Shan Ning

PhD student, SIST, ShanghaiTech University

Joined

November 2022

Names

Shan Ning (Preferred)

Emails

****@shanghaitech.edu.cn (Confirmed)

Personal Links

Career & Education History

PhD student

SIST, ShanghaiTech University (shanghaitech.edu.cn)

2024 – Present

MS student

SIST, ShanghaiTech University (shanghaitech.edu.cn)

2022 – 2024

Undergrad student

SIST, ShanghaiTech University (shanghaitech.edu.cn)

2018 – 2022

Advisors, Relations & Conflicts

Coauthor

Jiaxuan Sun

Present

PhD Advisor

Xuming He

2022 – 2025

Coauthor

Longtian Qiu

2022 – 2025

Coauthor

Yongfei Liu

2021 – 2022

Expertise

Computer Vision

2022 – 2025

natural language processing

2022 – 2025

Publications

Wiki-R1: Incentivizing Multimodal Reasoning for Knowledge-based VQA via Data and Sampling Curriculum
Shan Ning, Longtian Qiu, Xuming He
- ICLR 2026 Poster
- Readers: Everyone
DA-DPO: Cost-efficient Difficulty-aware Preference Optimization for Reducing MLLM Hallucinations
Longtian Qiu, Shan Ning, Chuyu Zhang, Jiaxuan Sun, Xuming He
- Accepted by TMLR
- Readers: Everyone
NoisyGRPO: Incentivizing Multimodal CoT Reasoning via Noise Injection and Bayesian Estimation
Longtian Qiu, Shan Ning, Jiaxuan Sun, Xuming He
- NeurIPS 2025 poster
- Readers: Everyone
Training-Free Retrieval-Augmented Generation for Knowledge-Intensive Visual Question Answering
Shan Ning, Longtian Qiu, Jiaxuan Sun, Xuming He
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Mining Fine-Grained Image-Text Alignment for Zero-Shot Captioning via Text-Only Training
Longtian Qiu, Shan Ning, Xuming He
- AAAI 2024
- Readers: Everyone
HOICLIP: Efficient Knowledge Transfer for HOI Detection with Vision-Language Models
Shan Ning, Longtian Qiu, Yongfei Liu, Xuming He
- Published: 01 Jan 2023, Last Modified: 27 Apr 2023
- CoRR 2023
- Readers: Everyone

Shan Ning

Names

Emails

Personal Links

Career & Education History

Advisors, Relations & Conflicts

Expertise

Publications

Wiki-R1: Incentivizing Multimodal Reasoning for Knowledge-based VQA via Data and Sampling Curriculum

DA-DPO: Cost-efficient Difficulty-aware Preference Optimization for Reducing MLLM Hallucinations

NoisyGRPO: Incentivizing Multimodal CoT Reasoning via Noise Injection and Bayesian Estimation

Training-Free Retrieval-Augmented Generation for Knowledge-Intensive Visual Question Answering

Mining Fine-Grained Image-Text Alignment for Zero-Shot Captioning via Text-Only Training

HOICLIP: Efficient Knowledge Transfer for HOI Detection with Vision-Language Models

Co-Authors