Author

Qian Kou

Observed name: Kou, Qian

Institutions: Beijing Academy of Artificial Intelligence, Xi'an Jiaotong University

Observed institutions: Beijing Academy of Artificial Intelligence, Xi'an Jiaotong University

OpenAlex ID: A5137629515

Rethinking Supervised Fine-Tuning: Emphasizing Key Answer Tokens for Improved LLM Accuracy

2025 · Shi, Xiaofeng, Kou, Qian, et al. · arXiv (Cornell University) · 7

MechVQA: Benchmarking and Enhancing Multimodal LLMs on Comprehensive Mechanical Drawing Understanding

2026 · Kou, Qian, Shi, Xiaofeng, et al. · arXiv (Cornell University) · 3

RAFT: Data Refinement and Adaptive Distillation for Domain Fine-Tuning with Alleviated Forgetting

2026 · Li, Yuduo, Shi, Xiaofeng, et al. · arXiv (Cornell University) · 1

Improving sample efficiency in visual reinforcement learning under data augmentation

2026 · Ziru Wang, Wanli Jiang, et al. · Robot learning. · 1

Inject, Align, Recover: Staged Post-Training for Retrieval-Free Document Knowledge Internalization

2026 · Kou, Qian, Shi, Xiaofeng, et al. · arXiv (Cornell University)

Wnuan: Staged Post-Training for Question Answering over Proprietary Enterprise Knowledge

2026 · Shi, Xiaofeng, Qiu, Xiaosong, et al. · arXiv (Cornell University)

ChartWalker: Benchmarking the Cross-Chart RAG Task with Hierarchical Knowledge Graphs

2026 · Tang, Ning, Xie, Chenghan, et al. · arXiv (Cornell University)

Works count: 7

Citation count: 12

H-index: 2

I10-index: