ZZ
Zhuosheng Zhang
cs.CLcs.AIcs.LGcs.HCcs.CRcs.CVcs.IRArtificial Intelligencecs.MAcs.CY
On Valency
published · living versionsW_34j8mh82·v1 · currentpublished
Zooming without Zooming v2: From Seeing Details to Connecting Evidence for Generalizable Multimodal Perception
with Lai Wei, Yatai Li, Liangbo He, Jun Lan +8
1 version
Preprints & journals
139 papers in the corpus · 2018–2026Do GUI Agents Know When Not to Act? Enabling Conflict-Aware Termination for Multimodal GUI Agents2609.03438v1 · Zhaoyuan Huang, Tianjie Ju, Pengzhou Cheng et al.2026 · 0 citationsarXiv
Beyond a Single Judge: The Evidence-Grounded, Social-Weighted Persona Panel for Generative UI Evaluation2607.28439v2 · Zheng Wu, Yibo Luo, Pu Zhang et al.2026 · 0 citationsarXiv
Would You Walk to the Car Wash? Salience Bias in LLM Commonsense Reasoning2607.28478v2 · Zheng Wu, Chenhao Xue, Shijie Zheng et al.2026 · 0 citationsarXiv
Retrospective Progress-Aware Self-Refinement for LLM Agent Training2606.14302v2 · Xinbei Ma, Congmin Zheng, Jiyang Qiu et al.2026 · 0 citationsarXiv
Communication Policy Evolution for Proactive LLM Agents2606.14314v1 · Xinbei Ma, Jiyang Qiu, Yao Yao et al.2026 · 0 citationsarXiv
DiG-Plan: Mitigating Early Commitment for Tool-Graph Planning via Diffusion Guidance2606.05728v1 · Yansi Li, Zhuosheng Zhang2026 · 0 citationsarXiv
Mobile-Aptus: Confidence-Driven Proactive and Robust Interaction in MLLM-based Mobile-Using Agents2605.28629v1 · Zheng Wu, Pengzhou Cheng, Zongru Wu et al.2026 · 0 citationsarXiv
SE-GA: Memory-Augmented Self-Evolution for GUI Agents2605.16883v1 · Shilong Jin, Lanjun Wang, Zhuosheng Zhang2026 · 0 citationsarXiv
OS-SPEAR: A Toolkit for the Safety, Performance,Efficiency, and Robustness Analysis of OS Agents2604.24348v1 · Zheng Wu, Yi Hua, Zhaoyuan Huang et al.2026 · 0 citationsarXiv
Discourse-Aware Language Representation.41086082 · Zhang, Zhuosheng, Ouyang, Siru, Zhao, Hai2026 · 1 citationIEEE transactions on pattern analysis and machine intelligence. 2026;48(2):1888-1903
On the Overscaling Curse of Parallel Thinking: System Efficacy Contradicts Sample Efficiency2601.21619v2 · Yiming Wang, Zhuosheng Zhang, Rui Wang2026 · 0 citationsarXiv
Generalizable and Adaptive Continual Learning Framework for AI-generated Image Detection2601.05580v1 · Hanyi Wang, Jun Lan, Yaoyu Kang et al.2026 · 0 citationsarXiv
Agent-Dice: Disentangling Knowledge Updates via Geometric Consensus for Agent Continual Learning2601.03641v4 · Zheng Wu, Xingyu Lou, Xinbei Ma et al.2026 · 0 citationsarXiv
An LLM-based Quantitative Framework for Evaluating High-Stealthy Backdoor Risks in OSS Supply Chains2511.13341v1 · Zihe Yan, Kai Luo, Haoyu Yang et al.2025 · 0 citationsarXiv
Beyond Elicitation: Provision-based Prompt Optimization for Knowledge-Intensive Tasks2511.10465v2 · Yunzhe Xu, Zhuosheng Zhang, Zhe Liu2025 · 0 citationsarXiv
