset, and can make generalization impossible
We show that both data whitening and second order optimization can harm or entirely prevent generalization.
Scene Representation Transformer: Geometry-Free Novel View Synthesis Through Set-Latent Scene Representations
In this work, we propose the Scene Representation Transformer (SRT), a method which processes posed or unposed RGB images of a new area, infers a "set-latent scene representation", and synthesises novel views, all in a single feed-forward pass.
NeSF: Neural Semantic Fields for Generalizable Semantic Segmentation of 3D Scenes
We present NeSF, a method for producing 3D semantic fields from posed RGB images alone.
Kubric: A scalable dataset generator
Data is the driving force of machine learning, with the amount and quality of training data often being more important for the performance of a system than architecture and training details.
Object Scene Representation Transformer
A compositional understanding of the world in terms of objects and their geometry in 3D space is considered a cornerstone of human cognition.
RUST: Latent Neural Scene Representations from Unposed Imagery
Our main insight is that one can train a Pose Encoder that peeks at the target image and learns a latent pose embedding which is used by the decoder for view synthesis.
RobustNeRF: Ignoring Distractors with Robust Losses
To cope with distractors, we advocate a form of robust estimation for NeRF training, modeling distractors in training data as outliers of an optimization problem.
PaLM-E: An Embodied Multimodal Language Model
Large language models excel at a wide range of complex tasks.
Ranked #2 on
Visual Question Answering (VQA)
on OK-VQA
RePAST: Relative Pose Attention Scene Representation Transformer
The Scene Representation Transformer (SRT) is a recent method to render novel views at interactive rates.
SMERF: Streamable Memory Efficient Radiance Fields for Real-Time Large-Scene Exploration
Recent techniques for real-time view synthesis have rapidly advanced in fidelity and speed, and modern methods are capable of rendering near-photorealistic scenes at interactive frame rates.
RadSplat: Radiance Field-Informed Gaussian Splatting for Robust Real-Time Rendering with 900+ FPS
First, we use radiance fields as a prior and supervision signal for optimizing point-based scene representations, leading to improved quality and more robust optimization.
