Scholar

Junhong Wu

Google Scholar ID: Ci4l4yQAAAAJ

PhD student, Institute of Automation, Chinese Academy of Sciences

Natural language processinglifelong learning

Google Scholar↗

Citations & Impact

All-time

Citations

124

H-index

5

i10-index

3

Publications

9

Co-authors

8

list available

Contact

No contact links provided.

Publications

8 items

Enough is as good as a feast: A Comprehensive Analysis of How Reinforcement Learning Mitigates Task Conflicts in LLMs

2026

Cited

0

Latent-GRPO: Group Relative Policy Optimization for Latent Reasoning

2026

Cited

0

Parallel Scaling Law: Unveiling Reasoning Generalization through A Cross-Linguistic Perspective

2025

Cited

0

Look Again, Think Slowly: Enhancing Visual Reflection in Vision-Language Models

2025

Cited

0

Emergent Hierarchical Reasoning in LLMs through Reinforcement Learning

2025

Cited

0

Implicit Cross-Lingual Rewarding for Efficient Multilingual Preference Alignment

2025

Cited

0

LADM: Long-context Training Data Selection with Attention-based Dependency Measurement for LLMs

2025

Cited

0

Language Imbalance Driven Rewarding for Multilingual Self-improving

arXiv.org · 2024

Cited

0

Resume (English only)

Co-authors

8 total

Chengqing Zong (宗成庆)

Institute of Automation, Chinese Academy of Sciences

Institute of Automation Chinese Academy of Sciences

Institute of Automation, Chinese Academy of Sciences

Institute of Automation Chinese Academy of Sciences

Distinguished Professor, University of Illinois at Chicago

Institute of Automation, Chinese Academy of Sciences