ColorEcosystem: Powering Personalized, Standardized, and Trustworthy Agentic Service in massive-agent Ecosystem2510.21566v2 · Fangwen Wu, Zheng Wu, Jihong Wang et al.2025 · 0 citationsarXiv
ColorBench: Benchmarking Mobile Agents with Graph-Structured Framework for Complex Long-Horizon Tasks2510.14621v1 · Yuanyi Song, Heyuan Huang, Qiqiang Lin et al.2025 · 0 citationsarXiv
Chain-of-Trigger: An Agentic Backdoor that Paradoxically Enhances Agentic Robustness2510.08238v1 · Jiyang Qiu, Xinbei Ma, Yunqing Xu et al.2025 · 0 citationsarXiv
Say One Thing, Do Another? Diagnosing Reasoning-Execution Gaps in VLM-Powered Mobile-Use Agents2510.02204v1 · Lingzhong Dong, Ziqi Zhou, Shuaibo Yang et al.2025 · 0 citationsarXiv
Reasoning or Rambling? Exploring the Effect of Thinking on Agent Persuasion2509.21054v3 · Haodong Zhao, Jidong Li, Zhaomin Wu et al.2025 · 0 citationsarXiv
Risks of AI scientists: prioritizing safeguarding over autonomy.40968279 · Tang, Xiangru, Jin, Qiao, Zhu, Kunlun et al.2025 · 53 citationsNature communications. 2025;16(1):8317
See, Think, Act: Teaching Multimodal Agents to Effectively Interact with GUI by Identifying Toggles2509.13615v5 · Zongru Wu, Rui Mao, Zhiyuan Tian et al.2025 · 1 citationarXiv
VeriOS: Query-Driven Proactive Human-Agent-GUI Interaction for Trustworthy OS Agents2509.07553v3 · Zheng Wu, Heyuan Huang, Xingyu Lou et al.2025 · 0 citationsarXiv
Quick on the Uptake: Eliciting Implicit Intents from Human Demonstrations for Personalized Mobile-Use Agents2508.08645v3 · Zheng Wu, Heyuan Huang, Yanjia Yang et al.2025 · 0 citationsarXiv
Atomic-to-Compositional Generalization for Mobile Agents with A New Benchmark and Scheduling System2506.08972v1 · Yuan Guo, Tingjia Miao, Zheng Wu et al.2025 · 0 citationsarXiv
On the Adaptive Psychological Persuasion of Large Language Models2506.06800v1 · Tianjie Ju, Yujia Chen, Hao Fei et al.2025 · 0 citationsarXiv
DeepTheorem: Advancing LLM Reasoning for Theorem Proving Through Natural Language and Reinforcement Learning2505.23754v2 · Ziyin Zhang, Jiahao Xu, Zhiwei He et al.2025 · 0 citationsarXiv
EVA: Evolving Semantic Adversaries for Red-Teaming GUI Agents Against Environmental Injection Attacks2505.14289v2 · Yijie Lu, Manman Zhao, Tianjie Ju et al.2025 · 0 citationsarXiv
Hidden Ghost Hand: Unveiling Backdoor Vulnerabilities in MLLM-Powered Mobile GUI Agents2505.14418v3 · Pengzhou Cheng, Haowen Hu, Zheng Wu et al.2025 · 1 citationarXiv
GEM: Gaussian Embedding Modeling for Out-of-Distribution Detection in GUI Agents2505.12842v4 · Zheng Wu, Pengzhou Cheng, Zongru Wu et al.2025 · 1 citationarXiv
GuideBench: Benchmarking Domain-Oriented Guideline Following for LLM Agents2505.11368v2 · Lingxiao Diao, Xinyue Xu, Wanxuan Sun et al.2025 · 1 citationarXiv
Revisiting Data Auditing in Large Vision-Language Models2504.18349v1 · Hongyu Zhu, Sichu Liang, Wenwen Wang et al.2025 · 3 citationsarXiv
DeepMath-103K: A Large-Scale, Challenging, Decontaminated, and Verifiable Mathematical Dataset for Advancing Reasoning2504.11456v2 · Zhiwei He, Tian Liang, Jiahao Xu et al.2025 · 1 citationarXiv
