Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Docs
  • Enterprise
  • Pricing

  • Log In
  • Sign Up
Amirkia Rafiei Oskooei's picture
5 17

Amirkia Rafiei Oskooei

amirkiarafiei
Mi6paulino's profile picture mertgokbayrak's profile picture hannantoprak's profile picture
Β·
https://www.amirkia.tech/
  • amirkiarafiei
  • amirkiarafiei

AI & ML interests

None yet

Recent Activity

liked a dataset about 1 month ago
nvidia/ProfBench
upvoted a paper about 1 month ago
Lost in the Middle: How Language Models Use Long Contexts
reacted to onekq's post with πŸ‘ about 1 month ago
Context rot is such a catchy phrase, but the problem has been identified 2+ years ago, called attention decay. https://huggingface.co/papers/2307.03172 I spotted the same problem in coding tasks, and documented in my book (https://www.amazon.com/dp/9999331130). Why did this problem become hot again? This is because many of us thought the problem has been solved by long context models, which is not true. Here we were misled by benchmarks. Most long-context benchmarks build around the QA scenario, i.e. "finding needle in haystack". But in agentic scenarios, the model needs to find EVERYTHING in the haystack, and just can't afford enough attention for this challenge.
View all activity

Organizations

DNext Technology's profile picture Intellica Business Intelligence and AI's profile picture Lokum AI's profile picture Rail Dev Hub's profile picture

spaces 1

Sleeping

Github and Hugging Face Space Synchronization

🀝

A Sample Space Synced with a GitHub Repository

Apr 9

models 0

None public yet

datasets 0

None public yet
Company
TOS Privacy About Jobs
Website
Models Datasets Spaces Pricing Docs