Related papers: A Hierarchical Reinforced Sequence Operation Metho…

Set Shaping Theory (SST) moves beyond the classical fixed-space model by constructing bijective mappings the original sequence set into structured regions of a larger sequence space. These shaped subsets are characterized by a reduced…

Supervised learning has been widely used for attack categorization, requiring high-quality data and labels. However, the data is often imbalanced and it is difficult to obtain sufficient annotations. Moreover, supervised models are subject…

Extrapolation remains a grand challenge in deep neural networks across all application domains. We propose an operator learning method to solve time-dependent partial differential equations (PDEs) continuously and with extrapolation in time…

Non-prehensile multi-object rearrangement is a robotic task of planning feasible paths and transferring multiple objects to their predefined target poses without grasping. It needs to consider how each object reaches the target and the…

Controlled text generation tasks such as unsupervised text style transfer have increasingly adopted the use of Reinforcement Learning (RL). A major challenge in applying RL to such tasks is the sparse reward, which is available only after…

Symbolic planning models allow decision-making agents to sequence actions in arbitrary ways to achieve a variety of goals in dynamic domains. However, they are typically handcrafted and tend to require precise formulations that are not…

The next token prediction loss is the dominant self-supervised training objective for large language models and has achieved promising results in a variety of downstream tasks. However, upon closer investigation of this objective, we find…

We propose LaserTagger - a sequence tagging approach that casts text generation as a text editing task. Target texts are reconstructed from the inputs using three main edit operations: keeping a token, deleting it, and adding a phrase…

Lip-reading aims to infer the speech content from the lip movement sequence and can be seen as a typical sequence-to-sequence (seq2seq) problem which translates the input image sequence of lip movements to the text sequence of the speech…

In this paper, we present a substantial step in better understanding the SOTA sequence-to-sequence (Seq2Seq) pretraining for neural machine translation~(NMT). We focus on studying the impact of the jointly pretrained decoder, which is the…

Academic paper search is a fundamental task in scientific research, yet most existing approaches rely on rigid, predefined workflows that struggle with complex, conditional queries. To address this limitation, we propose PaperScout, an…

We introduce a novel multi-source technique for incorporating source syntax into neural machine translation using linearized parses. This is achieved by employing separate encoders for the sequential and parsed versions of the same source…

Controlling the degree of stylization in the Neural Style Transfer (NST) is a little tricky since it usually needs hand-engineering on hyper-parameters. In this paper, we propose the first deep Reinforcement Learning (RL) based architecture…

We propose a Speech-to-Text Translation (S2TT) approach that integrates phoneme representations into a Chain-of-Thought (CoT) framework to improve translation in low-resource and zero-resource settings. By introducing phoneme recognition as…

Recently, sequence-to-sequence models with attention have been successfully applied in Text-to-speech (TTS). These models can generate near-human speech with a large accurately-transcribed speech corpus. However, preparing such a large…

Facial stylization aims to transform facial images into appealing, high-quality stylized portraits, with the critical challenge of accurately learning the target style while maintaining content consistency with the original image. Although…

Stylometry can be used to profile or deanonymize authors against their will based on writing style. Style transfer provides a defence. Current techniques typically use either encoder-decoder architectures or rule-based algorithms.…

Direct speech-to-speech translation (S2ST) with discrete self-supervised representations has achieved remarkable accuracy, but is unable to preserve the speaker timbre of the source speech. Meanwhile, the scarcity of high-quality…

Editing videos with textual guidance has garnered popularity due to its streamlined process which mandates users to solely edit the text prompt corresponding to the source video. Recent studies have explored and exploited large-scale…

We introduce a novel sequence-to-sequence (seq2seq) voice conversion (VC) model based on the Transformer architecture with text-to-speech (TTS) pretraining. Seq2seq VC models are attractive owing to their ability to convert prosody. While…