MF
Mingqian Feng
cs.CVcs.AIcs.CLcs.LGcs.HCeess.SP
On Valency
published · living versionsW_5tfddhs5·v1 · currentpublished
ShallowDefend: Harnessing Shallow Safety Alignment for Multi-Turn Defender
with Qiyao Ma, Xiaodong Liu, Weiwei Yang, Chengquan Guo +7
1 version
W_43ut8yvk·v1published
Preprints & journals
18 papers in the corpus · 2022–2026BVB: Benchmarking Agentic Video Understanding via Programmatic Reconstruction in Blender2609.15478v3 · Yolo Y. Tang, Daiki Shimada, Jiayue Meng et al.2026 · 0 citationsarXiv
MultiBreak: A Scalable and Diverse Multi-turn Jailbreak Benchmark for Evaluating LLM Safety2605.01687v1 · Jialin Song, Xiaodong Liu, Weiwei Yang et al.2026 · 1 citationarXiv
SEMA: Simple yet Effective Learning for Multi-Turn Jailbreak Attacks2602.06854v2 · Mingqian Feng, Xiaodong Liu, Weiwei Yang et al.2026 · 0 citationsarXiv
Statistical Estimation of Adversarial Risk in Large Language Models under Best-of-N Sampling2601.22636v2 · Mingqian Feng, Xiaodong Liu, Weiwei Yang et al.2026 · 0 citationsarXiv
VidComposition: Can MLLMs Analyze Compositions in Compiled Videos?40917926 · Tang, Yunlong, Guo, Junjia, Hua, Hang et al.2025 · 3 citationsProceedings. IEEE Computer Society Conference on Computer Vision and Pattern Recognition. 2025;2025:8490-8500
MMPerspective: Do MLLMs Understand Perspective? A Comprehensive Benchmark for Perspective Perception, Reasoning, and Robustness2505.20426v5 · Yolo Y. Tang, Pinxin Liu, Zhangyun Tan et al.2025 · 1 citationarXiv
Caption Anything in Video: Fine-grained Object-centric Captioning via Spatiotemporal Multimodal Prompting2504.05541v2 · Yunlong Tang, Jing Bi, Chao Huang et al.2025 · 1 citationarXiv
Forward Learning with Differential Privacy2504.00411v1 · Mingqian Feng, Zeliang Zhang, Jinyang Jiang et al.2025 · 0 citationsarXiv
Generative AI for Cel-Animation: A Survey2501.06250v5 · Yolo Y. Tang, Junjia Guo, Pinxin Liu et al.2025 · 10 citationsarXiv
Will the Inclusion of Generated Data Amplify Bias Across Generations in Future Image Classification Models?2410.10160v1 · Zeliang Zhang, Xin Liang, Mingqian Feng et al.2024 · 0 citationsarXiv
FLOPS: Forward Learning with OPtimal Sampling2410.05966v3 · Tao Ren, Zishi Zhang, Jinyang Jiang et al.2024 · 0 citationsarXiv
Can CLIP Count Stars? An Empirical Study on Quantity Bias in CLIP2409.15035v1 · Zeliang Zhang, Zhuo Liu, Mingqian Feng et al.2024 · 1 citationarXiv
Do More Details Always Introduce More Hallucinations in LVLM-based Image Captioning?2406.12663v1 · Mingqian Feng, Yunlong Tang, Zeliang Zhang et al.2024 · 1 citationarXiv
Empowering LLMs with Pseudo-Untrimmed Videos for Audio-Visual Temporal Understanding2403.16276v3 · Yolo Yunlong Tang, Daiki Shimada, Jing Bi et al.2024 · 9 citationsarXiv
Forward Learning for Gradient-based Black-box Saliency Map Generation2403.15603v2 · Zeliang Zhang, Mingqian Feng, Jinyang Jiang et al.2024 · 1 citationarXiv
Discover and Mitigate Multiple Biased Subgroups in Image Classifiers2403.12777v2 · Zeliang Zhang, Mingqian Feng, Zhiheng Li et al.2024 · 8 citationsarXiv
Video Understanding with Large Language Models: A Survey2312.17432v8 · Yolo Y. Tang, Jing Bi, Siting Xu et al.2023 · 117 citationsarXiv
cs-net: structural approach to time-series forecasting for high-dimensional feature space data with limited observations2212.02567v1 · Weiyu Zong, Mingqian Feng, Griffin Heyrich et al.2022 · 0 citationsarXiv
Career total: 20 works. 18 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.