Nanqing Liu

MuSS: A Large-Scale Dataset and Cinematic Narrative Benchmark for Multi-Shot Subject-to-Video Generation

arXiv 2026

Patch-as-Decodable-Token: Towards Unified Multi-Modal Vision Tasks in MLLMs

arXiv 2025

PS-TTL: Prototype-based Soft-labels and Test-Time Learning for Few-shot Object Detection

arXiv 2024

Haojie Zhang

Bingyan Liu

Chen Li

Chong Sun

Di Huang

Di wu

Jingyi Liao

Junyi Pan

Linjie Zhong

Nancy F. Chen