Scholar
Xiaotong Li
Google Scholar ID: cpCE_T4AAAAJ
Peking University
Multimodal LLM
Foundation Model
Transfer Learning
Follow
Google Scholar
↗
Citations & Impact
All-time
Citations
817
H-index
11
i10-index
11
Publications
16
Co-authors
7
list available
Publications
20 items
EgoExo-Next:Benchmarking Vision-Language Models on Visual-Option Next-State and Cross-View Reasoning
2026
Cited
0
DC-SAE: Deep Compression Semantic Autoencoder for Faster Diffusion Convergence
2026
Cited
0
Track2Art: Motion-Centric Articulated Object Model Recovery from 2D Point Trackers
2026
Cited
0
RouteGraph-Mona: Confusion-Aware Routing Fine-Tuning for Mineral Image Classification
2026
Cited
0
AutoDesign: Meta-Harness Optimization for Long-Horizon Agentic Design
2026
Cited
0
VideoCoCo: Code-as-CoT for Physically-Consistent Video Generation via an Agentic Dual-Engine System
2026
Cited
0
UMI-Bench 1.0: An Open and Reproducible Real-World Benchmark for Tabletop Robotic Manipulation with UMI Data
2026
Cited
0
Crafter: A Multi-Agent Harness for Editable Scientific Figure Generation from Diverse Inputs
2026
Cited
0
Load more
Co-authors
7 total
Ling-Yu Duan 段凌宇
Full Professor, School of Computer Science, Peking University
Yixiao Ge (葛艺潇)
XPENG Robotics
Jun Liu
Professor, Lancaster University
Ying Shan
Distinguished Scientist at Tencent, Director of ARC Lab & AI Lab CVC
Yongxing Dai 戴永兴
Baidu Inc.
Xinlong Wang
Beijing Academy of Artificial Intelligence
Haiwen Diao
Nanyang Technological University