Dancing with Critiques: Enhancing LLM Reasoning with Stepwise Natural Language Self-Critique2503.17363v1 · Yansi Li, Jiahao Xu, Tian Liang et al.2025 · 0 citationsarXiv
Watch Out Your Album! On the Inadvertent Privacy Memorization in Multi-Modal Large Language Models2503.01208v2 · Tianjie Ju, Yi Hua, Hao Fei et al.2025 · 1 citationarXiv
Sampling-Efficient Test-Time Scaling: Self-Estimating the Best-of-N Sampling in Early Decoding2503.01422v3 · Yiming Wang, Pei Zhang, Siyuan Huang et al.2025 · 0 citationsarXiv
How Deep is Love in LLMs' Hearts? Exploring Semantic Size in Human-like Cognition2503.00330v1 · Yao Yao, Yifei Yang, Xinbei Ma et al.2025 · 0 citationsarXiv
Smoothing Grounding and Reasoning for MLLM-Powered GUI Agents with Query-Oriented Pivot Tasks2503.00401v2 · Zongru Wu, Pengzhou Cheng, Zheng Wu et al.2025 · 0 citationsarXiv
OS-Kairos: Adaptive Interaction for MLLM-Powered GUI Agents2503.16465v3 · Pengzhou Cheng, Zheng Wu, Zongru Wu et al.2025 · 4 citationsarXiv
When Disagreements Elicit Robustness: Investigating Self-Repair Capabilities under LLM Multi-Agent Disagreements2502.15153v2 · Tianjie Ju, Bowen Wang, Hao Fei et al.2025 · 0 citationsarXiv
Plan-over-Graph: Towards Parallelable LLM Agent Schedule2502.14563v1 · Shiqi Zhang, Xinbei Ma, Zouying Cao et al.2025 · 0 citationsarXiv
Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs2501.18585v2 · Yue Wang, Qiuzhi Liu, Jiahao Xu et al.2025 · 0 citationsarXiv
Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs2412.21187v2 · Xingyu Chen, Jiahao Xu, Tian Liang et al.2024 · 3 citationsarXiv
Look Before You Leap: Enhancing Attention and Vigilance Regarding Harmful Content with GuidelineLLM2412.10423v2 · Shaoqing Zhang, Zhuosheng Zhang, Kehai Chen et al.2024 · 0 citationsarXiv
Gracefully Filtering Backdoor Samples for Generative Large Language Models without Retraining2412.02454v1 · Zongru Wu, Pengzhou Cheng, Lingyong Fang et al.2024 · 1 citationarXiv
NSmark: Null Space Based Black-box Watermarking Defense Framework for Language Models2410.13907v2 · Haodong Zhao, Jinming Hu, Peixuan Li et al.2024 · 0 citationsarXiv
Dynamic Planning for LLM-based Graphical User Interface Automation2410.00467v3 · Shaoqing Zhang, Zhuosheng Zhang, Kehai Chen et al.2024 · 10 citationsarXiv
MEGen: Generative Backdoor into Large Language Models via Model Editing2408.10722v2 · Jiyang Qiu, Xinbei Ma, Zhuosheng Zhang et al.2024 · 3 citationsarXiv
Caution for the Environment: Multimodal LLM Agents are Susceptible to Environmental Distractions2408.02544v3 · Xinbei Ma, Yiting Wang, Yao Yao et al.2024 · 4 citationsarXiv
DOCBENCH: A Benchmark for Evaluating LLM-based Document Reading Systems2407.10701v1 · Anni Zou, Wenhao Yu, Hongming Zhang et al.2024 · 13 citationsarXiv
Career total: at least 199 works. 139 are in this corpus.Showing the 50 most recent.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.