Test-Time Scaling Makes Overtraining Compute-Optimal
Paper • 2604.01411 • Published • 28
Nicholas Roberts PRO
nick11roberts
AI & ML interests
Data-Centric AutoML–i.e., making machine learning more accessible and practically applicable to new domains while reducing human involvement.
Recent Activity
upvoted a paper about 1 month ago
Test-Time Scaling Makes Overtraining Compute-Optimal submitted a paper about 1 month ago
Test-Time Scaling Makes Overtraining Compute-Optimal upvoted a paper about 1 month ago
SlopCodeBench: Benchmarking How Coding Agents Degrade Over Long-Horizon Iterative TasksOrganizations
upvoted 2
papers about 1 month ago