Search Results for author:
Found 15 papers, 9 papers with code
PaLM 2 Technical Report
Through extensive evaluations on English and multilingual language, and reasoning tasks, we demonstrate that PaLM 2 has significantly improved quality on downstream tasks across different model sizes, while simultaneously exhibiting faster and more efficient inference compared to PaLM.
Ranked #1 on
Question Answering
on TriviaQA
(using extra training data)
N-Grammer: Augmenting Transformers with latent n-grams
Transformer models have recently emerged as one of the foundational models in natural language processing, and as a byproduct, there is significant recent interest and investment in scaling these models.
Ranked #5 on
Language Modelling
on C4
Hurdles to Progress in Long-form Question Answering
The task of long-form question answering (LFQA) involves retrieving documents relevant to a given question and using them to generate a paragraph-length answer.
Ranked #3 on
Question Answering
on KILT: ELI5
Efficient Content-Based Sparse Attention with Routing Transformers
This work builds upon two lines of research: it combines the modeling flexibility of prior work on content-based sparse attention with the efficiency gains from approaches based on local, temporal sparse attention.
Ranked #5 on
Image Generation
on ImageNet 64x64
(Bits per dim metric)
Unsupervised Paraphrasing without Translation
We compare with MT-based approaches on paraphrase identification, generation, and training augmentation.
Towards a better understanding of Vector Quantized Autoencoders
Deep neural networks with discrete latent variables offer the promise of better symbolic reasoning, and learning abstractions that are more useful to new tasks.
Understanding and Improving Interpolation in Autoencoders via an Adversarial Regularizer
Autoencoders provide a powerful framework for learning compressed representations by encoding all of the information needed to reconstruct a data point in a latent code.
Theory and Experiments on Vector Quantized Autoencoders
Deep neural networks with discrete latent variables offer the promise of better symbolic reasoning, and learning abstractions that are more useful to new tasks.
Fast Decoding in Sequence Models using Discrete Latent Variables
Finally, we evaluate our model end-to-end on the task of neural machine translation, where it is an order of magnitude faster at decoding than comparable autoregressive models.
Thermometer Encoding: One Hot Way To Resist Adversarial Examples
It is well known that it is possible to construct "adversarial examples" for neural networks: inputs which are misclassified by the network yet indistinguishable from true data.
Adversarial Patch
We present a method to create universal, robust, targeted adversarial image patches in the real world.
Reinforcement Learning under Model Mismatch
We study reinforcement learning under model misspecification, where we do not have access to the true environment but only to a reasonably close approximation to it.
Learning to Remember Rare Events
We present a large-scale life-long memory module for use in deep learning.
Hierarchical Clustering via Spreading Metrics
We also prove that our algorithm returns an $O(\log{n})$-approximate hierarchical clustering for a generalization of this cost function also studied in [arXiv:1510. 05043].
Technical Report on the CleverHans v2.1.0 Adversarial Examples Library
An adversarial example library for constructing attacks, building defenses, and benchmarking both
