Nived Rajaraman
Scholar

Nived Rajaraman

Google Scholar ID: ZvX1hXcAAAAJ
EECS PhD student at UC Berkeley
Reinforcement LearningLLMs
Homepage↗Google Scholar↗
Citations & Impact
All-time
Citations
654
 
H-index
11
 
i10-index
11
 
Publications
20
 
Co-authors
7
list available
Contact
GitHubOpen ↗
Publications
9 items
Learning to Reason with Curriculum I: Provable Benefits of Autocurriculum
2026
Cited
0
Interactive Learning of Single-Index Models via Stochastic Gradient Descent
2026
Cited
0
What One Cannot, Two Can: Two-Layer Transformers Provably Represent Induction Heads on Any-Order Markov Chains
2025
Cited
0
The Space Complexity of Learning-Unlearning Algorithms
2025
Cited
1
$ exttt{SPECS}$: Faster Test-Time Scaling through Speculative Drafts
2025
Cited
0
Computational Intractability of Strategizing against Online Learners
2025
Cited
0
Scaling Test-Time Compute Without Verification or RL is Suboptimal
2025
Cited
0
From Markov to Laplace: How Mamba In-Context Learns Markov Chains
2025
Cited
0
Resume (English only)
Co-authors
7 total
Kannan Ramchandran
Kannan Ramchandran
Professor of Electrical Engineering and Computer Science, UC Berkeley
Jiantao Jiao
Jiantao Jiao
Director of Research & Distinguished Scientist, NVIDIA; Professor of EECS and Stat, UC Berkeley
Swanand R. Kadhe
Swanand R. Kadhe
IBM Research
Lin F. Yang (杨林)
Lin F. Yang (杨林)
Assistant Professor, Department of Electrical and Computer Engineering @ UCLA
Yanjun Han
Yanjun Han
Assistant Professor, New York University
pranjal awasthi
pranjal awasthi
Google
Co-author 7
Co-author 7