Xin Lin

Unified Agent outperforms existing multi-agent systems by effectively maintaining a compact state across devices and time, revolutionizing user-agent interactions.

Proprietary MLLMs excel in chart annotation, but open-source models are rapidly catching up, especially with clearer instructions.

Local Margin Restoration not only shields VLMs from bias but also preserves their semantic integrity, leading to superior performance in dynamic environments.

Achieving high-quality 3D object selection with minimal user input and computational cost, GaussianSelector redefines the efficiency of scene editing.

Dense prediction can achieve state-of-the-art performance by leveraging generative pretraining without the overhead of RGB content generation.