3 papers
cs.CV2026
MuSS: A Large-Scale Dataset and Cinematic Narrative Benchmark for Multi-Shot Subject-to-Video Generation
Haojie Zhang, Di Wu, Bingyan Liu +5
While video foundation models excel at single-shot generation, real-world cinematic storytelling inherently relies on complex multi-shot sequencing. Further progress is constrained…
cs.CV2025
Patch-as-Decodable-Token: Towards Unified Multi-Modal Vision Tasks in MLLMs
Yongyi Su, Haojie Zhang, Shijie Li +11
Multimodal large language models (MLLMs) have advanced rapidly in recent years. However, existing approaches for vision tasks often rely on indirect representations, such as genera…
cs.LG2025
On the Adversarial Risk of Test Time Adaptation: An Investigation into Realistic Test-Time Data Poisoning
Yongyi Su, Yushu Li, Nanqing Liu +4
Test-time adaptation (TTA) updates the model weights during the inference stage using testing data to enhance generalization. However, this practice exposes TTA to adversarial risk…