Scholar
Weihong Lin
Google Scholar ID: Pb9wJ1sAAAAJ
Kuaishou
Vision Language Model
Computer Vision
Document Intelligence
Follow
Google Scholar
↗
Citations & Impact
All-time
Citations
1,294
H-index
8
i10-index
8
Publications
11
Co-authors
8
list available
Contact
No contact links provided.
Publications
11 items
CapRiCorn-1K: A Comprehensive Benchmark for Video Captioning and Subject Referential Consistency Across Temporal Scales
2026
Cited
0
RealClawBench: Live OpenClaw Benchmarks from Real Developer-Agent Sessions
2026
Cited
0
Beyond Parameter Arithmetic: Sparse Complementary Fusion for Distribution-Aware Model Merging
2026
Cited
0
Beyond Static Alignment: Hierarchical Policy Control for LLM Safety via Risk-Aware Chain-of-Thought
2026
Cited
0
DiaDem: Advancing Dialogue Descriptions in Audiovisual Video Captioning for Multimodal Large Language Models
2026
Cited
2
AVoCaDO: An Audiovisual Video Captioner Driven by Temporal Orchestration
2025
Cited
0
Uncertainty Under the Curve: A Sequence-Level Entropy Area Metric for Reasoning LLM
2025
Cited
0
Evaluation is All You Need: Strategic Overclaiming of LLM Reasoning Capabilities Through Evaluation Design
2025
Cited
0
Load more
Resume (English only)
Co-authors
8 total
Lei Sun
Microsoft Resarch Asia
Yuhui Yuan
Canva CORE, ex-Microsoft Research Asia
Jingdong Wang (王井东), Fellow of CAE & IEEE & IAPR
Baidu
Rao Fu
Brown University
Co-author 5
Kai Hu (胡凯)
University of Science and Technology of China
Jiawei Wang
University of Science and Technology of China
Han Hu
Distinguished Scientist, Tencent Hunyuan
