PPaperPicks

Zhuosheng Zhang

Shanghai Jiao Tong University, Shanghai, China

43 papers at tracked venues · 34 at CORE A* · active 2024–2026

DBLP profile ↗ORCID 0000-0002-4183-3645 ↗Google Scholar ↗Homepage ↗

Venues

ACL ×18EMNLP ×5AAAI ×4ICML ×3NAACL ×3NeurIPS ×3ACM MM ×2ICLR ×2ECAI ×1ICCV ×1WWW ×1

Frequent coauthors

Xinbei Ma
DBLP profile ↗ORCID search ↗
×3
Pengzhou Cheng
DBLP profile ↗ORCID search ↗
×3
Zhiwei He
DBLP profile ↗ORCID search ↗
×3
Yiming Wang
DBLP profile ↗ORCID search ↗
×3
Zheng Wu
DBLP profile ↗ORCID search ↗
×2
Xiangru Tang
DBLP profile ↗ORCID search ↗
×2
Shaoqing Zhang
DBLP profile ↗ORCID search ↗
×2
Hongyu Zhu
DBLP profile ↗ORCID search ↗
×2
Tianjie Ju
DBLP profile ↗ORCID search ↗
×2
Siru Ouyang
DBLP profile ↗ORCID search ↗
×2
Zihe Yan
DBLP profile ↗ORCID search ↗
×1
Yuanyi Song
DBLP profile ↗ORCID search ↗
×1

