collaborators

7 papers

cs.CV2026

UltraCUA: A Foundation Model for Computer Use Agents with Hybrid Action

Yuhao Yang, Zhen Yang, Zi-Yi Dou +10

Computer-use agents face a fundamental limitation. They rely exclusively on primitive GUI actions (click, type, scroll), creating brittle execution chains prone to cascading failur…

cs.AI2026

Learning Structured Reasoning via Tractable Trajectory Control

Po-Nien Kung, Zhen Yang, Jeffrey Luo +7

Large language models can exhibit emergent reasoning behaviors, often manifested as recurring lexical patterns (e.g., "wait," indicating verification). However, complex reasoning t…

cs.AI2025

VaPR -- Vision-language Preference alignment for Reasoning

Rohan Wadhawan, Fabrice Y Harel-Canada, Zi-Yi Dou +3

Preference finetuning methods like Direct Preference Optimization (DPO) with AI-generated feedback have shown promise in aligning Large Vision-Language Models (LVLMs) with human pr…

cs.CV2025

Ferret-UI Lite: Lessons from Building Small On-Device GUI Agents

Zhen Yang, Zi-Yi Dou, Di Feng +13

Developing autonomous agents that effectively interact with Graphic User Interfaces (GUIs) remains a challenging open problem, especially for small on-device models. In this paper,…

cs.CV2025

MANZANO: A Simple and Scalable Unified Multimodal Model with a Hybrid Vision Tokenizer

Yanghao Li, Rui Qian, Bowen Pan +24

Unified multimodal Large Language Models (LLMs) that can both understand and generate visual content hold immense potential. However, existing open-source models often suffer from…

cs.CL2025

Re-ReST: Reflection-Reinforced Self-Training for Language Agents

Zi-Yi Dou, Cheng-Fu Yang, Xueqing Wu +2

Finetuning language agents with reasoning-action trajectories is effective, but obtaining these trajectories from human annotations or stronger models is costly and sometimes impra…