Non-LLM neural networks & ML foundations for expert learners
100 resources · page 4 of 4
xLSTM (NXAI, Linz)
by Maximilian Beck et al. (NXAI)
arXiv paper (2024) introducing xLSTM, extended long short-term memory with exponential gating and matrix memory.
EASA AI Concept Paper Proposed Issue 03
by European Union Aviation Safety Agency (EASA)
EASA AI Concept Paper Proposed Issue 03 (PDF), extending aviation AI assurance guidance to more methods and Level 3 automation.
Reward Hacking in Reinforcement Learning (Lil'Log)
by Lilian
Lilian Weng's survey of reward hacking in reinforcement learning, including in RLHF and coding tasks.
Mamba
by Albert Gu and Tri Dao (Carnegie Mellon University)
arXiv paper (2023) introducing Mamba, linear-time sequence modelling with selective state spaces.