Dongsheng Xu

4 papers · 2023–2026 · 3 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 ↓

🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Silver 🗺️ Taxonomy Completionist (13)

Venues

CVPR (2) AAAI (1) ACL (1)

Top co-authors

Ruizhi Zhong (2) Xingxing Huang (2) Peizhi Zhao (2) Jiacheng Pi (2) Wenjie Ruan (2) Zhiguo Yang (2) Qingbao Huang (2) Wenye Zhao (2) Pijian Li (1) Yi Cai (1)

Research topics

Artificial Intelligence (3) Core AI (3) Computer Vision (2) Deep Learning (2) Learning Types · Deep Learning (2) Machine Learning (1) Natural Language Processing (1) Analysis (1) Applications (1) Core Methods (1) Generation (1) Learning Types · Machine Learning (1) Optimization & Theory (1)

Keywords

multimodal learning (2) neural network pruning (1) binary classification (1) backdoor defense (1) text generation (1) image captioning (1) cross-modal learning (1) referring expression (1) visual grounding (1) instance segmentation (1) safety alignment (1) backdoor attack (1) vision-language model (1) adversarial example (1) jailbreak attack (1) referring expression comprehension (1) channel pruning (1) cross-model transferability (1) sarcasm generation (1) point-based detection (1)

Papers

Jailbreaking Vision-Language Models via Dissonance-Guided Suffix Optimization and Image-Phrase Injection CVPR 2026 Logit-Margin Repulsion for Backdoor Defense CVPR 2026 Rethinking Two-Stage Referring Expression Comprehension: A Novel Grounding and Segmentation Method Modulated by Point AAAI 2024 Multi-modal Sarcasm Generation: Dataset and Solution ACL 2023