Jiangning Zhang
3 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
The paper proposes ST-DRC, a Spatial-Temporal Decoupled Reference Conditioning framework that effectively balances high-level semantic control and low-level identity fidelity for text-to-video generation.
The paper proposes ST-DRC, a Spatial-Temporal Decoupled Reference Conditioning framework that effectively balances high-level semantic control and low-level identity fidelity for text-to-video generation.
This paper introduces SPOT-E, a plug-and-play test-time method that improves the performance of vision-language models on evidence-intensive tasks by producing question-conditioned spotlights.
Papers
SPOT-E: Test-Time Entropy Shaping with Visual Spotlights for Frozen VLMs
Bo Yin, Xiaobin Hu, Chengming Xu, Ruolin Shen +5 more
This paper introduces SPOT-E, a plug-and-play test-time method that improves the performance of vision-language models on evidence-intensive tasks by producing question-conditioned spotlights.