René's URL Explorer Experiment


Title: Xinyuan Wang (王新元) - Homepage

Open Graph Title: Xinyuan Wang (王新元)

Description: Xinyuan Wang is a PhD student at Fudan University researching multimodal large language models, post-training, AI safety, and computer vision.

Open Graph Description: Xinyuan Wang is a PhD student at Fudan University researching multimodal large language models, post-training, AI safety, and computer vision.

Mail addresses
buaa42wxy@gmail.com
buaa42wxy@gmail.com

Opengraph URL: https://dirtycomputer.github.io/

direct link

Domain: dirtycomputer.github.io

og:localeen
og:site_nameXinyuan Wang (王新元)
HandheldFriendlyTrue
MobileOptimized320
Noneon
msapplication-TileColor#000000
msapplication-TileImageimages/mstile-144x144.png?v=M44lzPylqQ
msapplication-configimages/browserconfig.xml?v=M44lzPylqQ
theme-color#ffffff

Links:

Homepagehttps://dirtycomputer.github.io#about-me
Newshttps://dirtycomputer.github.io/#news
Publicationshttps://dirtycomputer.github.io/#publications
Honors & Awardshttps://dirtycomputer.github.io/#honors-awards
Academic Servicehttps://dirtycomputer.github.io/#academic-service
Educationhttps://dirtycomputer.github.io/#education
Teachinghttps://dirtycomputer.github.io/#teaching
Invited Talkshttps://dirtycomputer.github.io/#invited-talks
Internshipshttps://dirtycomputer.github.io/#internships
Twitterhttps://twitter.com/buaa42wxy
LinkedInhttps://www.linkedin.com/in/xinyuan-wang-b3419a288
DBLPhttps://dblp.org/pid/81/3778-9.html
Githubhttps://github.com/dirtycomputer
Google Scholarhttps://scholar.google.com/citations?user=jQSagnIAAAAJ
ORCIDhttps://orcid.org/0009-0005-7577-1648
https://twitter.com/buaa42wxy
https://www.linkedin.com/in/xinyuan-wang-b3419a288
https://dblp.org/pid/81/3778-9.html
https://github.com/dirtycomputer
https://scholar.google.com/citations?user=jQSagnIAAAAJ
https://orcid.org/0009-0005-7577-1648
Xipeng Qiuhttps://scholar.google.com/citations?user=Pq4Yp_kAAAAJ&hl=en
https://scholar.google.com/citations?user=jQSagnIAAAAJ
TIKE was accepted to ACL 2026 Main (Long Paper)https://aclanthology.org/2026.acl-long.405/
BandPO was accepted to ICML 2026https://arxiv.org/abs/2603.04918
BandPOhttps://arxiv.org/abs/2603.04918
https://github.com/OpenMOSS/BandPO.git
DiffusionAttacker was accepted to EMNLP 2025https://arxiv.org/abs/2412.17522
DiffAtlas was accepted to MICCAI 2025 (Spotlight)https://arxiv.org/abs/2503.06748
https://github.com/HINTLab/DiffAtlas
LeFusion was accepted to ICLR 2025 (Spotlight)https://arxiv.org/abs/2403.14066
https://github.com/HINTLab/LeFusion
CVLabhttps://www.epfl.ch/labs/cvlab/
https://github.com/thu-coai/AISafetyLab
CoAIhttps://github.com/thu-coai
O2M_attack was accepted to AAAI 2025https://arxiv.org/abs/2405.20775
O2M_attackhttps://arxiv.org/abs/2405.20775
https://huggingface.co/datasets/MedMLLM-attack/3MAD-Tiny-1K
https://huggingface.co/datasets/MedMLLM-attack/3MAD-66K
