Qin, Haotong
32 publications
NeurIPS
2025
$\text{S}^2$Q-VDiT: Accurate Quantized Video Diffusion Transformer with Salient Data and Sparse Token Distillation
NeurIPS
2025
Exploring Semantic-Constrained Adversarial Example with Instruction Uncertainty Reduction
AAAI
2025
ODDN: Addressing Unpaired Data Challenges in Open-World Deepfake Detection on Online Social Networks