Wenxuan Wang

57 papers · 2018–2026 · 14 conferences · across top CS/AI conferences

Achievements

🌍 Conference Polyglot (14) 🐝 Cross-Pollinator (13) 🐣 Hot Topic Early Bird 🏃 Academic Marathon (7) 🌈 Renaissance Researcher (5) 🌉 Interdisciplinary Bridge 🗺️ Taxonomy Completionist (11) 🧭 Keyword Pioneer 🤝 Dynamic Duo (21) 🏆 Grand Slam 🔬 Deep Specialist (13) 🧬 Topic Evolution 🔥 Unstoppable (6) ⚡ Prolific Year (5) ❓ The Questioner (3) 🗃️ Keyword Collector (261) 💎 Century Club (54) 🚀 Conference Pioneer

Conferences

ACL (14) EMNLP (10) CVPR (9) ICLR (5) AAAI (4) ICML (3) COLING (2) ECCV (2) NIPS (2) WACV (2) ICCV (1) IJCAI (1) INTERSPEECH (1) MIDL (1)

Top co-authors

Jen-tse Huang (21) Wenxiang Jiao (14) Youliang Yuan (14) Zhaopeng Tu (14) Michael Lyu (8) Pinjia He (7) Michael R. Lyu (6) Jing Liu (5) Chen Chen (5) Man Ho Lam (4)

Keywords

large language model (14) adversarial attack (9) adversarial example (5) benchmark evaluation (5) multimodal large language model (4) neural machine translation (4) black-box attack (4) jailbreak attack (3) vision-language model (3) data augmentation (3) prompt engineering (3) neural network (3) face recognition (3) semantic segmentation (2) instruction following (2) visual reasoning (2) medical image segmentation (2) attention mechanism (2) representation learning (2) knowledge distillation (2)

Papers

Probing Semantic Insensitivity for Inference-Time Backdoor Defense in Multimodal Large Language Model AAAI 2026

Mem-PAL: Towards Memory-based Personalized Dialogue Assistants for Long-term User-Agent Interaction AAAI 2026

ChartEditor: A Reinforcement Learning Framework for Robust Chart Editing AAAI 2026

Learning to Ask: When LLM Agents Meet Unclear Instruction EMNLP 2025

AI Sees Your Location—But With A Bias Toward The Wealthy World EMNLP 2025

EAGLE: Expert-Guided Self-Enhancement for Preference Alignment in Pathology Large Vision-Language Model ACL 2025

Can’t See the Forest for the Trees: Benchmarking Multimodal Safety Awareness for Multimodal LLMs ACL 2025

VisCRA: A Visual Chain Reasoning Attack for Jailbreaking Multimodal Large Language Models EMNLP 2025

ToolSafety: A Comprehensive Dataset for Enhancing Safety in LLM-Based Agent Tool Invocations EMNLP 2025

VisBias: Measuring Explicit and Implicit Social Biases in Vision Language Models EMNLP 2025

Insight Over Sight: Exploring the Vision-Knowledge Conflicts in Multimodal LLMs ACL 2025

Asclepius: A Spectrum Evaluation Benchmark for Medical Multi-Modal Large Language Models ACL 2025

QueryAttack: Jailbreaking Aligned Large Language Models Using Structured Non-natural Query Language ACL 2025

A Survey of LLM-based Agents in Medicine: How far are we from Baymax? ACL 2025

Chain-of-Jailbreak Attack for Image Generation Models via Step by Step Editing ACL 2025

IntentionESC: An Intention-Centered Framework for Enhancing Emotional Support in Dialogue Systems ACL 2025

NYA’s Offline Speech Translation System for IWSLT 2025 ACL 2025

LipsNet++: Unifying Filter and Controller into a Policy Network ICML 2025

On the Resilience of LLM-Based Multi-Agent Collaboration with Faulty Agents ICML 2025

Diffusion Feedback Helps CLIP See Better ICLR 2025

Competing Large Language Models in Multi-Agent Gaming Environments ICLR 2025

ODE-based Smoothing Neural Network for Reinforcement Learning Tasks ICLR 2025

Refuse Whenever You Feel Unsafe: Improving Safety in LLMs via Decoupled Refusal Training ACL 2025

Improving the Transferability of Adversarial Attacks on Face Recognition with Diverse Parameters Augmentation CVPR 2025

SeCap: Self-Calibrating and Adaptive Prompts for Cross-view Person Re-Identification in Aerial-Ground Networks CVPR 2025

EVEv2: Improved Baselines for Encoder-Free Vision-Language Models ICCV 2025

Where Fact Ends and Fairness Begins: Redefining AI Bias Evaluation through Cognitive Biases EMNLP 2025

GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via Cipher ICLR 2024

Apathetic or Empathetic? Evaluating LLMs' Emotional Alignments with Humans NIPS 2024

Not All Countries Celebrate Thanksgiving: On the Cultural Dominance in Large Language Models ACL 2024

Beyond Literal Descriptions: Understanding and Locating Open-World Objects Aligned with Human Intentions ACL 2024

All Languages Matter: On the Multilingual Safety of LLMs ACL 2024

Does ChatGPT Know That It Does Not Know? Evaluating the Black-Box Calibration of ChatGPT COLING 2024

Unveiling Parts Beyond Objects: Towards Finer-Granularity Referring Expression Segmentation CVPR 2024

Boosting Adversarial Transferability by Block Shuffle and Rotation CVPR 2024

LogicAsker: Evaluating and Improving the Logical Reasoning Ability of Large Language Models EMNLP 2024

On the Reliability of Psychological Scales on Large Language Models EMNLP 2024

On the Humanity of Conversational AI: Evaluating the Psychological Portrayal of LLMs ICLR 2024

Diffusion Actor-Critic with Entropy Regulator NIPS 2024

Med-Tuning: A New Parameter-Efficient Tuning Framework for Medical Volumetric Segmentation MIDL 2024

Med-DANet V2: A Flexible Dynamic Architecture for Efficient Medical Volumetric Segmentation WACV 2024

FreMIM: Fourier Transform Meets Masked Image Modeling for Medical Image Segmentation WACV 2024

Language-Routing Mixture of Experts for Multilingual and Code-Switching Speech Recognition INTERSPEECH 2023

ParroT: Translating during Chat using Large Language Models tuned with Human Translation and Feedback EMNLP 2023

LipsNet: A Smooth and Robust Neural Network with Adaptive Lipschitz Constant for High Accuracy Optimal Control ICML 2023

Improving the Transferability of Adversarial Samples by Path-Augmented Method CVPR 2023

Med-DANet: Dynamic Architecture Network for Efficient Medical Volumetric Segmentation ECCV 2022

Tencent’s Multilingual Machine Translation System for WMT22 Large-Scale African Languages EMNLP 2022

Understanding and Improving Sequence-to-Sequence Pretraining for Neural Machine Translation ACL 2022

DST: Dynamic Substitute Training for Data-Free Black-Box Attack CVPR 2022

Improving Adversarial Transferability via Neuron Attribution-Based Attacks CVPR 2022

Adv-Makeup: A New Imperceptible and Transferable Attack on Face Recognition IJCAI 2021

Delving into Data: Effectively Substitute Training for Black-box Attack CVPR 2021

Rethinking the Value of Transformer Components COLING 2020

FPETS: Fully Parallel End-to-End Text-to-Speech System AAAI 2020

FM2u-Net: Face Morphological Multi-Branch Network for Makeup-Invariant Face Verification CVPR 2020

Pose-Normalized Image Generation for Person Re-identification ECCV 2018