Yancheng Long

Pre-indexing hours of video is a computational dead end—growing an online, query-driven textual memory tree during inference matches offline accuracy without the upfront processing tax.

Fine-grained spatial feedback can dramatically enhance image editing quality, outperforming traditional methods that rely on whole-image rewards.

Achieving lossless processing of 256K contexts, Keye-VL-2.0 transforms how we approach long-video understanding and agentic intelligence.

Key contribution not extracted.

Achieve scalable and consistent multi-reference image editing by dynamically serializing reference images into a coherent latent sequence, outperforming existing diffusion-based methods.