@dair_ai

–

29 January 2023 16h29

ProGen – an LLM that can generate protein sequences with a predictable function across large protein families. 10 of 11

StyleGAN-T: New Model Enhances GAN Competitiveness for Text-to-Image

By

–

29 January 2023 16h29

StyleGAN-T – a new model that aims to regain the competitiveness of GANs for fast large-scale text-to-image synthesis.

9 of 11https://t.co/leKD2VEcmv
— DAIR.AI (@dair_ai) 29 janvier 2023

StyleGAN-T – a new model that aims to regain the competitiveness of GANs for fast large-scale text-to-image synthesis. 9 of 11

DetectGPT: Zero-Shot Machine-Generated Text Detection Method

By

–

29 January 2023 16h28

DetectGPT – an approach for zero-shot machine-generated text detection. Uses raw log probabilities from the LLM to determine if the passage was sampled from it. 8 of 11

Open Problems in Applied Deep Learning Reference

By

–

29 January 2023 16h28

Open Problems in Applied Deep Learning – a new reference to learn about interesting open problems in deep learning. 7 of 11

ClimaX Foundation Model Advances Weather Climate Science

By

–

29 January 2023 16h27

ClimaX – a foundation model for weather and climate, including many capabilities for atmospheric science tasks. 6 of 11

Make-A-Video3D: New Text-to-4D Model for Dynamic Scene Generation

By

–

29 January 2023 16h27

Make-A-Video3D – a new text-to-4D model for dynamic scene generation from input text.

5 of 11https://t.co/V56rEVVGYV
— DAIR.AI (@dair_ai) 29 janvier 2023

Make-A-Video3D – a new text-to-4D model for dynamic scene generation from input text. 5 of 11

Watermarking Framework for Proprietary Language Models

By

–

29 January 2023 16h17

A Watermark for LLMs – a watermarking framework for proprietary language models. 4 of 11

H3: Bridging Performance Gap Between State Space Models and Attention

By

–

29 January 2023 16h17

H3 – an approach to reduce the gap, in terms of performance and hardware utilization, between state space models and attention for language modeling. 3 of 11

Generative Modeling for Time Series Forecasting with Diffusion VAE

By

–

15 January 2023 18h31

This work addresses the time series forecasting problem with generative modeling; involves a bidirectional VAE backbone equipped with diffusion, denoising for prediction accuracy, and disentanglement for model interpretability. 11 of 11