Junjie Wang

44 papers · 2019–2026 · 12 conferences · across top CS/AI conferences

Achievements

+10 more ↓

🏃 Academic Marathon (6) 🌉 Interdisciplinary Bridge 🧭 Keyword Pioneer 🌍 Conference Polyglot (12) 🐝 Cross-Pollinator (12)

🐣 Hot Topic Early Bird 🏃 Academic Marathon (6) 🧭 Keyword Pioneer 🧬 Topic Evolution 🔥 Unstoppable (5) 🚀 Conference Pioneer 💎 Century Club (34) ⚡ Prolific Year (9) 📈 Trend Setter 🗃️ Keyword Collector (199)

Conferences

ACL (11) AAAI (8) EMNLP (8) CVPR (5) ICCV (3) ICLR (2) INTERSPEECH (2) ACML (1) MICCAI (1) NAACL (1) NIPS (1) WACV (1)

Top co-authors

Qing Wang (13) Yujiu Yang (8) Mingyang Li (8) Yuxiang Zhang (6) Zhiyuan Chang (5) Xinyu Zhu (5) Yuekai Huang (5) Ziyou Jiang (4) Jiaxing Zhang (4) Tetsuya Sakai (4)

Research topics

Reasoning (1)

Keywords

large language model (9) multi-agent system (5) adversarial attack (5) diffusion model (4) retrieval-augmented generation (3) unsupervised learning (3) multimodal learning (3) contrastive learning (3) llm security (2) 3d gaussian splatting (2) vision-language model (2) text-to-image generation (2) zero-shot learning (2) human pose estimation (2) knowledge graph (2) question answering (2) data augmentation (2) attention mechanism (2) knowledge distillation (2) person re-identification (2)

Papers

Seeing the Whole Elephant: A Benchmark for Failure Attribution in LLM-based Multi-Agent Systems ACL 2026 SAGE: Synergistic Adaptive Gating of Experts for Hateful Video Detection ACL 2026 All Changes May Have Invariant Principles: Improving Ever-Shifting Harmful Meme Detection via Design Concept Reproduction ACL 2026 Joint-GCG: Unified Gradient-Based Poisoning Attacks on Retrieval-Augmented Generation Systems AAAI 2026 Adversarial Attack on Black-Box Multi-Agent by Adaptive Perturbation AAAI 2026 DEFT: Demystifying VLN Failures via a Unified Dual-View Explainability Framework for LLM-based Agents ACL 2026 WebClipper: Efficient Evolution of Web Agents with Graph-based Trajectory Pruning ACL 2026 Many Minds, One Path: LLM-Augmented Consensus Decision for Distributed Control in Multi-Agent Collaborative Stable Scenarios AAAI 2026 O-DisCo-Edit: Object Distortion Control for Unified Realistic Video Editing AAAI 2026 SpecQuant: Spectral Decomposition and Adaptive Truncation for Ultra-Low-Bit LLMs Quantization AAAI 2026 Identity-Clothing Similarity Modeling for Unsupervised Clothing Change Person Re-Identification CVPR 2025 DeCLIP: Decoupled Learning for Open-Vocabulary Dense Perception CVPR 2025 OV-DQUO: Open-Vocabulary DETR with Denoising Text Query Training and Open-World Unknown Objects Supervision AAAI 2025 Mimicking the Familiar: Dynamic Command Generation for Information Theft Attacks in LLM Tool-Learning System ACL 2025 One Shot Dominance: Knowledge Poisoning Attack on Retrieval-Augmented Generation Systems EMNLP 2025 Augmented and Softened Matching for Unsupervised Visible-Infrared Person Re-Identification ICCV 2025 TorchTitan: One-stop PyTorch native solution for production ready LLM pretraining ICLR 2025 ChartMimic: Evaluating LMM's Cross-Modal Reasoning Capability via Chart-to-Code Generation ICLR 2025 Latency Robust Cooperative Perception using Asynchronous Feature Fusion WACV 2025 Chain-of-Reasoning: Towards Unified Mathematical Reasoning in Large Language Models via a Multi-Paradigm Perspective ACL 2025 From Allies to Adversaries: Manipulating LLM Tool-Calling through Adversarial Injection NAACL 2025 Vulnerability of Text-to-Image Models to Prompt Template Stealing: A Differential Evolution Approach ACL 2025 Understanding Individual Agent Importance in Multi-Agent System via Counterfactual Reasoning AAAI 2025 TrustUQA: A Trustful Framework for Unified Structured Data Question Answering AAAI 2025 Repairing Catastrophic-Neglect in Text-to-Image Diffusion Models via Attention-Guided Feature Enhancement EMNLP 2024 Play Guessing Game with LLM: Indirect Jailbreak Attack with Implicit Clues ACL 2024 GaussianEditor: Editing 3D Gaussians Delicately with Text Instructions CVPR 2024 GaussianDreamer: Fast Generation from Text to 3D Gaussians by Bridging 2D and 3D Diffusion Models CVPR 2024 ToolBeHonest: A Multi-level Hallucination Diagnostic Benchmark for Tool-Augmented Large Language Models EMNLP 2024 Learning to Plan for Retrieval-Augmented Large Language Models from Knowledge Graphs EMNLP 2024 HoLLMwood: Unleashing the Creativity of Large Language Models in Screenwriting via Role Playing EMNLP 2024 Vision Model Pre-training on Interleaved Image-Text Data via Latent Compression Learning NIPS 2024 Prompting Vision-Language Models for Dental Notation Aware Abnormality Detection MICCAI 2024 AdapterDistillation: Non-Destructive Task Composition with Knowledge Distillation EMNLP 2023 Solving Math Word Problems via Cooperative Reasoning induced Language Models ACL 2023 UniEX: An Effective and Efficient Framework for Unified Information Extraction via a Span-extractive Perspective ACL 2023 MAP: Multimodal Uncertainty-Aware Vision-Language Pre-Training Model CVPR 2023 Zero-Shot Learners for Natural Language Understanding via a Unified Multiple Choice Perspective EMNLP 2022 The 2020 Personalized Voice Trigger Challenge: Open Datasets, Evaluation Metrics, Baseline System and Results INTERSPEECH 2021 MIRTT: Learning Multimodal Interaction Representations from Trilinear Transformers for Visual Question Answering EMNLP 2021 Skeleton2Mesh: Kinematics Prior Injected Unsupervised Human Mesh Recovery ICCV 2021 Towards Alleviating the Modeling Ambiguity of Unsupervised Monocular 3D Human Pose Estimation ICCV 2021 Prediction of Crowd Flow in City Complex with Missing Data ACML 2019 The LeVoice Far-Field Speech Recognition System for VOiCES from a Distance Challenge 2019 INTERSPEECH 2019