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

Han Lin

4 indexed papers

Recent (6 mo)
4
With code
0
Influential cites
0
Benchmarked
0

Publications per year

4
26

Top categories

AI×4ML×2Vision×2NLP×2

Frequent co-authors

Hanyang Zhao2×
Haoxian Chen2×
Genta Indra Winata2×
David Yao2×
Wenpin Tang2×
Yue Zhang2×

Research Timeline

2026
Seeing Isn't Knowing: Do VLMs Know When Not to Answer Spatial Questions (and Why)?

This paper introduces a new evaluation framework, SpatialUncertain, demonstrating that current Vision-Language Models (VLMs) are prone to overconfident and incorrect answers to spatial questions when visual evidence is incomplete or misleading.

Seeing Isn't Knowing: Do VLMs Know When Not to Answer Spatial Questions (and Why)?

This paper introduces a new evaluation framework, SpatialUncertain, demonstrating that current Vision-Language Models (VLMs) are prone to overconfident and incorrect answers to spatial questions when visual evidence is incomplete or misleading.

OPD+: Rethinking the Advantage Design for On-Policy Distillation

The paper introduces OPD+, a corrected on-policy distillation framework that mathematically proves the bias of standard stop-gradient methods and improves the stability and performance of knowledge transfer from teacher to student models.

OPD+: Rethinking the Advantage Design for On-Policy Distillation

The paper introduces OPD+, a corrected on-policy distillation framework that mathematically proves the bias of standard stop-gradient methods and improves the stability and performance of knowledge transfer from teacher to student models.

Highlighted terms show continued research focus across papers

Papers

cs.LGcs.AIRecentMay 31, 2026

OPD+: Rethinking the Advantage Design for On-Policy Distillation

Hanyang Zhao, Haoxian Chen, Han Lin, Genta Indra Winata +2 more

The paper introduces OPD+, a corrected on-policy distillation framework that mathematically proves the bias of standard stop-gradient methods and improves the stability and performance of knowledge tr…

View →
cs.LGcs.AIRecentMay 31, 2026

OPD+: Rethinking the Advantage Design for On-Policy Distillation

Hanyang Zhao, Haoxian Chen, Han Lin, Genta Indra Winata +2 more

The paper introduces OPD+, a corrected on-policy distillation framework that mathematically proves the bias of standard stop-gradient methods and improves the stability and performance of knowledge tr…

View →
cs.CVcs.AIcs.CLRecentMay 28, 2026

Seeing Isn't Knowing: Do VLMs Know When Not to Answer Spatial Questions (and Why)?

Yue Zhang, Zun Wang, Han Lin, Yonatan Bitton +2 more

This paper introduces a new evaluation framework, SpatialUncertain, demonstrating that current Vision-Language Models (VLMs) are prone to overconfident and incorrect answers to spatial questions when…

View →
cs.CVcs.AIcs.CLRecentMay 28, 2026

Seeing Isn't Knowing: Do VLMs Know When Not to Answer Spatial Questions (and Why)?

Yue Zhang, Zun Wang, Han Lin, Yonatan Bitton +2 more

This paper introduces a new evaluation framework, SpatialUncertain, demonstrating that current Vision-Language Models (VLMs) are prone to overconfident and incorrect answers to spatial questions when…

View →