paper-with-me

홈 › Papers

Text-Free Learning of a Natural Language Interface for Pretrained Face Generators

2022-09-08 · Xiaodan Du, Raymond A. Yeh, Nicholas Kolkin, Eli Shechtman, Greg Shakhnarovich

We propose Fast text2StyleGAN, a natural language interface that adapts pre-trained GANs for text-guided human face synthesis. Leveraging the recent advances in Contrastive Language-Image Pre-training (CLIP), no text data is required during training. Fast text2StyleGAN is formulated as a conditional variational autoencoder (CVAE) that provides extra control and diversity to the generated images at test time. Our model does not require re-training or fine-tuning of the GANs or CLIP when encountering new text prompts. In contrast to prior work, we do not rely on optimization at test time, making our method orders of magnitude faster than prior work. Empirically, on FFHQ dataset, our method offers faster and more accurate generation of images from natural language descriptions with varying levels of detail compared to prior work.

📄 PDF Abstract BibTeX arXiv:2209.03953

Code (1)

duxiaodan/fast_text2stylegan 공식 구현 pytorch

Tasks

DiversityFace Generation

Methods 이 논문이 사용한 방법론

Test 설명 없음
CLIP Contrastive Language-Image Pre-training (CLIP), consisting of a simplified version of ConVIRT trained from scratch, is an efficient method of image representation learning…

Similar Papers 제목 키워드 기반

On joint training with interfaces for spoken language understanding

2021-06-30 · Anirudh Raju, Milind Rao, Gautam Tiwari, Pranav Dheram 외

Spoken language understanding (SLU) systems extract both text transcripts and semantics associated with intents and slots from input speech utterances. SLU systems usually consist of (1) an automatic speech recognition (…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Natural Language Understandingspeech-recognition+2

Hands-Free VR

2024-02-23 · Jorge Askur Vazquez Fernandez, Jae Joong Lee, Santiago Andrés Serrano Vacca, Alejandra Magana 외

The paper introduces Hands-Free VR, a voice-based natural-language interface for VR. The user gives a command using their voice, the speech audio data is converted to text using a speech-to-text deep learning model that …

DiversityLanguage ModellingLarge Language ModelSpeech-to-Text

Towards Neural Programming Interfaces

2020-12-10 · NeurIPS 2020 12 · Zachary C. Brown, Nathaniel Robinson, David Wingate, Nancy Fulda

It is notoriously difficult to control the behavior of artificial neural networks such as generative neural language models. We recast the problem of controlling natural language generation as that of learning to interfa…

Language ModelingLanguage ModellingText Generation

GestureGPT: Toward Zero-Shot Free-Form Hand Gesture Understanding with Large Language Model Agents

2023-10-19 · Xin Zeng, Xiaoyu Wang, Tengxiang Zhang, Chun Yu 외

Existing gesture interfaces only work with a fixed set of gestures defined either by interface designers or by users themselves, which introduces learning or demonstration efforts that diminish their naturalness. Humans,…

Common Sense ReasoningFormGesture RecognitionLanguage Modeling+3

When Machines Speak: A Unified Generative Framework for Integrating Machine-Native Symbols into Pretrained Large Language Models

2026-08-20 · Su Yan, Rakesh Iyer arxiv

Many real-world AI systems represent entities, behaviors, and structured information using discrete machine-native symbols rather than natural language. While these representations are compact and preserve task-relevant …

Sequential RecommendationStructured Prediction