UCAS / CASIA / BEIJING

Wulin Xie

Master’s student · Class of 2028

I am a master’s student in Pattern Recognition and Intelligent Systems at the University of Chinese Academy of Sciences and the Institute of Automation, Chinese Academy of Sciences.

My research focuses on LLM mid/post-training, agents, and multimodal reinforcement learning. I am interested in how models learn to reason, use tools, and connect understanding with generation.

I am currently a research intern at Meituan LongCat Interaction through the Beidou Talent Program, following research internships at Alibaba Amap and vivo.

Email ↗Google Scholar ↗GitHub ↗

300+Google Scholar citations

4Accepted first / co-first papers

3Industry research internships

As of Sep. 2026

01Research interests

Learning after pre-training

Mid-Training, SFT, reinforcement learning, and on-policy distillation for capable, reliable foundation models.

Agents that learn by doing

Tool use, long-horizon interaction, and efficient learning from multi-turn agent experience.

Understanding × generation

Unified multimodal evaluation, video understanding, visual reasoning, and preference alignment.

Recent highlights

2026VI-Bench accepted to NeurIPS 2026 as a first-author paper.
2026.04Joined Meituan LongCat Interaction through the Beidou Talent Program.
2026MME-Unify accepted to ICLR 2026 as a co-first-author paper.

02Selected publications

All on Scholar ↗

A selection of my work on learning, alignment, and evaluation. First / co-first-author work is highlighted.

NeurIPS 2026First author

VI-Bench: Benchmarking Prompt Inversion from AIGC Videos

Wulin Xie, Rui Zhao, Kecen Li, Xiujin Liu, Bokang Zhang, Zheng Liu, Xinwen Hou, Chen Gong

Can a model recover the prompt behind a generated video? A closed-loop benchmark with 900 verified videos and 18 VLMs connects video understanding to generation control.

Paper Code Dataset

ICLR 2026Co-first author

MME-Unify: A Comprehensive Benchmark for Unified Multimodal Understanding and Generation Models

Wulin Xie, Yi-Fan Zhang, Chaoyou Fu, Yang Shi, Bingyan Nie, Hongkai Chen, Zhang Zhang, Liang Wang, Tieniu Tan

Evaluating understanding and generation together: 4,104 examples across 30 subtasks reveal the gap between strong individual capabilities and truly unified multimodal reasoning.

Paper Project Code

AAAI 2027 · Under ReviewFirst author

Q-Hawkeye: Reliable Visual Policy Optimization for Image Quality Assessment

Wulin Xie, Rui Dai, Ruidong Ding, Kaikui Liu, Xiangxiang Chu, Xinwen Hou, Jie Wen

Making visual reinforcement learning more reliable with uncertainty-aware optimization and perceptual supervision. KADID PLCC / SRCC improves from 0.723 / 0.719 to 0.779 / 0.775 over VisualQuality-R1.

Paper Code

ICML 2025Core contributor

MM-RLHF: The Next Step Forward in Multimodal LLM Alignment

Yi-Fan Zhang, Tao Yu, Haochen Tian, Chaoyou Fu, Peiyan Li, Jianshu Zeng, Wulin Xie, et al.

Multimodal preference alignment with 120K human-annotated preference pairs, critique-based reward modeling, and dynamic preference optimization, evaluated on 27 benchmarks.

Paper Project

NeurIPS 2025Core contributor

MME-VideoOCR: Evaluating OCR-Based Capabilities of Multimodal LLMs in Video Scenarios

Yang Shi, Huanqian Wang, Wulin Xie, Huanyao Zhang, Lijie Zhao, Yi-Fan Zhang, et al.

Beyond reading a single frame: 2,000 human-annotated questions probe text recognition, cross-frame integration, and spatiotemporal reasoning in video.

Paper Project

WACV 2025 · OralFirst author

Multi-View Factorizing and Disentangling: A Novel Framework for Incomplete Multi-View Multi-Label Classification

Wulin Xie, Lian Zhao, Jiang Long, Xiaohuan Lu, Bingyan Nie

Learning shared and view-specific representations under missing views and labels. Evaluated against 10 methods on five datasets, with stronger average precision under 50% missingness.

Paper

ACM MM 2024First author

Uncertainty-Aware Pseudo-Labeling and Dual Graph Driven Network for Incomplete Multi-View Multi-Label Classification

Wulin Xie, Xiaohuan Lu, Yadong Liu, Jiang Long, Bob Zhang, Shuping Zhao, Jie Wen

Turning incomplete supervision into reliable learning signals through uncertainty-aware pseudo-labeling and label-guided dual graph constraints, validated on six datasets.

Paper Code

Additional research & journal articles

A Survey of Unified Multimodal Understanding and Generation: Advances and Challenges
Y. Yang, H. Tian, Y. Shi, Wulin Xie, et al. · TPAMI · Under Review
Confidence-Enhanced Dual-Space Semantic Alignment for Partial Multi-View Incomplete Multi-Label Classification
J. Chen, Wulin Xie, et al. · Knowledge-Based Systems
Cross-modal mapping: Mitigating the modality gap for few-shot classification
X. Yang, Wulin Xie, et al. · Pattern Recognition