Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Xiaofeng Shi

Xiaofeng Shi

2 indexed papers

Recent (6 mo)
2
With code
0
Influential cites
0
Benchmarked
0

Publications per year

2
26

Top categories

AI×2Vision×1ML×1

Frequent co-authors

Qian Kou2×
Hua Zhou2×
Yulin Li1×
Xiaosong Qiu1×
Xinyang Wang1×
Cao Dongxing1×

Research Timeline

2026
MechVQA: Benchmarking and Enhancing Multimodal LLMs on Comprehensive Mechanical Drawing Understanding

The paper introduces MechVQA, a comprehensive dataset and benchmark for mechanical drawing understanding, and proposes the MechVL model, which significantly improves Multimodal LLMs' performance on these specialized tasks.

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

RAFT proposes a two-stage framework combining data refinement and adaptive distillation to improve domain-specific fine-tuning while mitigating the loss of general model capabilities.

Highlighted terms show continued research focus across papers

Papers

cs.CVcs.AIRecentMay 29, 2026

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

Qian Kou, Xiaofeng Shi, Yulin Li, Xiaosong Qiu +3 more

The paper introduces MechVQA, a comprehensive dataset and benchmark for mechanical drawing understanding, and proposes the MechVL model, which significantly improves Multimodal LLMs' performance on th…

View →
cs.LGcs.AIRecentMay 29, 2026

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

Yuduo Li, Xiaofeng Shi, Qian Kou, Longbin Yu +1 more

RAFT proposes a two-stage framework combining data refinement and adaptive distillation to improve domain-specific fine-tuning while mitigating the loss of general model capabilities.

View →