O2M_attackhttps://arxiv.org/abs/2405.20775
https://github.com/dirtycomputer/O2M_attack
LightM-UNethttps://arxiv.org/abs/2403.05246.pdf
https://github.com/mrblankness/lightm-unet
BiPFT (accepted to AAAI 2024) was reported by BAAIhttps://mp.weixin.qq.com/s/ibBaWCdDcF2pA-Ug9XH1gQ
BiPFT was accepted to AAAI 2024https://arxiv.org/abs/2312.08937.pdf
https://github.com/Xingrun-Xing/BiPFT
Fseg was accepted to BIBM 2023https://ieeexplore.ieee.org/abstract/document/10386064
National Key R&D Program of Chinahttps://en.most.gov.cn/programmes1/200610/t20061009_36224.htm
TIKE: Efficient KL Divergence Estimation via Truncated Top-K Integration for Large Language Modelshttps://aclanthology.org/2026.acl-long.405/
Xinyuan Wanghttps://scholar.google.com/citations?user=jQSagnIAAAAJ
Luozhijie Jinhttps://scholar.google.com/citations?user=0Au6-0IAAAAJ&hl=zh-CN
Bo Wanghttps://scholar.google.com/citations?user=Q8xj86EAAAAJ&hl=zh-CN
Yuan Lihttps://scholar.google.com/citations?user=UmKOAF0AAAAJ
Zhangyue Yinhttps://scholar.google.com/citations?user=9gRQqSkAAAAJ
Xipeng Qiuhttps://scholar.google.com/citations?user=Pq4Yp_kAAAAJ&hl=en
Paperhttps://aclanthology.org/2026.acl-long.405/
Codehttps://github.com/jinluo12345/TIKE
BandPO: Bridging Trust Regions and Ratio Clipping via Probability-Aware Bounds for LLM Reinforcement Learninghttps://proceedings.mlr.press/v306/li26gm.html
Yuan Lihttps://scholar.google.com/citations?user=UmKOAF0AAAAJ
Bo Wanghttps://scholar.google.com/citations?user=Q8xj86EAAAAJ&hl=zh-CN
Yufei Gaohttps://scholar.google.com/citations?user=yUzpCD4AAAAJ&hl=zh-CN
Xinyuan Wanghttps://scholar.google.com/citations?user=jQSagnIAAAAJ
Zhangyue Yinhttps://scholar.google.com/citations?user=9gRQqSkAAAAJ
Xipeng Qiuhttps://scholar.google.com/citations?user=Pq4Yp_kAAAAJ&hl=en
Paperhttps://proceedings.mlr.press/v306/li26gm.html
arXivhttps://arxiv.org/abs/2603.04918
Codehttps://github.com/OpenMOSS/BandPO
DiffusionAttacker: Diffusion-Driven Prompt Manipulation for LLM Jailbreakhttps://aclanthology.org/2025.emnlp-main.1128/
Hao Wanghttps://scholar.google.com/citations?hl=en&user=LfbCou8AAAAJ
Hao Lihttps://scholar.google.com/citations?user=iZcvrH8AAAAJ&hl=en
Junda Zhuhttps://scholar.google.com/citations?user=NrsJYwkAAAAJ&hl=zh-CN
Xinyuan Wanghttps://scholar.google.com/citations?user=jQSagnIAAAAJ
Chengwei Panhttps://scholar.google.com/citations?user=7i1dqbEAAAAJ&hl=en
Minlie Huanghttps://scholar.google.com/citations?user=P1jPSzMAAAAJ&hl=zh-CN
Lei Shahttps://scholar.google.com/citations?user=EbZ_P6gAAAAJ&hl=zh-CN
Paperhttps://aclanthology.org/2025.emnlp-main.1128/
arXivhttps://arxiv.org/abs/2412.17522
DiffAtlas: GenAI-fying Atlas Segmentation via Image-Mask Diffusionhttps://papers.miccai.org/miccai-2025/0231-Paper0228.html
Hantao Zhanghttps://scholar.google.com/citations?hl=en&user=7RJH908AAAAJ
Jiancheng Yanghttps://jiancheng-yang.com/
Xinyuan Wanghttps://scholar.google.com/citations?user=jQSagnIAAAAJ
