Author

Siyuan Li

Observed name: Li, Siyuan

Institutions: Harbin Institute of Technology, Westlake University, Shanghai Artificial Intelligence Laboratory, ByteDance (China), Zhejiang University, Tsinghua University

Observed institutions: Chongqing Technology and Business University, Harbin Institute of Technology, Westlake University, Shanghai Artificial Intelligence Laboratory, ByteDance (China), Zhejiang University, Tsinghua University

OpenAlex ID: A5136526827

A Survey on Mixup Augmentations and Beyond

2024 · Jin, Xin, Zhu, Hongyu, et al. · arXiv (Cornell University) · 7

MemForest: Efficient Agent Memory Management via EventTree Partitioning and Progressive Merging

2026 · Wang, Junxi, Sun, Te, et al. · arXiv (Cornell University)

Safe Task Planning with Long-Term Graph Memory for Embodied Agents

2026 · Li, Siyuan, Lang, Taiyan, et al. · arXiv (Cornell University)

Bridging Modal Isolation in Interleaved Thinking: Supervising Modality Transitions via Stepwise Reinforcement

2026 · Li, Tingyu, Zhou, Le, et al. · arXiv (Cornell University)

EndoVL: An expert annotated dataset of public gastrointestinal endoscopic images with uncertainty labels

2026 · Fu, Peiyao, Li, Siyuan, et al. · Figshare

RankE: End-to-End Post-Training for Discrete Text-to-Image Generation with Decoder Co-Evolution

2026 · Jian, Siyong, Li, Siyuan, et al. · arXiv (Cornell University)

Modality-Decoupled Online Recursive Editing

2026 · Li, Siyuan, Zhang, Youyuan, et al. · arXiv (Cornell University)

PAGER: Bridging the Semantic-Execution Gap in Point-Precise Geometric GUI Control

2026 · Wei, Jingxuan, Bai, Xi, et al. · arXiv (Cornell University)

The Trinity of Consistency as a Defining Principle for General World Models

2026 · Wei, Jingxuan, Li, Siyuan, et al. · arXiv (Cornell University)

Zooming without Zooming: Region-to-Image Distillation for Fine-Grained Multimodal Perception

2026 · Wei, Lai, He, Liangbo, et al. · arXiv (Cornell University)

Thinking with Drafting: Optical Decompression via Logical Reconstruction

2026 · Wei, Jingxuan, He, Honghao, et al. · arXiv (Cornell University)

Anchoring What Matters: A Dual-Level Learning Framework for Visually-Grounded Multimodal Reasoning

2026 · Xinxin Song, Siyuan Li, et al. · Conference on Empirical Methods in Natural Language Processing (EMNLP)

Works count: 12

Citation count: 7

H-index: 1

I10-index: