Tokyo

Zhen Li

Intermediate
@Lixsp11
lixsp11.github.io/

sekai-codebase. [NeurIPS 2025] Sekai: A Video Dataset towards World Exploration

301

UPDN_VQA. Implemention of the BUTD model proposed by paper "Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering" for VQA task

2

CompIL. [AAAI 2026] The official repository of "Composition-Incremental Learning for Compositional Generalization"

1

SeamCarving. C++ with opencv implementation of paper Seam Carving for Content-Aware Image Resizing

1
4
Apply