Similar to "We don't share the code but the details are described in the paper for those who want to implement and use it"
CODE
-
Transformer-based Vulnerability Detection in Code: Zero-shot, Few-shot, Fine-tuning
By
–
Transformer-based Vulnerability Detection in Code at EditTime: Zero-shot, Few-shot, or Fine-tuning? paper page: https://
huggingface.co/papers/2306.01
754
… Software vulnerabilities bear enterprises significant costs. Despite extensive efforts in research and development of software vulnerability -
George Builds AI Assistant with GPT-3.5 in 15 Days
By
–
George was paired with Dom’s project.
— Replit ⠕ (@Replit) 5 juin 2023
Within 10 days, George had a prototype running on gpt-3.5 and the Mighty Deals database.
And in 15 days, the AI assistant was deployed to production using Replit Deployments. pic.twitter.com/iLpxJ9R5rXGeorge was paired with Dom’s project. Within 10 days, George had a prototype running on gpt-3.5 and the Mighty Deals database. And in 15 days, the AI assistant was deployed to production using Replit Deployments.
-
CS Student Earns $1000 Monthly Through Replit Bounties Freelancing
By
–
George Wandhe, @tec_toi, studies computer science at Moi University.
— Replit ⠕ (@Replit) 5 juin 2023
3 months ago, he discovered Replit Bounties from @amasad’s tweets and decided to give freelancing a shot.
His goal: earn $1000 USD per month to see if life as a full-time freelancer was possible. pic.twitter.com/BBdq9lDlWfGeorge Wandhe, @tec_toi
, studies computer science at Moi University. 3 months ago, he discovered Replit Bounties from @amasad
’s tweets and decided to give freelancing a shot. His goal: earn $1000 USD per month to see if life as a full-time freelancer was possible. -
Python Walrus Operator Reduces Boilerplate Code Elegantly
By
–
Have recently started using the walrus operator (:=) everywhere in my Python code, which lets you write code like this: if foo := bar(): print(foo) vs: foo = bar()
if foo: print(foo) Love little reductions in boilerplate without sacrificing clarity — they add up. -
CORN Method for Finetuning LLMs on Prediction Tasks
By
–
Oh, and I should have emphasized that you can use our CORN (Conditional Ordinal Regression for Neural Networks) method to finetune your favorite LLM for prediction tasks, or course! An example for TripAdvisor customer reviews here: https://
github.com/Raschka-resear
ch-group/coral-pytorch/blob/main/docs/tutorials/pytorch_lightning/distilbert-corn-tripadvisor.ipynb
… -
IoT Skills and Expertise for Legacy System Upgrades
By
–
Advancing new IoT initiatives and upgrading existing legacy systems call for the skills and expertise of developers, architects, engineers, and a variety of other IoT professionals. Source @101Blockchains Link https://
bit.ly/3qjXzhO via @antgrasso #IoT #IIoT #skills -
LIV: Language-Image Representations and Rewards for Robotic Control
By
–
LIV: Language-Image Representations and Rewards for Robotic Control
— AK (@_akhaliq) 5 juin 2023
paper page: https://t.co/wYfPYkBWP6
Language-Image Value (LIV) is a unified pre-training, fine-tuning, and reward learning algorithm for language-conditioned visual manipulation. LIV can perform zero-shot… pic.twitter.com/IeKJiwVTADLIV: Language-Image Representations and Rewards for Robotic Control paper page: https://
huggingface.co/papers/2306.00
958
… Language-Image Value (LIV) is a unified pre-training, fine-tuning, and reward learning algorithm for language-conditioned visual manipulation. LIV can perform zero-shot -
Hiera: Advanced Vision Transformer Architecture with 3.6x Speed Improvement
By
–
Hiera represents a significant advance over the vision transformer architecture. This work outperforms SOTA while being up to 3.6x faster across a range of image and video tasks — without use of domain specialized modules. Code https://
bit.ly/45OSyhq
