Scholar
Yinhan He
Google Scholar ID: SMHk6PMAAAAJ
University of Virginia
Machine learning explainability and interpretability
Large Language Models
Graph Machine Learning
Follow
Google Scholar
↗
Citations & Impact
All-time
Citations
49
H-index
4
i10-index
1
Publications
15
Co-authors
8
list available
Publications
17 items
Adapting Context Compression for Long-Horizon Agents with Counterfactual Continuations
2026
Cited
0
S^3martCirc: Self-supervised Smart Circuit Discovery
2026
Cited
0
Every Token Leaves a Ripple in the Stream of Thought: Eliciting Model-Internal Token Saliency for Chain-of-Thought Compression
2026
Cited
0
Implicit Reasoning for Large Language Model-based Generative Recommendation
2026
Cited
0
Mult-DPO: Multinomial Direct Preference Optimization for Recommender Systems
2026
Cited
0
Mechanistic Circuit-Based Knowledge Editing in Large Language Models
2026
Cited
0
Wired for Overconfidence: A Mechanistic Perspective on Inflated Verbalized Confidence in LLMs
2026
Cited
0
Reforming the Mechanism: Editing Reasoning Patterns in LLMs with Circuit Reshaping
2026
Cited
0
Load more
Co-authors
8 total
Jundong Li
Associate Professor, University of Virginia
Song Wang
Assistant Professor, University of Central Florida
Yaochen Zhu
University of Virginia
Yushun Dong
Assistant Professor, Department of Computer Science, Florida State University
Binchi Zhang
University of Virginia
Jing Ma
Case Western Reserve University
Mengxuan Hu
The University of Virginia
Mucong Ding
Department of Computer Science, University of Maryland
