Teng Wang

With the advancement of vision-language models, web automation has made significant progress. However, deploying autonomous agents in real-world settings remains challenging, primarily due to site heterogeneity, where generalist models lack domain-specific priors for diverse interfaces, and long-...

Large Language Models (LLMs) have demonstrated strong mathematical reasoning abilities through supervised fine-tuning and reinforcement learning. However, existing Process Reward Models (PRMs) are vulnerable to reward hacking and require expensive, large-scale annotation of reasoning steps, limit...

Scoring models such as click-through rate (CTR) prediction underpin recommendation and advertising systems, but their features are highly sensitive, making plaintext cloud inference risky. Fully homomorphic encryption (FHE) enables inference directly on ciphertexts, yet homomorphic computation is...