Nived Rajaraman

2
Papers
68
Total Citations

Papers (2)

Scaling Test-Time Compute Without Verification or RL is Suboptimal

ICML 2025
68
citations

What One Cannot, Two Can: Two-Layer Transformers Provably Represent Induction Heads on Any-Order Markov Chains

NeurIPS 2025arXiv
0
citations