Wei Penghttps://scholar.google.com/citations?user=TDFM0QYAAAAJ&hl=zh-CN
Pascal Fuahttps://scholar.google.com/citations?user=kzFmAkYAAAAJ&hl=en
Paperhttps://papers.miccai.org/miccai-2025/0231-Paper0228.html
arXivhttps://arxiv.org/abs/2503.06748
Codehttps://github.com/HINTLab/DiffAtlas
Datasethttps://huggingface.co/datasets/YuheLiuu/DiffAtlas_Preprocessed_Data
AISafetyLab: A Comprehensive Framework for AI Safety Evaluation and Improvementhttps://arxiv.org/abs/2502.16776
Zhexin Zhanghttps://scholar.google.com/citations?user=I-Cn8gkAAAAJ&hl=zh-CN
Leqi Leihttps://scholar.google.com/citations?user=j65DJIEAAAAJ&hl=zh-CN
Junxiao Yanghttps://scholar.google.com/citations?user=8Zu6HocAAAAJ&hl=zh-CN
Xijie Huanghttps://scholar.google.com/citations?user=pL5W9z4AAAAJ&hl=en
Yida Luhttps://openreview.net/profile?id=~Yida_Lu1
Shiyao Cuihttps://scholar.google.com/citations?user=sVXAK-kAAAAJ&hl=zh-CN
Renmiao Chenhttps://openreview.net/profile?id=~Renmiao_Chen1
Xinyuan Wanghttps://scholar.google.com/citations?user=jQSagnIAAAAJ
Hao Wanghttps://scholar.google.com/citations?hl=en&user=LfbCou8AAAAJ
Hao Lihttps://scholar.google.com/citations?user=iZcvrH8AAAAJ&hl=en
Chengwei Panhttps://scholar.google.com/citations?user=7i1dqbEAAAAJ&hl=en
Lei Shahttps://scholar.google.com/citations?user=EbZ_P6gAAAAJ&hl=zh-CN
Hongning Wanghttps://scholar.google.com/citations?hl=en&user=qkdvKNoAAAAJ&view_op=list_works&sortby=pubdate
Minlie Huanghttps://scholar.google.com/citations?user=P1jPSzMAAAAJ&hl=zh-CN
arXivhttps://arxiv.org/abs/2502.16776
Codehttps://github.com/thu-coai/AISafetyLab
BlackDAN: A Black-Box Multi-Objective Approach for Effective and Contextual Jailbreaking of Large Language Modelshttps://arxiv.org/abs/2410.09804
Xinyuan Wanghttps://scholar.google.com/citations?user=jQSagnIAAAAJ
Victor Shea-Jay Huanghttps://scholar.google.com/citations?user=pL5W9z4AAAAJ&hl=en
Hao Wanghttps://scholar.google.com/citations?hl=en&user=LfbCou8AAAAJ
Chengwei Panhttps://scholar.google.com/citations?user=7i1dqbEAAAAJ&hl=en
Lei Shahttps://scholar.google.com/citations?user=EbZ_P6gAAAAJ&hl=zh-CN
Minlie Huanghttps://scholar.google.com/citations?user=P1jPSzMAAAAJ&hl=zh-CN
arXivhttps://arxiv.org/abs/2410.09804
LeFusion: Controllable Pathology Synthesis via Lesion-Focused Diffusion Modelshttps://proceedings.iclr.cc/paper_files/paper/2025/hash/233d16f17f809981763db2f01b7f9603-Abstract-Conference.html
Hantao Zhanghttps://scholar.google.com/citations?hl=en&user=7RJH908AAAAJ
Jiancheng Yanghttps://jiancheng-yang.com/
Shouhong Wanhttps://cs.ustc.edu.cn/2020/0906/c23239a460133/page.htm
Xinyuan Wanghttps://scholar.google.com/citations?user=jQSagnIAAAAJ
Wei Penghttps://scholar.google.com/citations?user=TDFM0QYAAAAJ&hl=zh-CN
Pascal Fuahttps://scholar.google.com/citations?user=kzFmAkYAAAAJ&hl=en
Paperhttps://proceedings.iclr.cc/paper_files/paper/2025/hash/233d16f17f809981763db2f01b7f9603-Abstract-Conference.html
