Dazhao Du

HKUST

Papers on Lattice

Total citations

Topics

h-index

Publication activitypapers/week, last 8 weeks

Research focus

Computer Vision (2)Tool Use & Agents (2)Multimodal Models (1)RLHF & Preference Learning (1)

Frequent co-authors

Yao Fan (1)Tao Han (1)Andy J. Ma (1)Jia Wan (1)

Papers (2)

May 28, 2026

May 28, 2026·also HKUST

Train the Agent, Not the Expert: Learning to Harness Heterogeneous Experts for Multi-Turn Visual Reasoning

Forget end-to-end training for complex vision tasks; VisHarness shows that a lightweight agent can outperform task-specific models by learning to orchestrate a diverse set of pre-trained visual experts.

Yao Fan, Tao Han, Dazhao Du +2

Computer Vision Multimodal Models Tool Use & Agents

Apr 30, 2026

Apr 30, 2026·also HKUST, SJTU, Tencent AI, The Hong Kong University

GUI Agents with Reinforcement Learning: Toward Digital Inhabitants

Forget tedious, brittle automation scripts: RL-powered GUI agents are showing signs of "System 2" reasoning without explicit supervision, hinting at a future of truly intelligent digital inhabitants.

Junan Hu, Jin-Shei Lai, Jingxiang Lai +6

Computer Vision RLHF & Preference Learning Tool Use & Agents

Search

Dazhao Du

Publication activitypapers/week, last 8 weeks

Research focus

Frequent co-authors

Papers (2)