Customizing Sequence Generation with Multi-Task Dynamical Systems
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.
Code (1)
Tasks
Style TransferSimilar Papers 제목 키워드 기반
Group Linguistic Bias Aware Neural Response Generation
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 GenerationCustomizing Synthetic Data for Data-Free Student Learning
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 DistillationMotion-Agent: A Conversational Framework for Human Motion Generation with LLMs
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 GenerationRethinking Model Redundancy for Low-light Image Enhancement
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 EnhancementmodelEnhancing Detail Preservation for Customized Text-to-Image Generation: A Regularization-Free Approach
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