MM-BrowseComp: A Comprehensive Benchmark for Multimodal Browsing Agents
Shilong Li*, Xingyuan Bu*, Wenjie Wang, Jiaheng Liu, et al. "MM-BrowseComp: A Comprehensive Benchmark for Multimodal Browsing Agents." arXiv 2025.
CV
Education
- M.S. in Artificial Intelligence, Beijing University of Posts and Telecommunications (BUPT), 2023 - 2026
- B.S. in Information Engineering, Beijing University of Posts and Telecommunications (BUPT), 2019 - 2023
Work experience
- 2024 - 2025: Research Intern
- ByteDance
- LLM and VLM research
- 2023 - 2024: Research Intern
- Didi
- 2022 - 2023: Research Intern
- Alibaba Group
Publications
Can Large Language Models Detect Errors in Long Chain-of-Thought Reasoning?
Yancheng He*, Shilong Li*, Jiaheng Liu*, et al. "Can Large Language Models Detect Errors in Long Chain-of-Thought Reasoning?" ACL 2025.
Chinese SimpleQA: A Chinese Factuality Evaluation for Large Language Models
Yancheng He*, Shilong Li*, Jiaheng Liu*, et al. "Chinese SimpleQA: A Chinese Factuality Evaluation for Large Language Models." ACL 2025.
2D-DPO: Scaling Direct Preference Optimization with 2-Dimensional Supervision
Shilong Li*, Yancheng He*, Hui Huang, et al. "2D-DPO: Scaling Direct Preference Optimization with 2-Dimensional Supervision." NAACL Findings 2025.
GraphReader: Building Graph-based Agent to Enhance Long-Context Abilities of Large Language Models
Shilong Li*, Yancheng He*, Hangyu Guo*, Xingyuan Bu*, et al. "GraphReader: Building Graph-based Agent to Enhance Long-Context Abilities of Large Language Models." EMNLP Findings 2024.
Fusion Makes Perfection: An Efficient Multi-Grained Matching Approach for Zero-Shot Relation Extraction
Shilong Li*, Ge Bai*, Zhang Zhang*, et al. "Fusion Makes Perfection: An Efficient Multi-Grained Matching Approach for Zero-Shot Relation Extraction." NAACL 2024.
Skills
- Research: Large Language Models, Vision-Language Models, Reinforcement Learning, NLP
- Programming: Python, PyTorch, Transformers, DeepSpeed
Languages
- Chinese (Native)
- English (Fluent)