Boyang Li

REZE achieves a new state of the art in training-free video temporal grounding, outperforming fully supervised models in highlight detection and moment retrieval.

nD-RoPE achieves superior performance in high-dimensional contexts by ensuring isotropy and directionally balanced responses, challenging the limitations of traditional position embeddings.

Spotting AI-generated harms requires more than just image analysis: this system links images to their source even when paired with harmful text, enabling accountability.

Rethinking IRSTD as a centroid regression problem with single-point supervision achieves competitive detection performance with significantly reduced computational cost, challenging the dominance of pixel-level segmentation approaches.