Scholar
Yan Ma
Google Scholar ID: tnJyAAoAAAAJ
Fudan University
Citations & Impact
Citations
261
H-index
8
i10-index
8
Publications
16
Co-authors
5
list available
Contact
Publications
Resume (English only)
Academic Achievements
- Publications: 'One RL to See Them All: Visual Triple Unified Reinforcement Learning' (May 2025), 'Rethinking RL Scaling for Vision Language Models' (Apr 2025), 'Thinking with Generated Images' (May 2025), 'Test Time Scaling Drives Cognition Engineering' (Apr 2025), 'Fine-Tuning Token-Based Large Multimodal Models' (ICLR 2025 Blogpost Track), 'OlympicArena' (NeurIPS 2024 Dataset & Benchmark Track), 'Weak-to-strong reasoning' (EMNLP 2024 Findings), 'ANOLE: An Open, Autoregressive, Native Large Multimodal Models for Interleaved Image-Text Generation' (Technical Report), 'MoPS: Modular Story Premise Synthesis for Open-Ended Automatic Story Generation' (ACL 2024), 'Evolutionary Action Selection' (ICONIP 2022 Oral).
Research Experience
- Internship experiences: MiniMax (vision-language reasoning models), Shanghai AI Laboratory (text generation and multimodal foundation models), Netease Games AI Laboratory (Game AI research); Current work: RL-based post-training for vision-language models.
Education
- Degree: Ph.D.; Institution: Fudan University; Advisors: Prof. Pengfei Liu, Prof. Yu Qiao; Time: Currently a second-year Ph.D. student; Major: Computer Science.
Background
- Research interests: intersection of reinforcement learning and foundation models; Field: Computer Science; Background: A second-year Ph.D. student from the Department of Computer Science at Fudan University, advised by Prof. Pengfei Liu and Prof. Yu Qiao.
Miscellany
- Personal interests: Not mentioned
