Qingyu Shi

Identifiers

• name variant Qingyu Shi 0.60 · backfill

Papers (6)

1. Defending Against Malicious Finetuning by Scaling Train-time Adversarial Attacks cs.CL · 2026 · author #3
2. Mind-Omni: A Unified Multi-Task Framework for Brain-Vision-Language Modeling via Discrete Diffusion cs.AI · 2026 · author #3
3. Threshold-Guided Optimization for Visual Generative Models cs.LG · 2026 · author #3
4. Towards Customized Multimodal Role-Play cs.LG · 2026 · author #3
5. Prism: Efficient Test-Time Scaling via Hierarchical Search and Self-Verification for Discrete Diffusion Language Models cs.LG · 2026 · author #5
6. Muddit: Liberating Generation Beyond Text-to-Image with a Unified Discrete Diffusion Model cs.LG · 2025 · author #1

Mentions

• 2606.07970 #3 · arxiv_oai · confidence 0.70 Qingyu Shi
• 2605.29591 #3 · arxiv_oai · confidence 0.70 Qingyu Shi

Frequent Coauthors

• Jinbin Bai 3 shared papers
• Aosong Feng 2 shared papers
• Jianzong Wu 2 shared papers
• Kaidong Yu 2 shared papers
• Xiangtai Li 2 shared papers
• Yi Xin 2 shared papers
• Yunhai Tong 2 shared papers
• Zhuoran Zhao 2 shared papers
• Aixi Zhang 1 shared papers
• Changde Du 1 shared papers
• Chao Tang 1 shared papers
• Fei Shen 1 shared papers
• Hang Chen 1 shared papers
• Hao Jiang 1 shared papers
• Haoming Wen 1 shared papers
• Huiguang He 1 shared papers
• Jason Li 1 shared papers
• Jiangning Zhang 1 shared papers
• Jianru Xue 1 shared papers
• Jie Peng 1 shared papers