Chengzhi Mao

26 papers · 2019–2026 · 10 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

+11 more ↓

🗺️ Taxonomy Completionist (56) 🌍 Conference Polyglot · Gold 🏃 Academic Marathon · Sprint 🌉 Interdisciplinary Bridge · Bronze 🐣 Hot Topic Early Bird

🏆 Grand Slam 🧬 Topic Evolution 👑 Triple Crown 🧭 Keyword Pioneer 🤝 Dynamic Duo (16) 🚀 Conference Pioneer 🔥 Unstoppable · Bronze ⚡ Prolific Year · Productive 💎 Century Club · Bronze 🌈 Renaissance Researcher (5) 🗃️ Keyword Collector (137)

Venues

CVPR (7) ICLR (6) ICML (3) ACL (2) ICCV (2) NeurIPS (2) AAAI (1) ECCV (1) EMNLP (1) NAACL (1)

Top co-authors

Junfeng Yang (16) Carl Vondrick (15) Hao Wang (7) Wei Hao (3) Baishakhi Ray (3) Haozhe Chen (2) Ruoshi Liu (2) Mia Chiquier (2) Kexin Pei (2) Amogh Gupta (2)

Research topics

Artificial Intelligence (21) Core AI (21) Machine Learning (17) Deep Learning (11) Learning Types · Machine Learning (11) Application Areas (7) Models (6) Natural Language Processing (5) Learning Types · Deep Learning (5) Computer Vision (3) Analysis (3) Architectures (3) Core Methods (3) Optimization & Theory (3) Resources & Methods (3)

Keywords

adversarial attack (4) out-of-distribution generalization (3) model robustness (3) large language model (3) vision-language model (3) domain generalization (3) adversarial robustness (3) text rewriting (2) reinforcement learning (2) image classification (2) language model (2) adversarial defense (2) zero-shot learning (2) foundation model (2) adversarial training (2) visual recognition (2) representation learning (2) multimodal learning (2) spurious correlation (2) out of distribution (2)

Papers

Differences That Matter: Auditing Models for Capability Gap Discovery and Rectification CVPR 2026 R-C2: Cycle-Consistent Reinforcement Learning Improves Multimodal Reasoning CVPR 2026 Aligned but Blind: Alignment Increases Implicit Bias by Reducing Awareness of Race ACL 2025 Diversity Helps Jailbreak Large Language Models NAACL 2025 EditLord: Learning Code Transformation Rules for Code Editing ICML 2025 I Can Hear You: Selective Robust Training for Deepfake Audio Detection ICLR 2025 Learning to Rewrite: Generalized LLM-Generated Text Detection ACL 2025 ImageNet-D: Benchmarking Neural Network Robustness on Diffusion Synthetic Object CVPR 2024 INViTE: INterpret and Control Vision-Language Models with Text Explanations ICLR 2024 RAFT: Realistic Attacks to Fool Text Detectors EMNLP 2024 Raidar: geneRative AI Detection viA Rewriting ICLR 2024 SelfIE: Self-Interpretation of Large Language Model Embeddings ICML 2024 Convolutional Visual Prompt for Robust Visual Perception NeurIPS 2023 Doubly Right Object Recognition: A Why Prompt for Visual Rationales CVPR 2023 Landscape Learning for Neural Network Inversion ICCV 2023 Robust Perception through Equivariance ICML 2023 Understanding Zero-shot Adversarial Robustness for Large-Scale Models ICLR 2023 What You Can Reconstruct From a Shadow CVPR 2023 Causal Transportability for Visual Recognition CVPR 2022 Discrete Representations Strengthen Vision Transformer Robustness ICLR 2022 Real-Time Neural Voice Camouflage ICLR 2022 Adversarial Attacks Are Reversible With Natural Supervision ICCV 2021 Generative Interventions for Causal Learning CVPR 2021 Multitask Learning Strengthens Adversarial Robustness ECCV 2020 Bidirectional Inference Networks:A Class of Deep Bayesian Networks for Health Profiling AAAI 2019 Metric Learning for Adversarial Robustness NeurIPS 2019