PPaperPicks

Junjie Wang

Chinese Academy of Sciences, Laboratory for Internet Software Technologies, Institute of Software, Beijing, China

18 papers at tracked venues · 15 at CORE A* · active 2024–2026

DBLP profile ↗ORCID 0000-0002-9941-6713 ↗Homepage ↗

Venues

ACL ×10AAAI ×4EMNLP ×2CHI ×1NAACL ×1

Frequent coauthors

Zhiyuan Chang
DBLP profile ↗ORCID search ↗
×4
Jianming Chen
DBLP profile ↗ORCID search ↗
×3
Ziyou Jiang
DBLP profile ↗ORCID search ↗
×2
Jie Huang
DBLP profile ↗ORCID search ↗
×2
Yawen Wang
DBLP profile ↗ORCID search ↗
×1
Haowei Wang
DBLP profile ↗ORCID search ↗
×1
Zhuohao Yu
DBLP profile ↗ORCID search ↗
×1
Pengxiang Liu
DBLP profile ↗ORCID search ↗
×1
Mengzhuo Chen
DBLP profile ↗ORCID search ↗
×1
Rupeng Zhang
DBLP profile ↗ORCID search ↗
×1
Zhe Liu
DBLP profile ↗ORCID search ↗
×1

Papers

  1. Adversarial Attack on Black-Box Multi-Agent by Adaptive Perturbation
    AAAI 2026 ·
    Jianming Chen
    DBLP profile ↗ORCID search ↗
  2. All Changes May Have Invariant Principles: Improving Ever-Shifting Harmful Meme Detection via Design Concept Reproduction
    ACL 2026 ·
    Ziyou Jiang
    DBLP profile ↗ORCID search ↗
  3. DEFT: Demystifying VLN Failures via a Unified Dual-View Explainability Framework for LLM-based Agents
    ACL 2026 ·
    Yawen Wang
    DBLP profile ↗ORCID search ↗
  4. Generative Text-to-Image Retrieval via Hierarchical Identifiers and Semantic Internalization
    ACL 2026 ·
    Jie Huang
    DBLP profile ↗ORCID search ↗
  5. Joint-GCG: Unified Gradient-Based Poisoning Attacks on Retrieval-Augmented Generation Systems
    AAAI 2026 ·
    Haowei Wang
    DBLP profile ↗ORCID search ↗
  6. Know Thy Enemy: Securing LLMs Against Prompt Injection via Diverse Data Synthesis and Instruction-Level Chain-of-Thought Learning
    ACL 2026 ·
    Zhiyuan Chang
    DBLP profile ↗ORCID search ↗
  7. Many Minds, One Path: LLM-Augmented Consensus Decision for Distributed Control in Multi-Agent Collaborative Stable Scenarios
    AAAI 2026 ·
    Zhuohao Yu
    DBLP profile ↗ORCID search ↗
  8. OntoGuard: Enforcing Action Admissibility for LLM Agents in Complex Interactive Environments
    ACL 2026 ·
    Pengxiang Liu
    DBLP profile ↗ORCID search ↗
  9. SAGE: Synergistic Adaptive Gating of Experts for Hateful Video Detection
    ACL 2026 ·
    Jie Huang
    DBLP profile ↗ORCID search ↗
  10. Seeing the Whole Elephant: A Benchmark for Failure Attribution in LLM-based Multi-Agent Systems
    ACL 2026 ·
    Mengzhuo Chen
    DBLP profile ↗ORCID search ↗
  11. Where Did It Go Wrong? Capability-Oriented Failure Attribution for Vision-and-Language Navigation Agents
    ACL 2026 ·
    Jianming Chen
    DBLP profile ↗ORCID search ↗
  12. From Allies to Adversaries: Manipulating LLM Tool-Calling through Adversarial Injection
    NAACL 2025 ·
    Rupeng Zhang
    DBLP profile ↗ORCID search ↗
  13. Mimicking the Familiar: Dynamic Command Generation for Information Theft Attacks in LLM Tool-Learning System
    ACL 2025 ·
    Ziyou Jiang
    DBLP profile ↗ORCID search ↗
  14. One Shot Dominance: Knowledge Poisoning Attack on Retrieval-Augmented Generation Systems
    EMNLP 2025 ·
    Zhiyuan Chang
    DBLP profile ↗ORCID search ↗
  15. Understanding Individual Agent Importance in Multi-Agent System via Counterfactual Reasoning
    AAAI 2025 ·
    Jianming Chen
    DBLP profile ↗ORCID search ↗
  16. Play Guessing Game with LLM: Indirect Jailbreak Attack with Implicit Clues
    ACL 2024 ·
    Zhiyuan Chang
    DBLP profile ↗ORCID search ↗
  17. Repairing Catastrophic-Neglect in Text-to-Image Diffusion Models via Attention-Guided Feature Enhancement
    EMNLP 2024 ·
    Zhiyuan Chang
    DBLP profile ↗ORCID search ↗
  18. Unblind Text Inputs: Predicting Hint-text of Text Input in Mobile Apps via LLM
    CHI 2024 ·
    Zhe Liu
    DBLP profile ↗ORCID search ↗