Scholar

Yangyang Guo

Google Scholar ID: E4pqJ8wAAAAJ

National University of Singapore

vision-and-languageMLLM Safety

Citations & Impact

All-time

Citations

1,102

H-index

i10-index

Publications

Co-authors

list available

Contact

Publications

1 items

2026

Cited

Resume (English only)

Academic Achievements

Published 'The VLLM Safety Paradox: Dual Ease in Jailbreak Attack and Defense' at NeurIPS 2025 (CCF A)
Published 'Fair Deepfake Detectors Can Generalize' at NeurIPS 2025 (CCF A)
Published 'SCAN: Bootstrapping Contrastive Pre-training for Data Efficiency' at ICCV 2025 (CCF A)
Published 'Social Debiasing for Fair Multi-modal LLMs' at ICCV 2025 (CCF A)
Published 'Joint Vision-Language Social Bias Removal for CLIP' at CVPR 2025 (CCF A)
Published 'UNK-VQA: A Dataset and a Probe into the Abstention Ability of Multi-modal Large Models' in IEEE TPAMI 2024 (CCF A)
Published 'Diffusion Facial Forgery Detection' at ACM MM 2024 (CCF A)
Published 'PELA: Learning Parameter-Efficient Models with Low-Rank Approximation' at CVPR 2024 (CCF A)
Published 'Bilateral Adaptation for Human-Object Interaction Detection with Occlusion-Robustness' at CVPR 2024 (CCF A)
Published 'Voice-face Homogeneity Tells Deepfake' in ACM ToMM 2024 (CCF B)
Published 'Sample Less, Learn More: Efficient Action Recognition via Frame Feature Restoration' at ACM MM 2023 (CCF A)
Published 'Do Vision-Language Transformers Exhibit Visual Commonsense? An Empirical Study of VCR' at ACM MM 2023 (CCF A)
Published 'On Modality Bias Recognition and Reduction' in ACM ToMM 2023 (CCF B)

Co-authors

9 total