arxiv:2402.15343
🔄 In a Training Loop
Constantin
Alexandre-Numind
AI & ML interests
Training AI models @Numind
Recent Activity
upvoted a paper 6 days ago
EarlyEval: Cheaper Agent Evaluation via Early Outcome Prediction new activity 24 days ago
numind/NuExtract3:Add ExtractBench evaluation results upvoted a paper about 1 month ago
SFT Conflicts, RL Coexists: A Theoretical and Empirical Analysis of Multi-Task Learning for LLMs