Yinpeng Dong
~Yinpeng_Dong2
14
论文总数
7.0
年均投稿
平均评分
接收情况8/14
会议分布
ICLR
8
NeurIPS
5
ICML
1
发表论文 (14 篇)
20255 篇
4
Towards Mitigating Factual Hallucination in LLMs through Self-Alignment with Memory
ICLR 2025withdrawn
4
Red-Teaming Text-to-Image Systems by Rule-based Preference Modeling
NeurIPS 2025Poster
4
Mitigating Overthinking in Large Reasoning Models via Manifold Steering
NeurIPS 2025Poster
4
Adaptive Strategy Evolution for Generating Tailored Jailbreak Prompts against Black-Box Safety-Aligned LLMs
ICLR 2025Rejected
4
STAIR: Improving Safety Alignment with Introspective Reasoning
ICML 2025Oral
20249 篇
4
Diffusion Models are Certifiably Robust Classifiers
NeurIPS 2024Poster
4
Improving Robustness of 3D Point Cloud Recognition from a Fourier Perspective
NeurIPS 2024Poster
3
Robust Classification via a Single Diffusion Model
ICLR 2024Rejected
4
DIFFender: Diffusion-Based Adversarial Defense against Patch Attacks
ICLR 2024withdrawn
4
Membership Inference on Text-to-Image Diffusion Models via Conditional Likelihood Discrepancy
NeurIPS 2024Poster
4
Rethinking Model Ensemble in Transfer-based Adversarial Attacks
ICLR 2024Poster
4
Evaluating the Robustness of Text-to-image Diffusion Models against Real-world Attacks
ICLR 2024Rejected
4
BSPA: Exploring Black-box Stealthy Prompt Attacks against Image Generators
ICLR 2024withdrawn
4
Embodied Active Defense: Leveraging Recurrent Feedback to Counter Adversarial Patches
ICLR 2024Poster