1k citations · 2.2k across the 22 of their papers we have counts for
8 papers · 1 filter
Improving alignment of dialogue agents via targeted human judgements
Amelia Glaese, Nat McAleese, Maja Trębacz +31
We present Sparrow, an information-seeking dialogue agent trained to be more helpful, correct, and harmless compared to prompted language model baselines. We use reinforcement lear…
Achieving Robustness in the Wild via Adversarial Mixing with Disentangled Representations
Sven Gowal, Chongli Qin, Po-Sen Huang +4
Recent research has made the surprising finding that state-of-the-art deep learning models sometimes fail to generalize to small variations of the input. Adversarial training has b…
Learning Transferable Graph Exploration
Hanjun Dai, Yujia Li, Chenglong Wang +3
This paper considers the problem of efficient exploration of unseen environments, a key challenge in AI. We propose a `learning to explore' framework where we learn a policy from a…
An Alternative Surrogate Loss for PGD-based Adversarial Testing
Sven Gowal, Jonathan Uesato, Chongli Qin +3
Adversarial testing methods based on Projected Gradient Descent (PGD) are widely used for searching norm-bounded perturbations that cause the inputs of neural networks to be miscla…
Are Labels Required for Improving Adversarial Robustness?
Jonathan Uesato, Jean-Baptiste Alayrac, Po-Sen Huang +3
Recent work has uncovered the interesting (and somewhat surprising) finding that training models to be invariant to adversarial perturbations requires substantially larger datasets…
Knowing When to Stop: Evaluation and Verification of Conformity to Output-size Specifications
Chenglong Wang, Rudy Bunel, Krishnamurthy Dvijotham +3
Models such as Sequence-to-Sequence and Image-to-Sequence are widely used in real world applications. While the ability of these neural architectures to produce variable-length out…
ReasoNet: Learning to Stop Reading in Machine Comprehension
Yelong Shen, Po-Sen Huang, Jianfeng Gao +1
Teaching a computer to read and answer general questions pertaining to a document is a challenging yet unsolved problem. In this paper, we describe a novel neural network architect…
Unsupervised Learning of Predictors from Unpaired Input-Output Samples
Jianshu Chen, Po-Sen Huang, Xiaodong He +2
Unsupervised learning is the most challenging problem in machine learning and especially in deep learning. Among many scenarios, we study an unsupervised learning problem of high e…