HN Explorer

panabee

↗ HN profile [ 71.5 ms ] full profile
Karma
0
Created
()
Submissions
0
  1. mRNA-LM: full-length integrated SLM for mRNA analysis (academic.oup.com)
    4 points 0
  2. DiLoCo: Distributed Low-Communication Training of Language Models (huggingface.co)
    3 points 0
  3. Revised Chinchilla scaling laws – LLM compute and token requirements (educatingsilicon.com)
    1 points 0
  4. Compute-Optimal Context Size (manifestai.com)
    2 points 0
  5. An Empirical Study of Mamba-Based Language Models (arxiv.org)
    43 points 5
  6. Human Language Understanding and Reasoning (2022) (amacad.org)
    1 points 1
  7. MapReduce: A Flexible Data Processing Tool (2010) (cacm.acm.org)
    3 points 2
  8. RLHF: Reinforcement Learning from Human Feedback (huyenchip.com)
    1 points 0
  9. Gemini 1.5 Model Family: Technical Report [pdf] (storage.googleapis.com)
    57 points 3
  10. Illuminate: Turn academic papers into AI-generated audio discussions (illuminate.withgoogle.com)
    3 points 1
  11. Sparse Llama: 70% Smaller, 3x Faster, Full Accuracy (cerebras.net)
    40 points 1
  12. Mitochondria and Chloroplasts (khanacademy.org)
    2 points 0
  13. Asian American women are getting lung cancer despite never smoking (nbcnews.com)
    148 points 160
  14. CatLIP: Clip Vision Accuracy with 2.7x Faster Pre-Training on Web-Scale Data (arxiv.org)
    48 points 5
  15. Patchscopes: A framework for viewing hidden representations of language models (research.google)
    12 points 0
  16. Understanding Diffusion Models: A Unified Perspective (arxiv.org)
    2 points 0
  17. Fast-forward – comparing a 1980s supercomputer to the modern smartphone (blog.adobe.com)
    2 points 0
  18. Griffin: Mixing Gated Linear Recurrences with Local Attention for Efficient LMs (arxiv.org)
    1 points 0
  19. Prostate cancer includes two different evotypes (ox.ac.uk)
    152 points 91
  20. Stanford researchers: 45% of GPT4 responses to medical queries hallucinate (twitter.com)
    3 points 4
  21. Understanding Diffusion Models: A Unified Perspective (ar5iv.labs.arxiv.org)
    3 points 0
  22. The promises and pitfalls of specialized ribosomes (2022) (sciencedirect.com)
    2 points 0
  23. Shallow Feed-Forward Neural Networks as Alternative to Attention in Transformers (huggingface.co)
    11 points 0
  24. New Bing attracts new Edge users – who then use Google Search (searchengineland.com)
    2 points 0
  25. FlashFFTConv: Efficient Convolutions for Long Sequences with Tensor Cores (hazyresearch.stanford.edu)
    3 points 0