arXivhttps://arxiv.org/abs/2403.14066
Codehttps://github.com/HINTLab/LeFusion
Medical MLLM is Vulnerable: Cross-Modality Jailbreak and Mismatched Attacks on Medical Multimodal Large Language Modelshttps://ojs.aaai.org/index.php/AAAI/article/view/32396
Xijie Huanghttps://github.com/JeixHuang
Xinyuan Wanghttps://scholar.google.com/citations?user=jQSagnIAAAAJ
Hantao Zhanghttps://scholar.google.com/citations?hl=en&user=7RJH908AAAAJ
Yinghao Zhuhttps://yhzhu99.github.io
Jingkun Anhttps://scholar.google.com/citations?hl=zh-CN&user=gtoavQoAAAAJ
Hao Wanghttps://scholar.google.com/citations?hl=en&user=LfbCou8AAAAJ
Hao Lianghttps://scholar.google.com/citations?hl=zh-CN&user=HgapY3sAAAAJ&view_op=list_works&sortby=pubdate
Chengwei Panhttps://scholar.google.com/citations?user=7i1dqbEAAAAJ&hl=en
Paperhttps://ojs.aaai.org/index.php/AAAI/article/view/32396
arXivhttps://arxiv.org/abs/2405.20775
Codehttps://github.com/dirtycomputer/O2M_attack
Dataset-1Khttps://huggingface.co/datasets/MedMLLM-attack/3MAD-Tiny-1K
Dataset-66Khttps://huggingface.co/datasets/MedMLLM-attack/3MAD-66K
LightM-UNet: Mamba Assists in Lightweight UNet for Medical Image Segmentationhttps://arxiv.org/abs/2403.05246
Weibin Liaohttps://scholar.google.com/citations?hl=zh-CN&user=4yUXvDsAAAAJ
Yinghao Zhuhttps://yhzhu99.github.io
Xinyuan Wanghttps://scholar.google.com/citations?user=jQSagnIAAAAJ
Chengwei Panhttps://scholar.google.com/citations?user=7i1dqbEAAAAJ&hl=en
Yasha Wanghttps://www.aminer.cn/profile/yasha-wang/542cc019dabfae4b91c24265
Liantao Mahttp://scholar.pku.edu.cn/malt
arXivhttps://arxiv.org/abs/2403.05246
Codehttps://github.com/MrBlankness/LightM-UNet
BiPFT: Binary Pre-trained Foundation Transformer with Low-rank Estimation of Binarization Residual Polynomialshttps://ojs.aaai.org/index.php/AAAI/article/view/29542
Xingrun Xinghttps://scholar.google.com.hk/citations?hl=zh-CN&user=sEdxu1UAAAAJ&view_op=list_works&sortby=pubdate
Li Duhttps://scholar.google.com.hk/citations?user=ag1JoOEAAAAJ&hl=zh-CN
Xinyuan Wanghttps://scholar.google.com/citations?user=jQSagnIAAAAJ
Yequan Wanghttps://www.wangyequan.com
Zheng Zhanghttps://scholar.google.com/citations?hl=zh-CN&user=S2bil1cAAAAJ&view_op=list_works&sortby=pubdate
Jiajun Zhanghttps://nlpr.ia.ac.cn/cip/jjzhang.htm
Paperhttps://ojs.aaai.org/index.php/AAAI/article/view/29542
arXivhttps://arxiv.org/abs/2312.08937
Codehttps://github.com/Xingrun-Xing/BiPFT
Leveraging Frequency Domain Learning in 3D Vessel Segmentationhttps://ieeexplore.ieee.org/abstract/document/10386064
Xinyuan Wanghttps://scholar.google.com/citations?user=jQSagnIAAAAJ
Chengwei Panhttps://scholar.google.com/citations?user=7i1dqbEAAAAJ&hl=en
Hongming Daihttps://www.linkedin.com/in/hongming-dai-76b936176/
Gangming Zhaohttps://scholar.google.com/citations?user=bRKA7fUAAAAJ&hl=en
Jinpeng Lihttps://scholar.google.com/citations?user=hzEaITAAAAAJ&hl=zh-CN
Yizhou Yuhttps://i.cs.hku.hk/~yzyu/
