We present the SUPERB challenge at SLT 2022, which aims at learning self-supervised speech representation for better performance, generalization, and efficiency.
In this paper, we develop Glimpse Transformers (GliTr), which observe only narrow glimpses at all times, thus predicting an ongoing action and the following most informative...
We show the first non-trivial approximation factor for this problem by giving a polynomial time O(log k)-approximation algorithm for graphs with treewidth k.
In this paper, we focus on two key problems impacting deployment of distributed inference (DI) models on SC: resource allocation and cold start latency. To address the two...
We present MidasTouch, a tactile perception system for online global localization of a vision-based touch sensor sliding on an object surface.
We conduct real-world experiments where the robot is tasked to achieve a relative target angle. We show that our approach outperforms a sliding-window based MLP in a zero-shot...
We propose to use transfer learning from both pre-trained MSA language models and our own model from the first subtask. Our system ranks in the 5th and 7th best spots of the...
We show that soft-prompt based conditional text generation can be improved with simple and efficient methods that simulate modeling the discourse structure of human written text.
To address this problem, we propose Normalized Contrastive Learning (NCL) which utilizes the Sinkhorn-Knopp algorithm to compute the instance-wise biases that properly normalize...
We compare the 0-shot performance of a neural caption-based image retriever when given as input either human-produced captions or captions generated by a neural captioner.
