Homepage
Close
Menu

Site Navigation

  • Home
  • Archive(TODO)
    • By Day
    • By Month
  • About(TODO)
  • Stats
Close
by _akhaliq on 2022-10-24 (UTC).

Diffuser: Efficient Transformers with Multi-hop Attention Diffusion for Long Sequences
abs: https://t.co/e0ZSrPRoeH pic.twitter.com/V9STZ7nmQU

— AK (@_akhaliq) October 24, 2022
research
by _akhaliq on 2022-10-24 (UTC).

Large Language Models Can Self-Improve
abs: https://t.co/Hjp5AfvFD3

approach improves the general reasoning ability of a 540B-parameter LLM (74.4%→82.1% on GSM8K, 78.2%→83.0% on DROP, 90.0%→94.4% on OpenBookQA, and 63.4%→67.9% on ANLI-A3) pic.twitter.com/yYW7e2WsPB

— AK (@_akhaliq) October 24, 2022
nlp
by rasbt on 2022-10-23 (UTC).

It's always exciting to add a new method to the deep tabular list: https://t.co/pWOAwqiTS0.

Just read through the paper. It's an intriguing fresh take on deep learning for tabular data, combining approximate Bayesian inference and transformer tokenization. [1/6] https://t.co/iJeYGFC9dG

— Sebastian Raschka 📚 (@rasbt) October 23, 2022
research
In a group with 2 other tweets.
by tunguz on 2022-10-22 (UTC).

Accurate. pic.twitter.com/7AXTPP7Li7

— Bojan Tunguz (@tunguz) October 22, 2022
miscthought
by rasbt on 2022-10-21 (UTC).

Wow, below is the 2nd paper shared today on deep tabular methods!
The deep learning from tabular data research field is on fire today 🔥!

(PS: And don't forget about diffusion models for tabular data: https://t.co/CaEWyMyqnK 😁)

(PPS: My reviews will follow soon 😊) https://t.co/xupH4Znh3e

— Sebastian Raschka 📚 (@rasbt) October 21, 2022
research
In a group with 2 other tweets.
by amuellerml on 2022-10-21 (UTC).

A meta-learned transformer for tabular data: https://t.co/3rlNtJa2hc I was waiting for this to happen, and I'm pretty convinced that's where ML will go. From Frank Hutter's (imho legendary) lab!

— Andreas Mueller (@amuellerml) October 21, 2022
research
In a group with 2 other tweets.
by ai_fast_track on 2022-10-21 (UTC).

🤔 You probably never heard of MMRotate

Here are some reasons why you should be familiar with:

• MMRotate is an open-source toolbox for rotated object detection based on PyTorch

• Like the awesome MMDetection library, It is part of the @OpenMMLab project (18 libraries 🤯) pic.twitter.com/yd4VhmVkc7

— @farid@sigmoid.social (Mastodon) (@ai_fast_track) October 21, 2022
toolcvpytorch
by _akhaliq on 2022-10-21 (UTC).

MovieCLIP: Visual Scene Recognition in Movies
abs: https://t.co/WaF11rNcX1
project page: https://t.co/ZTK9PYWmcW pic.twitter.com/KyPsp3DkNt

— AK (@_akhaliq) October 21, 2022
researchcv
by _akhaliq on 2022-10-21 (UTC).

DiffEdit: Diffusion-based semantic image editing with mask guidance
abs: https://t.co/9pzsPwiU1K pic.twitter.com/elAYmnMh2w

— AK (@_akhaliq) October 21, 2022
researchcvnlp
by ai_fast_track on 2022-10-20 (UTC).

😨 Training an Object Detection Model is a very challenging task and involves tweaking so many knobs

Here is an exhaustive 🎁 tips & tricks list 🎁 that you could use to boost your model performance

🧵 pic.twitter.com/sOvEUhCCwg

— @farid@sigmoid.social (Mastodon) (@ai_fast_track) October 20, 2022
learningcv
by _akhaliq on 2022-10-20 (UTC).

RankT5: Fine-Tuning T5 for Text Ranking with Ranking Losses
abs: https://t.co/j8i1CgQrYb pic.twitter.com/qG1VqFWwEb

— AK (@_akhaliq) October 20, 2022
researchnlp
by _akhaliq on 2022-10-20 (UTC).

A Unified View of Masked Image Modeling
abs: https://t.co/Kw4zgbpgXY pic.twitter.com/WS9RgFU4NJ

— AK (@_akhaliq) October 20, 2022
research
  • Prev
  • 10
  • 11
  • 12
  • 13
  • 14
  • …
  • 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