Scholar
Yuki Ichihara
Google Scholar ID: qexbctUAAAAJ
Nara Institute of Science and Technology
Reinforcement Learning
NLP
Follow
Homepage
↗
Google Scholar
↗
Citations & Impact
All-time
Citations
18
H-index
2
i10-index
1
Publications
5
Co-authors
0
Publications
8 items
Prefix-Denoising Consistency: Test-Time Verification for Diffusion Language Models
2026
Cited
0
Privileged Solutions or Context-Induced Teacher Behavior? Dissecting On-Policy Self-Distillation
2026
Cited
0
Reliable Chain-of-Thought via Prefix Consistency
2026
Cited
0
CITE: Anytime-Valid Statistical Inference in LLM Self-Consistency
2026
Cited
0
Consensus Group Relative Policy Optimization for Text Generation
2026
Cited
0
MO-GRPO: Mitigating Reward Hacking of Group Relative Policy Optimization on Multi-Objective Problems
2025
Cited
0
Theoretical Guarantees for Minimum Bayes Risk Decoding
2025
Cited
0
Evaluation of Best-of-N Sampling Strategies for Language Model Alignment
2025
Cited
0
