Papers by Biwei Huang

2 papers
C-World: A Computer Use Agent Environment Creator (2026.acl-long)

Copied to clipboard

Challenge: C-World enables users to build agent environments on demand.
Approach: They propose a system that enables users to build agent environments on demand.
Outcome: The proposed system outperforms baselines on 119k samples and achieves Spearman = 0.883 ranking correlation with real execution.
Hybrid Self-evolving Structured Memory for Computer-Use Agents (2026.findings-acl)

Copied to clipboard

Challenge: despite advances in vision–language models, real-world computer-use tasks remain challenging due to long-horizon workflows, diverse interfaces, and frequent intermediate errors.
Approach: They propose a graph-based memory that couples discrete symbolic nodes with continuous trajectory embeddings.
Outcome: The proposed system outperforms closed-source models in Qwen2.5-VL-7B and Gemini2.5-Pro-Vision on desktop and mobile platforms.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations