Homepage
Close
Menu

Site Navigation

  • Home
  • Archive(TODO)
    • By Day
    • By Month
  • About(TODO)
  • Stats
Close
by _akhaliq on 2022-12-14 (UTC).

What do Vision Transformers Learn? A Visual Exploration
abs: https://t.co/0xJ8UyglHP
github: https://t.co/ftJejEIn43 pic.twitter.com/TPi6YjKZac

— AK (@_akhaliq) December 14, 2022
researchcvw_code
by MichaelAuli on 2022-12-13 (UTC).

New work on efficient self-supervised learning: data2vec 2.0 pre-trains vision models 16.4x faster than the most popular existing algorithm.
Blog: https://t.co/pz6XWKOGGh
Paper: https://t.co/x4kgTbMj7t
Code/models: https://t.co/DoUxCzkHEX
with @ZloiAlexei @mhnt1580 @arunbabu1234 pic.twitter.com/zFHnpOo4iI

— Michael Auli (@MichaelAuli) December 13, 2022
research
by _akhaliq on 2022-12-13 (UTC).

REVEAL: Retrieval-Augmented Visual-Language Pre-Training with Multi-Source Multimodal Knowledge Memory
abs: https://t.co/8e5JXjSZlS pic.twitter.com/Wp0HKjNOCg

— AK (@_akhaliq) December 13, 2022
researchnlpcv
by _akhaliq on 2022-12-13 (UTC).

CLIP Itself is a Strong Fine-tuner: Achieving 85.7% and 88.0% Top-1 Accuracy with ViT-B and ViT-L on ImageNet
abs: https://t.co/T78PJg7rHK pic.twitter.com/SBL4DksY9z

— AK (@_akhaliq) December 13, 2022
researchnlpcv
by _akhaliq on 2022-12-13 (UTC).

MAGVIT: Masked Generative Video Transformer
abs: https://t.co/LOuF71lgLl
project page: https://t.co/o1uf6BsCbB pic.twitter.com/rHfhtUqeBB

— AK (@_akhaliq) December 13, 2022
researchcv
by _akhaliq on 2022-12-12 (UTC).

Seeing a Rose in Five Thousand Ways
abs: https://t.co/g3DPhg4FLY pic.twitter.com/GUZWdmjmQF

— AK (@_akhaliq) December 12, 2022
researchcv
by _akhaliq on 2022-12-12 (UTC).

Training-Free Structured Diffusion Guidance for Compositional Text-to-Image Synthesis
abs: https://t.co/nW5Gpx56ov
github: https://t.co/yXx0RJyzhH pic.twitter.com/qXisikcrDO

— AK (@_akhaliq) December 12, 2022
researchw_code
by _akhaliq on 2022-12-10 (UTC).

LORA - Low-rank Adaptation for Fast Text-to-Image Diffusion Fine-tuning @Gradio demo on @huggingface spaces by @yvrjsharma
⁰Fine-tune Stable diffusion models twice as faster than dreambooth method, by Low-rank Adaptation

demo: https://t.co/aV5QusLq5s

— AK (@_akhaliq) December 10, 2022
researchtooldiffusion
by rasbt on 2022-12-10 (UTC).

Just read through state of AI report by McKinsey: https://t.co/fYhnZ2JGvX
(As a researcher, it seems to be useful summary of how AI is *actually* used in industry.)

Interesting insights

1. Computer vision now ties with NLP for classification/understanding

1 of 4 pic.twitter.com/8FBhjjRJau

— Sebastian Raschka (@rasbt) December 10, 2022
misc
by _akhaliq on 2022-12-09 (UTC).

VideoDex: Learning Dexterity from Internet Videos
abs: https://t.co/j9g9QJ8X2L
project page: https://t.co/2CwgvxlDqo pic.twitter.com/5FunjX44NY

— AK (@_akhaliq) December 9, 2022
researchcv
by _akhaliq on 2022-12-09 (UTC).

Diffusion Art or Digital Forgery? Investigating Data Replication in Diffusion Models
abs: https://t.co/VfVDCq1cwY pic.twitter.com/IDDDUuhs2b

— AK (@_akhaliq) December 9, 2022
researchdiffusion
by _akhaliq on 2022-12-09 (UTC).

SINE: SINgle Image Editing with Text-to-Image Diffusion Models
abs: https://t.co/t9DOAdJUgU
project page: https://t.co/G4PGZCKeGQ pic.twitter.com/H3ugxkPaR5

— AK (@_akhaliq) December 9, 2022
researchdiffusioncv
  • Prev
  • 1
  • 2
  • 3
  • 4
  • 5
  • …
  • Next

Tags

learning tutorial misc nlp rstats gan ethics research dataviz survey python tool security kaggle video thought bayesian humour tensorflow w_code bias dataset pytorch cv tip application javascript forecast swift golang rl jax julia gnn causal surey diffusion
© Copyright Philosophy 2018 Site Template by Colorlib