Han Lin
4 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
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.
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.
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.
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.
Papers
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…