Papers

  1. Agent-Dice: Disentangling Knowledge Updates via Geometric Consensus for Agent Continual Learning
    ACL 2026 ·
    Zheng Wu
    DBLP profile ↗ORCID search ↗
  2. An LLM-based Quantitative Framework for Evaluating High-Stealthy Backdoor Risks in OSS Supply Chains
    AAAI 2026 ·
    Zihe Yan
    DBLP profile ↗ORCID search ↗
  3. ColorBench: Benchmarking Mobile Agents with Graph-Structured Framework for Complex Long-Horizon Tasks
    WWW 2026 ·
    Yuanyi Song
    DBLP profile ↗ORCID search ↗
  4. ColorBrowserAgent: Complex Long-Horizon Browser Agent with Adaptive Knowledge Evolution
    ACL 2026 ·
    Jihong Wang
    DBLP profile ↗ORCID search ↗
  5. EVA: Evolving Semantic Adversaries for Red-Teaming GUI Agents Against Environmental Injection Attacks
    ACL 2026 ·
    Yijie Lu
    DBLP profile ↗ORCID search ↗
  6. GEM: Gaussian Embedding Modeling for Out-of-Distribution Detection in GUI Agents
    AAAI 2026 ·
    Zheng Wu
    DBLP profile ↗ORCID search ↗
  7. OS-Sentinel: Towards Safety-Enhanced Mobile GUI Agents via Hybrid Validation in Realistic Workflows
    ACL 2026 ·
    Qiushi Sun
    DBLP profile ↗ORCID search ↗
  8. ParaCook: On Time-Efficient Planning for Multi-Agent Systems
    ACL 2026 ·
    Shiqi Zhang
    DBLP profile ↗ORCID search ↗
  9. The Confidence Paradox: Unveiling the Latent Discriminative Power of Diffusion Large Language Models in Mathematical Reasoning
    ACL 2026 ·
    Yansi Li
    DBLP profile ↗ORCID search ↗
  10. Can Knowledge be Transferred from Unimodal to Multimodal? Investigating the Transitivity of Multimodal Knowledge Editing
    ICCV 2025 ·
    Lingyong Fang
    DBLP profile ↗ORCID search ↗
  11. Caution for the Environment: Multimodal LLM Agents are Susceptible to Environmental Distractions
    ACL 2025 ·
    Xinbei Ma
    DBLP profile ↗ORCID search ↗
  12. ChemAgent: Self-updating Memories in Large Language Models Improves Chemical Reasoning
    ICLR 2025 ·
    Xiangru Tang
    DBLP profile ↗ORCID search ↗
  13. Do NOT Think That Much for 2+3=? On the Overthinking of Long Reasoning Models
    ICML 2025 ·
    Xingyu Chen
    DBLP profile ↗ORCID search ↗
  14. GuideBench: Benchmarking Domain-Oriented Guideline Following for LLM Agents
    ACL 2025 ·
    Lingxiao Diao
    DBLP profile ↗ORCID search ↗
  15. Hidden Ghost Hand: Unveiling Backdoor Vulnerabilities in MLLM-Powered Mobile GUI Agents
    EMNLP 2025 ·
    Pengzhou Cheng
    DBLP profile ↗ORCID search ↗
  16. Look Before You Leap: Enhance Attention and Vigilance Regarding Harmful Content with GuidelineLLM
    AAAI 2025 ·
    Shaoqing Zhang
    DBLP profile ↗ORCID search ↗
  17. MEGen: Generative Backdoor into Large Language Models via Model Editing
    ACL 2025 ·
    Jiyang Qiu
    DBLP profile ↗ORCID search ↗
  18. OS-Kairos: Adaptive Interaction for MLLM-Powered GUI Agents
    ACL 2025 ·
    Pengzhou Cheng
    DBLP profile ↗ORCID search ↗
  19. RaSA: Rank-Sharing Low-Rank Adaptation
    ICLR 2025 ·
    Zhiwei He
    DBLP profile ↗ORCID search ↗
  20. Revisiting Data Auditing in Large Vision-Language Models
    ACM MM 2025 ·
    Hongyu Zhu
    DBLP profile ↗ORCID search ↗
  21. Sampling-Efficient Test-Time Scaling: Self-Estimating the Best-of-N Sampling in Early Decoding
    NeurIPS 2025 ·
    Yiming Wang
    DBLP profile ↗ORCID search ↗
  22. Stealing Knowledge from Auditable Datasets
    ECAI 2025 ·
    Hongyu Zhu
    DBLP profile ↗ORCID search ↗
  23. SynGhost: Invisible and Universal Task-agnostic Backdoor Attack via Syntactic Transfer
    NAACL 2025 ·
    Pengzhou Cheng
    DBLP profile ↗ORCID search ↗
  24. Thoughts Are All Over the Place: On the Underthinking of Long Reasoning Models
    NeurIPS 2025 ·
    Yue Wang
    DBLP profile ↗ORCID search ↗
  25. Watch Out Your Album! On the Inadvertent Privacy Memorization in Multi-Modal Large Language Models
    ICML 2025 ·
    Tianjie Ju
    DBLP profile ↗ORCID search ↗
  26. Acquiring Clean Language Models from Backdoor Poisoned Datasets by Downscaling Frequency Space
    ACL 2024 ·
    Zongru Wu
    DBLP profile ↗ORCID search ↗
  27. Can Watermarks Survive Translation? On the Cross-lingual Consistency of Text Watermark for Large Language Models
    ACL 2024 ·
    Zhiwei He
    DBLP profile ↗ORCID search ↗
  28. CoCo-Agent: A Comprehensive Cognitive MLLM Agent for Smartphone GUI Automation
    ACL 2024 ·
    Xinbei Ma
    DBLP profile ↗ORCID search ↗
  29. Dynamic Planning for LLM-based Graphical User Interface Automation
    EMNLP 2024 ·
    Shaoqing Zhang
    DBLP profile ↗ORCID search ↗
  30. Embedding Trajectory for Out-of-Distribution Detection in Mathematical Reasoning
    NeurIPS 2024 ·
    Yiming Wang
    DBLP profile ↗ORCID search ↗
  31. Fact-Driven Logical Reasoning for Machine Reading Comprehension
    AAAI 2024 ·
    Siru Ouyang
    DBLP profile ↗ORCID search ↗
  32. From Multimodal LLM to Human-level AI: Modality, Instruction, Reasoning and Beyond
    ACM MM 2024 ·
    Hao Fei
    DBLP profile ↗ORCID search ↗
  33. GLaPE: Gold Label-agnostic Prompt Evaluation for Large Language Models
    EMNLP 2024 ·
    Xuanchang Zhang
    DBLP profile ↗ORCID search ↗
  34. Improving Machine Translation with Human Feedback: An Exploration of Quality Estimation as a Reward Model
    NAACL 2024 ·
    Zhiwei He
    DBLP profile ↗ORCID search ↗
  35. Investigating Multi-Hop Factual Shortcuts in Knowledge Editing of Large Language Models
    ACL 2024 ·
    Tianjie Ju
    DBLP profile ↗ORCID search ↗
  36. Measuring Bargaining Abilities of LLMs: A Benchmark and A Buyer-Enhancement Method
    ACL 2024 ·
    Tian Xia
    DBLP profile ↗ORCID search ↗
  37. MedAgents: Large Language Models as Collaborators for Zero-shot Medical Reasoning
    ACL 2024 ·
    Xiangru Tang
    DBLP profile ↗ORCID search ↗
  38. Meta-Reasoning: Semantics-Symbol Deconstruction for Large Language Models
    ACL 2024 ·
    Yiming Wang
    DBLP profile ↗ORCID search ↗
  39. On the Robustness of Editing Large Language Models
    EMNLP 2024 ·
    Xinbei Ma
    DBLP profile ↗ORCID search ↗
  40. R-Judge: Benchmarking Safety Risk Awareness for LLM Agents
    EMNLP 2024 ·
    Tongxin Yuan
    DBLP profile ↗ORCID search ↗
  41. Self-Prompting Large Language Models for Zero-Shot Open-Domain QA
    NAACL 2024 ·
    Junlong Li
    DBLP profile ↗ORCID search ↗
  42. Structured Chemistry Reasoning with Large Language Models
    ICML 2024 ·
    Siru Ouyang
    DBLP profile ↗ORCID search ↗
  43. You Only Look at Screens: Multimodal Chain-of-Action Agents
    ACL 2024 · Zhuosheng Zhang