paper-with-me

홈 › Papers

DIRECTOR: Generator-Classifiers For Supervised Language Modeling

2022-06-15 · Kushal Arora, Kurt Shuster, Sainbayar Sukhbaatar, Jason Weston

Current language models achieve low perplexity but their resulting generations still suffer from toxic responses, repetitiveness and contradictions. The standard language modeling setup fails to address these issues. In this paper, we introduce a new architecture, {\sc Director}, that consists of a unified generator-classifier with both a language modeling and a classification head for each output token. Training is conducted jointly using both standard language modeling data, and data labeled with desirable and undesirable sequences. Experiments in several settings show that the model has competitive training and decoding speed compared to standard language models while yielding superior results, alleviating known issues while maintaining generation quality. It also outperforms existing model guiding approaches in terms of both accuracy and efficiency.

📄 PDF Abstract BibTeX arXiv:2206.07694

Code (1)

facebookresearch/ParlAI pytorch

Tasks

Language ModelingLanguage Modelling

Methods 이 논문이 사용한 방법론

SPEED The monocular depth estimation (MDE) is the task of estimating depth from a single frame. This information is an essential knowledge in many computer vision tasks such as scene…

Similar Papers 제목 키워드 기반

Introspective Generative Modeling: Decide Discriminatively

2017-04-25 · Justin Lazarow, Long Jin, Zhuowen Tu

We study unsupervised learning by developing introspective generative modeling (IGM) that attains a generator using progressively learned deep convolutional neural networks. The generator is itself a discriminator, capab…

General Classification

Introspective Neural Networks for Generative Modeling

2017-10-01 · ICCV 2017 10 · Justin Lazarow, Long Jin, Zhuowen Tu

We study unsupervised learning by developing a generative model built from progressively learned deep convolutional neural networks. The resulting generator is additionally a discriminator, capable of "introspection" in …

General Classification

LLM as an Art Director (LaDi): Using LLMs to improve Text-to-Media Generators

2023-11-07 · Allen Roush, Emil Zakirov, Artemiy Shirokov, Polina Lunina 외

Recent advancements in text-to-image generation have revolutionized numerous fields, including art and cinema, by automating the generation of high-quality, context-aware images and video. However, the utility of these t…

Image GenerationRetrievalText to Image GenerationText-to-Image Generation+1

DirectorLLM for Human-Centric Video Generation

2024-12-19 · Kunpeng Song, Tingbo Hou, Zecheng He, Haoyu Ma 외

In this paper, we introduce DirectorLLM, a novel video generation model that employs a large language model (LLM) to orchestrate human poses within videos. As foundational text-to-video models rapidly evolve, the demand …

Language ModelingLanguage ModellingLarge Language ModelVideo Generation

DRAG: Director-Generator Language Modelling Framework for Non-Parallel Author Stylized Rewriting

2021-01-28 · EACL 2021 2 · Hrituraj Singh, Gaurav Verma, Aparna Garimella, Balaji Vasan Srinivasan

Author stylized rewriting is the task of rewriting an input text in a particular author's style. Recent works in this area have leveraged Transformer-based language models in a denoising autoencoder setup to generate aut…

DenoisingLanguage Modelling