Baifeng Shi

10

Papers

156

Total Citations

Papers (10)

LLM-grounded Video Diffusion Models

When Do We Not Need Larger Vision Models?

Recursive Visual Programming

Top-Down Visual Attention From Analysis by Synthesis

Temporal Action Detection With Multi-Level Supervision

Weakly-Supervised Action Localization with Expectation-Maximization Multi-Instance Learning

Scaling Vision Pre-Training to 4K Resolution

NVILA: Efficient Frontier Visual Language Models

Weakly-Supervised Action Localization by Generative Attention Modeling

Auxiliary Task Reweighting for Minimum-data Learning