Safal Shrestha
Scholar

Safal Shrestha

Google Scholar ID: z6GjhUgAAAAJ
Research Assistant
LLMReasoningReinforcement Learning
Homepage↗Google Scholar↗
Citations & Impact
All-time
Citations
13
 
H-index
2
 
i10-index
1
 
Publications
4
 
Co-authors
0
 
Contact
Emailss13750@nyu.comCVOpen ↗GitHubOpen ↗
Publications
7 items
Mixture-of-Experts Language Models Can Be Strong and Efficient Retrievers
2026
Cited
0
On the Limits of Layer Pruning for Generative Reasoning in LLMs
2026
Cited
0
Training Reasoning Models on Saturated Problems via Failure-Prefix Conditioning
2026
Cited
0
Layer Importance for Mathematical Reasoning is Forged in Pre-Training and Invariant after Post-Training
2025
Cited
0
Reinforcement Learning vs. Distillation: Understanding Accuracy and Capability in LLM Reasoning
2025
Cited
0
Warm Up Before You Train: Unlocking General Reasoning in Resource-Constrained Settings
2025
Cited
0
Mathematical Reasoning in Large Language Models: Assessing Logical and Arithmetic Errors across Wide Numerical Ranges
2025
Cited
0
Resume
Research Experience
  • Working as a research assistant in the Deep Learning Lab at New York University Abu Dhabi.
Education
  • Studying at New York University Abu Dhabi under the supervision of Prof. Keith Ross.
Background
  • Research interests include LLM reasoning, generalizability of LLMs, and interpretability of reasoning and generalization in LLMs.
Miscellany
  • Website referenced from Jon Barron's source code.