Paperhttps://ieeexplore.ieee.org/abstract/document/10386064
arXivhttps://arxiv.org/abs/2401.06224
AAAI 2025https://aaai.org/conference/aaai/aaai-25/
Student Union Presidenthttps://iai.buaa.edu.cn/info/1011/2924.htm
Silver Diplomahttps://mp.weixin.qq.com/s/EgRv-WxUEUq_sCSDsjBKgA
AAAI 2027https://aaai.org/conference/aaai/aaai-27/
ICLR 2027https://iclr.cc/Conferences/2027
ACL ARR 2026https://2026.aclweb.org/
ICLR 2026https://iclr.cc/Conferences/2026
AAAI 2026https://aaai.org/Conferences/AAAI-26/
ICME 2025https://2025.ieeeicme.org/
NeurIPS 2025https://neurips.cc/Conferences/2025
ICML 2025https://icml.cc/Conferences/2025
ICLR 2025https://iclr.cc/Conferences/2025
NeurIPS 2024https://neurips.cc/Conferences/2024
ACM MM 2024https://2024.acmmm.org/
Xipeng Qiuhttps://scholar.google.com/citations?user=Pq4Yp_kAAAAJ&hl=en
College of Computer Science and Artificial Intelligencehttps://cs.fudan.edu.cn/
Chengwei Panhttps://scholar.google.com/citations?user=7i1dqbEAAAAJ&hl=en
Institute of Artificial Intelligencehttps://iai.buaa.edu.cn/
Peng Caohttps://scholar.google.com/citations?user=0OfgZSsAAAAJ&hl=zh-CN
SII Summer School on Reinforcement Learning 2026https://www.sii.edu.cn/2026/0530/c60a1078/page.htm
Richard S. Suttonhttps://incompleteideas.net/
Shanghai Innovation Institutehttps://www.sii.edu.cn/
Openmind Research Institutehttps://www.openmindresearch.org/
Shanghai Jiao Tong University (SJTU)https://en.sjtu.edu.cn/
[Certificate]https://dirtycomputer.github.io/assets/files/summer_school_TA.pdf
Xuanjing Huanghttps://scholar.google.com/citations?user=RGsMgZA4H78C&hl=en
Chengwei Panhttps://scholar.google.com/citations?user=7i1dqbEAAAAJ&hl=en
HSBC Shanghaihttps://www.hsbc.com.cn/
Shoujing (Sherwin) Zhuhttps://www.linkedin.com/in/shoujing-z-114a4b212/
Torres (Haorong) Yaohttps://www.linkedin.com/in/torresyao/
IEEE BIBM 2023https://bidma.cpsc.ucalgary.ca/IEEE-BIBM-2023/documents/BIBM2023-Program-1208.pdf
TikTok Shophttps://shop.tiktok.com/
ByteDancehttps://www.bytedance.com/
Shanghai Innovation Institutehttps://www.sii.edu.cn/
Shanghai AI Laboratoryhttps://www.shlab.org.cn/
Chaochao Luhttps://causallu.com/bio/
Tsinghua Universityhttps://www.tsinghua.edu.cn/
Minlie Huanghttps://coai.cs.tsinghua.edu.cn/hml
Beijing Academy of Artificial Intelligence (BAAI)https://www.baai.ac.cn/
Xin Jianghttps://scholar.google.com/citations?user=3mqJwa8AAAAJ&hl=zh-CN
Yequan Wanghttps://www.wangyequan.com/
Hien Tranhttps://math.sciences.ncsu.edu/people/tran/
Peng Caohttps://scholar.google.com/citations?user=0OfgZSsAAAAJ&hl=zh-CN
Qidong Zhaohttps://scholar.google.com/citations?hl=zh-CN&user=cFAcguwAAAAJ&view_op=list_works&sortby=pubdate
Zhuoran Liuhttps://scholar.google.com/citations?user=tEyLvJQAAAAJ&hl=zh-CN
Changsheng Zhanghttps://dblp.org/pid/70/1079-1.html
Bin Zhanghttps://dblp.org/pid/13/5236-1.html

Viewport: width=device-width, initial-scale=1.0

URLs of crawlers that visited me.