Firecracker
Probabilistic Consistency in Machine Learning and Its Connection to Uncertainty Quantification
arxiv.org·1d
Built RL training for long-horizon terminal agents - tested on 32x H100s but too GPU poor to train 😅
Reviving Your MNEME: Predicting The Side Effects of LLM Unlearning and Fine-Tuning via Sparse Model Diffing
arxiv.org·1d
Loading...Loading more...