Tao Wang

Website fingerprinting attacks on Tor are still alarmingly effective in the real world, achieving >90% precision and recall even against realistic background noise and network jitter.

Forget backpropagation for test-time adaptation: FOZO achieves state-of-the-art accuracy with a memory-efficient, forward-only zeroth-order prompt optimization, even on quantized models.

Image-to-video models can now generate more consistent and expressive animated storyboards than static diffusion models, thanks to a Disney-inspired multi-agent framework.

LLMs can generate unbiased pseudo-labels for unexposed items in pre-ranking, boosting click-through rate by 3.07% in production while improving diversity.