collaborators

7 papers

cs.CL2026

A Task-State Representation for Long-Horizon Mobile GUI Agents

Yujie Zheng, Zikang Liu, Xin Zhao +1

While long-horizon mobile GUI agents typically rely on thought-action-observation loops, they struggle to separate persistent task states from transient screen observations. As exe…

cs.CV2026

Towards Long-horizon Agentic Multimodal Search

Yifan Du, Zikang Liu, Jinbiao Peng +5

Multimodal deep search agents have shown great potential in solving complex tasks by iteratively collecting textual and visual evidence. However, managing the heterogeneous informa…

cs.IR2026

Think Before Writing: Feature-Level Multi-Objective Optimization for Generative Citation Visibility

Zikang Liu, Peilan Xu

Generative answer engines expose content through selective citation rather than ranked retrieval, fundamentally altering how visibility is determined. This shift calls for new opti…

cs.CV2026

Beyond the Last Frame: Process-aware Evaluation for Generative Video Reasoning

Yifan Li, Yukai Gu, Yingqian Min +6

Recent breakthroughs in video generation have demonstrated an emerging capability termed Chain-of-Frames (CoF) reasoning, where models resolve complex tasks through the generation…

cs.CV2025

PAL-UI: Planning with Active Look-back for Vision-Based GUI Agents

Zikang Liu, Junyi Li, Wayne Xin Zhao +3

Graphical User Interface (GUI) agents powered by Multimodal Large Language Models (MLLMs) promise human-like interaction with software applications, yet long-horizon tasks remain c…

cs.CL2025

Do we Really Need Visual Instructions? Towards Visual Instruction-Free Fine-tuning for Large Vision-Language Models

Zikang Liu, Kun Zhou, Wayne Xin Zhao +3

Visual instruction tuning has become the predominant technology in eliciting the multimodal task-solving capabilities of large vision-language models (LVLMs). Despite the success,…