Search Results for author:
Found 5 papers, 1 papers with code
Zipper: A Multi-Tower Decoder Architecture for Fusing Modalities
In cross-modal tasks such as text-to-speech generation (TTS) where the output modality is speech, we show that using a pre-trained speech backbone results in superior performance to the baseline.
LLMs cannot find reasoning errors, but can correct them!
While self-correction has shown promise in improving LLM outputs in terms of style and quality (e. g. Chen et al., 2023; Madaan et al., 2023), recent attempts to self-correct logical or reasoning errors often cause correct answers to become incorrect, resulting in worse performances overall (Huang et al., 2023).
AudioPaLM: A Large Language Model That Can Speak and Listen
AudioPaLM inherits the capability to preserve paralinguistic information such as speaker identity and intonation from AudioLM and the linguistic knowledge present only in text large language models such as PaLM-2.
The Importance of Sampling inMeta-Reinforcement Learning
Results are presented on a new environment we call `Krazy World': a difficult high-dimensional gridworld which is designed to highlight the importance of correctly differentiating through sampling distributions in meta-reinforcement learning.
A Cross-lingual Messenger with Keyword Searchable Phrases for the Travel Domain
We present Qutr (Query Translator), a smart cross-lingual communication application for the travel domain.
