about
Stories from September 21, 2024 (UTC)
Go back a day, month, or year. Go forward a day.
1. Dissociating language and thought in large language models (arxiv.org)
42 points by rntn on Sep 21, 2024 | hide | past | pdf | 4 comments
2. SwiGLU activation function causes instability in FP8 LLM training (arxiv.org)
10 points by LarsDu88 on Sep 21, 2024 | hide | past | pdf | 2 comments
3. A Multimodal User Embedding Provides Personalized Explanations (arxiv.org)
1 point by PaulHoule on Sep 21, 2024 | hide | past | pdf | discuss