AI Briefing#catastrophic-forgetting
The latest AI and developer news about #catastrophic-forgetting, with the original source and a short summary.
The latest AI and developer news about #catastrophic-forgetting, with the original source and a short summary.
Sleep improved the AIME-24 score by 5.4%p through offline integration.
The framework uses MoE expansion and RL-based distillation to consolidate short-term context into long-term parameters, achieving 79.2% accuracy on AIME 24/25.
A parameter selection technique has been proposed that reduces forgetting of existing knowledge while training only on new data.
LG AI Research proposed ASER, a continual learning algorithm that minimizes forgetting by evaluating the importance of data.
This introduces the latest research trends in Transformer-based and self-supervised learning-based continual learning presented at CVPR 2022.
This introduces the Continual Learning research trends based on Transformers and self-supervised learning presented at CVPR 2022.
The KappaTune fine-tuning technique has been officially integrated into Hugging Face's PEFT library.
Self-Distillation Fine-Tuning reduced forgetting in demonstration-based learning.
FST improves both sample efficiency and the forgetting problem together in LLM continual learning.
The author compares SFT, RL, and OPD from a distributional perspective and emphasizes the importance of policy-based sampling.
An experiment interpreting reasoning degradation and catastrophic forgetting as the same kind of structural collapse.
Nova Forge lets enterprises directly train frontier models on their own data.