356 citations · 498 across the 14 of their papers we have counts for
16 papers
PaLM-E: An Embodied Multimodal Language Model
Danny Driess, Fei Xia, Mehdi S. M. Sajjadi +19
Large language models excel at a wide range of complex tasks. However, enabling general inference in the real world, e.g., for robotics problems, raises the challenge of grounding.…
RobustNeRF: Ignoring Distractors with Robust Losses
Sara Sabour, Suhani Vora, Daniel Duckworth +3
Neural radiance fields (NeRF) excel at synthesizing new views given multi-view, calibrated images of a static scene. When scenes include distractors, which are not persistent durin…
RUST: Latent Neural Scene Representations from Unposed Imagery
Mehdi S. M. Sajjadi, Aravindh Mahendran, Thomas Kipf +4
Inferring the structure of 3D scenes from 2D observations is a fundamental challenge in computer vision. Recently popularized approaches based on neural scene representations have…
Object Scene Representation Transformer
Mehdi S. M. Sajjadi, Daniel Duckworth, Aravindh Mahendran +6
A compositional understanding of the world in terms of objects and their geometry in 3D space is considered a cornerstone of human cognition. Facilitating the learning of such a re…
Kubric: A scalable dataset generator
Klaus Greff, Francois Belletti, Lucas Beyer +32
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 trainin…
NeSF: Neural Semantic Fields for Generalizable Semantic Segmentation of 3D Scenes
Suhani Vora, Noha Radwan, Klaus Greff +6
We present NeSF, a method for producing 3D semantic fields from posed RGB images alone. In place of classical 3D representations, our method builds on recent work in implicit neura…
Scene Representation Transformer: Geometry-Free Novel View Synthesis Through Set-Latent Scene Representations
Mehdi S. M. Sajjadi, Henning Meyer, Etienne Pot +10
A classical problem in computer vision is to infer a 3D scene representation from few images that can be used to render novel views at interactive rates. Previous work focuses on r…
Whitening and second order optimization both make information in the dataset unusable during training, and can reduce or prevent generalization
Neha S. Wadia, Daniel Duckworth, Samuel S. Schoenholz +2
Machine learning is predicated on the concept of generalization: a model achieving low error on a sufficiently large training set should also perform well on novel samples from the…
NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collections
Ricardo Martin-Brualla, Noha Radwan, Mehdi S. M. Sajjadi +3
We present a learning-based method for synthesizing novel views of complex scenes using only unstructured collections of in-the-wild photographs. We build on Neural Radiance Fields…
Trading Off Diversity and Quality in Natural Language Generation
Hugh Zhang, Daniel Duckworth, Daphne Ippolito +1
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…
Automatic Detection of Generated Text is Easiest when Humans are Fooled
Daphne Ippolito, Daniel Duckworth, Chris Callison-Burch +1
Recent advancements in neural language modelling make it possible to rapidly generate vast amounts of human-sounding text. The capabilities of humans and automatic discriminators t…
Neural Assistant: Joint Action Prediction, Response Generation, and Latent Knowledge Reasoning
Arvind Neelakantan, Semih Yavuz, Sharan Narang +5
Task-oriented dialog presents a difficult challenge encompassing multiple problems including multi-turn language understanding and generation, knowledge retrieval and reasoning, an…
Taskmaster-1: Toward a Realistic and Diverse Dialog Dataset
Bill Byrne, Karthik Krishnamoorthi, Chinnadhurai Sankar +7
A significant barrier to progress in data-driven approaches to building dialog systems is the lack of high quality, goal-oriented conversational data. To help satisfy this elementa…
Parallel Scheduled Sampling
Daniel Duckworth, Arvind Neelakantan, Ben Goodrich +2
Auto-regressive models are widely used in sequence generation problems. The output sequence is typically generated in a predetermined order, one discrete unit (pixel or word or cha…
The Importance of Generation Order in Language Modeling
Nicolas Ford, Daniel Duckworth, Mohammad Norouzi +1
Neural language models are a critical component of state-of-the-art systems for machine translation, summarization, audio transcription, and other tasks. These language models are…
Stochastic natural gradient descent draws posterior samples in function space
Samuel L. Smith, Daniel Duckworth, Semon Rezchikov +2
Recent work has argued that stochastic gradient descent can approximate the Bayesian uncertainty in model parameters near local minima. In this work we develop a similar correspond…