Conffusion: Confidence Intervals for Diffusion Models
— AK (@_akhaliq) November 18, 2022
abs: https://t.co/LJ9r2K5Ilz
project page: https://t.co/UtM0nyYZqg pic.twitter.com/UfJNvkagA9
Conffusion: Confidence Intervals for Diffusion Models
— AK (@_akhaliq) November 18, 2022
abs: https://t.co/LJ9r2K5Ilz
project page: https://t.co/UtM0nyYZqg pic.twitter.com/UfJNvkagA9
Null-text Inversion for Editing Real Images using Guided Diffusion Models
— AK (@_akhaliq) November 18, 2022
abs: https://t.co/otMgDpw5WA
project page: https://t.co/Lrwfa1XLyu pic.twitter.com/CHRq1qRxjn
Hybrid Transformers for Music Source Separation
— AK (@_akhaliq) November 17, 2022
abs: https://t.co/iuJ3tudk3H pic.twitter.com/F6J2TBTsJK
Holistic Evaluation of Language Models
— AK (@_akhaliq) November 17, 2022
abs: https://t.co/PwG6mDoJQX pic.twitter.com/e5itFfOQjM
Galactica: A Large Language Model for Science
— AK (@_akhaliq) November 17, 2022
abs: https://t.co/WZk3fmtDHS pic.twitter.com/99RLJqROyV
Introducing a novel mixture-of-experts routing algorithm, called Expert Choice, that can achieve optimal load balancing between experts while allowing heterogeneous token-to-expert mapping. Learn how it’s done at https://t.co/EDomelBL53 pic.twitter.com/Oyaa0wEMlX
— Google AI (@GoogleAI) November 16, 2022
Large Language Models Struggle to Learn Long-Tail Knowledge
— AK (@_akhaliq) November 16, 2022
abs: https://t.co/8WKY88NkfM pic.twitter.com/rulgHJDvyH
Versatile Diffusion: Text, Images and Variations All in One Diffusion Model
— AK (@_akhaliq) November 16, 2022
abs: https://t.co/UjdtkxFY2s
github: https://t.co/N3bQbpI4SB pic.twitter.com/KW8Ix4O91g
Fast Text-Conditional Discrete Denoising on Vector-Quantized Latent Spaces
— AK (@_akhaliq) November 15, 2022
abs: https://t.co/iX3hg5HOVn
github: https://t.co/TPwZNSJgaD
t2i model requiring less than 10 steps to sample high-fidelity images pic.twitter.com/veHSlEmkaG
DreamArtist: Towards Controllable One-Shot Text-to-Image Generation via Contrastive Prompt-Tuning with @Gradio SD Web UI
— AK (@_akhaliq) November 14, 2022
github: https://t.co/kPlCKwQNtZ pic.twitter.com/e4VryGVdGQ
OneFormer: One Transformer to Rule Universal Image Segmentation
— AK (@_akhaliq) November 14, 2022
abs: https://t.co/nZHKqesjBD
github: https://t.co/nQU7CL2PuY
propose OneFormer, a universal image segmentation framework that unifies segmentation with a multi-task train-once design pic.twitter.com/xlKgtF7Zcr
There's always something cringe on Twitter, here's a useful one!
— Jason Weston (@jaseweston) November 14, 2022
🚨 new paper 🚨
The CRINGE Loss: Learning what language not to model
Train your LM to not generate bad sequences.
Shows improvements on three tasks (safety, contradictions, open dialogue).https://t.co/yiAzzYQcbV pic.twitter.com/ZMmm31Xdil