Meta learning and recursive self-improvement are old ideas. Foundation models breathe new life into them. Our new survey, “Self-Improvements in Modern Agentic Systems,” reviews how the concepts are continuing to evolve.
Paper: https://t.co/59oXCMVUkD
Project: https://t.co/sZwFYdGetH
Github: https://t.co/7OFgJUCN3a
15 AI Research Papers Every AI Engineer Should Read
1. Attention Is All You Need (Transformers)
https://t.co/uNqD7WesTy
2. LoRA: Low-Rank Adaptation
https://t.co/7OfFr3JksJ
3. PEFT (Parameter-Efficient Fine-Tuning)
https://t.co/sT7HVw2Mux
4. An Image is Worth 16×16 Words (Vision Transformer)
https://t.co/JsgvilnrtM
5. Auto-Encoding Variational Bayes (VAE)
https://t.co/VDa7oD9xtT
6. Generative Adversarial Networks (GANs)
https://t.co/ZDW8H6lPOS
7. BERT
https://t.co/IqdUwr9w0n
8. High-Resolution Image Synthesis with Latent Diffusion Models
https://t.co/g3B2DtV0we
9. Retrieval-Augmented Generation (RAG)
https://t.co/Bkhg7OvtRx
10. Language Models are Few-Shot Learners (GPT-3)
https://t.co/bTNvpzFffw
11. Switch Transformers (MoE)
https://t.co/n2hpgHw6Ri
12. Learning to Summarize with Human Feedback (RLHF)
https://t.co/Xi7BLjbBQg
13. LLaMA: Open and Efficient Foundation Language Models
https://t.co/A8zfwaKroJ
14. RoFormer: Rotary Position Embedding (RoPE)
https://t.co/5vHovvUrl7
15. InstructGPT
https://t.co/METMZVuqxI
Reading papers is one thing. Understanding why each changed the field is what makes you a stronger AI engineer.
A paper in Nature presents OpenScholar, an open-source language model that can outperform commercial large language models (LLMs) in performing accurate literature reviews. https://t.co/HhXZfmGAS1
"Biz çocukken erkeklere bisiklet alınırdı, kızlar süremez denirdi”
Mardin'in Derik ilçesinde 72 kadın tek bir bisikletle çocukluk hayalini gerçekleştirdi, bisiklet sürmeyi öğrendi
@HaticeKamer bu kadınlarla bir gün geçirdi... https://t.co/MeYjPq4lML
🚄 Here is the German Greens’ plan for a night-train network across Europe
😴 Go to sleep in one country and wake up in another!
💚 Such an exciting vision of comfortable, romantic and *low-carbon* travel
#GreensMakeChange
h/t @PGolka
Imaginary numbers are not some wild invention, they are the deep and natural result of extending our number system. Imaginary numbers are all about the discovery of numbers existing not in 1 dimension along the number line, but in full 2 dimensional space https://t.co/grymJ3uM63
A very informative playlist of short bite-sized videos on #ethics in #machinelearning by @math_rachel.
They have been curated from her excellent lecture on ethics in the @fastdotai series.
📺Playlist: https://t.co/dGVV7rv7ZB
📰Blog: https://t.co/kKmva7iuvD
I came home from space 4 years ago this week, and if you've ever wondered what it looks like when you travel through this atmosphere -here you go😳
#Landaversary