Related papers: EdiT5: Semi-Autoregressive Text-Editing with T5 Wa…

We propose Seq2Edits, an open-vocabulary approach to sequence editing for natural language processing (NLP) tasks with a high degree of overlap between input and output texts. In this approach, each sequence-to-sequence transduction is…

Existing large language models have to run K times to generate a sequence of K tokens. In this paper, we present RecycleGPT, a generative language model with fast decoding speed by recycling pre-generated model states without running the…

Existing autoregressive large-scale text-to-speech (TTS) models have advantages in speech naturalness, but their token-by-token generation mechanism makes it difficult to precisely control the duration of synthesized speech. This becomes a…

Reaction prediction is a fundamental problem in computational chemistry. Existing approaches typically generate a chemical reaction by sampling tokens or graph edits sequentially, conditioning on previously generated outputs. These…

We propose a framework for training non-autoregressive sequence-to-sequence models for editing tasks, where the original input sequence is iteratively edited to produce the output. We show that the imitation learning algorithms designed to…

Explicit decomposition modeling, which involves breaking down complex tasks into more straightforward and often more interpretable sub-tasks, has long been a central theme in developing robust and interpretable NLU systems. However, despite…

Current state-of-the-art image captioning models adopt autoregressive decoders, \ie they generate each word by conditioning on previously generated words, which leads to heavy latency during inference. To tackle this issue,…

We present Entropy Adaptive Decoding (EAD), a novel approach for efficient language model inference that dynamically switches between different-sized models based on prediction uncertainty. By monitoring rolling entropy in model logit…

We propose a conditional non-autoregressive neural sequence model based on iterative refinement. The proposed model is designed based on the principles of latent variable models and denoising autoencoders, and is generally applicable to any…

In neural text editing, prevalent sequence-to-sequence based approaches directly map the unedited text either to the edited text or the editing operations, in which the performance is degraded by the limited source text encoding and long,…

Providing voice assistants the ability to navigate multi-turn conversations is a challenging problem. Handling multi-turn interactions requires the system to understand various conversational use-cases, such as steering, intent carryover,…

In this work, we first revisit the sampling issues in current autoregressive (AR) image generation models and identify that image tokens, unlike text tokens, exhibit lower information density and non-uniform spatial distribution.…

Text simplification (TS) rephrases long sentences into simplified variants while preserving inherent semantics. Traditional sequence-to-sequence models heavily rely on the quantity and quality of parallel sentences, which limits their…

Recent work has shown that either (1) increasing the input length or (2) increasing model size can improve the performance of Transformer-based neural models. In this paper, we present a new model, called LongT5, with which we explore the…

Despite recent progress in text-to-image (T2I) generation, existing models often struggle to faithfully capture user intentions from short and under-specified prompts. While prior work has attempted to enhance prompts using large language…

Existing approaches to neural machine translation are typically autoregressive models. While these models attain state-of-the-art translation quality, they are suffering from low parallelizability and thus slow at decoding long sequences.…

The recent "Text-to-Text Transfer Transformer" (T5) leveraged a unified text-to-text format and scale to attain state-of-the-art results on a wide variety of English-language NLP tasks. In this paper, we introduce mT5, a multilingual…

Controlled text generation is a very important task in the arena of natural language processing due to its promising applications. In order to achieve this task we mainly introduce the novel soft prompt tuning method of using soft prompts…

Existing Large Language Model (LLM) based autoregressive (AR) text-to-speech (TTS) systems, while achieving state-of-the-art quality, still face critical challenges. The foundation of this LLM-based paradigm is the discretization of the…

The recent advancements in large language models (LLMs) have been extraordinary, yet the escalating inference costs associated with them present challenges in real-world applications. To address these challenges, we propose a novel approach…