Zhengtao Yao

1. Seeing What Is Actually There: PriVE-Bench and PriVE-Tools for Counterfactual Evaluation of Agentic Visual Evidence in VLMs
   2026/07/14 by Jingyu Sun, Jiachen Tu, Yuyang Xue +8
   #cs.CV #cs.AI
2. Less Data, Better Alignment: Data-Centric Multi-Evaluator Agreement for Preference Optimization
   2026/07/27 by Zhengtao Yao, Runhao Li, Xupeng Chen +12
   #cs.AI
3. PreDiff-LM: Pretrained Discrete Masked Diffusion Language Modeling with Hybrid Attention
   2026/07/28 by Zhengtao Yao, Runhao Li, Xupeng Chen +12
   #cs.AI