Scholar

Rohan Surana

Google Scholar ID: hobIUIcAAAAJ

University Of California, San Diego

Google Scholar↗

Citations & Impact

All-time

Citations

16

H-index

2

i10-index

1

Publications

7

Co-authors

6

list available

Publications

13 items

RRPO: Reference-Relative Policy Optimization with Stratified Conditional Rollouts

2026

Cited

0

Can We Break LLMs Out of Self-Loops? Fine-Grained Reasoning Control with Activation Steering

2026

Cited

0

F-GRPO: Factorized Group-Relative Policy Optimization for Unified Candidate Generation and Ranking

2026

Cited

0

MASS-DPO: Multi-negative Active Sample Selection for Direct Policy Optimization

2026

Cited

0

Skill-R1: Agent Skill Evolution via Reinforcement Learning

2026

Cited

0

Skill-CMIB: Multimodal Agent Skill for Consistent Action via Conditional Multimodal Information Bottleneck

2026

Cited

0

WS-GRPO: Weakly-Supervised Group-Relative Policy Optimization for Rollout-Efficient Reasoning

2026

Cited

0

AMPS: Adaptive Modality Preference Steering via Functional Entropy

2026

Cited

0

Co-authors

5 total

Professor, UC San Diego

University of California San Diego

Prithviraj Ammanabrolu

Assistant Professor, University of California, San Diego

University of California San Diefo