paper-with-me

홈 › Papers

Customizing Sequence Generation with Multi-Task Dynamical Systems

2019-10-11 · Alex Bird, Christopher K. I. Williams

Dynamical system models (including RNNs) often lack the ability to adapt the sequence generation or prediction to a given context, limiting their real-world application. In this paper we show that hierarchical multi-task dynamical systems (MTDSs) provide direct user control over sequence generation, via use of a latent code $\mathbf{z}$ that specifies the customization to the individual data sequence. This enables style transfer, interpolation and morphing within generated sequences. We show the MTDS can improve predictions via latent code interpolation, and avoid the long-term performance degradation of standard RNN approaches.

📄 PDF Abstract BibTeX arXiv:1910.05026

Code (1)

ornithos/mtds-dblpend

Tasks

Style Transfer

Similar Papers 제목 키워드 기반

Group Linguistic Bias Aware Neural Response Generation

2017-12-01 · WS 2017 12 · Jianan Wang, Xin Wang, Fang Li, Zhen Xu 외

For practical chatbots, one of the essential factor for improving user experience is the capability of customizing the talking style of the agents, that is, to make chatbots provide responses meeting users{'} preference …

DecoderResponse Generation

Customizing Synthetic Data for Data-Free Student Learning

2023-07-10 · Shiya Luo, Defang Chen, Can Wang

Data-free knowledge distillation (DFKD) aims to obtain a lightweight student model without original training data. Existing works generally synthesize data from the pre-trained teacher model to replace the original train…

Data-free Knowledge DistillationKnowledge Distillation

Motion-Agent: A Conversational Framework for Human Motion Generation with LLMs

2024-05-27 · Qi Wu, Yubo Zhao, Yifan Wang, Xinhang Liu 외

While previous approaches to 3D human motion generation have achieved notable success, they often rely on extensive training and are limited to specific tasks. To address these challenges, we introduce Motion-Agent, an e…

Language ModelingLanguage ModellingMotion CaptioningMotion Generation

Rethinking Model Redundancy for Low-light Image Enhancement

2024-12-21 · Tong Li, Lizhi Wang, Hansen Feng, Lin Zhu 외

Low-light image enhancement (LLIE) is a fundamental task in computational photography, aiming to improve illumination, reduce noise, and enhance the image quality of low-light images. While recent advancements primarily …

Image EnhancementLow-Light Image Enhancementmodel

Enhancing Detail Preservation for Customized Text-to-Image Generation: A Regularization-Free Approach

2023-05-23 · Yufan Zhou, Ruiyi Zhang, Tong Sun, Jinhui Xu

Recent text-to-image generation models have demonstrated impressive capability of generating text-aligned images with high fidelity. However, generating images of novel concept provided by the user input image is still a…

GPUImage GenerationText to Image GenerationText-to-Image Generation