Scholar
Sambit Sahu
Google Scholar ID: lhCvmjkAAAAJ
Capital One
Generative AI
LLM Pre-training
Inference Optimization
Follow
Google Scholar
↗
Citations & Impact
All-time
Citations
3,434
H-index
30
i10-index
93
Publications
20
Co-authors
0
Contact
No contact links provided.
Publications
28 items
When Load-Balancing Goes Too Far: Expert Pruning in Over-Dispersed Mixture-of-Experts Models
2026
Cited
0
The Rise of Verbal Reinforcement Learning
2026
Cited
0
AREAs-Lab: An Interactive Environment for AI-driven Requirement Elicitation for AI Systems
2026
Cited
0
StreamHear: Domain-Adapted Pseudo-Labeling for Semi-Supervised Streaming Speech Recognition
2026
Cited
0
Efficient Reinforcement Learning for Long-Horizon Tool-Use Agentic Tasks
2026
Cited
0
Structured Thoughts For Improved Reasoning And Context Pruning
2026
Cited
0
Know When to Stop: Segment-Level Credit Assignment for Reducing Overthinking
2026
Cited
0
SEAD: Competence-Aware On-Policy Distillation via Entropy-Guided Supervision
2026
Cited
0
Load more
Resume (English only)
Co-authors
0 total
Co-authors: 0 (list not available)
