Scholar
Ximing Li
Google Scholar ID: 2WQ--c4AAAAJ
Jilin university, China; RIKEN AIP, Japan
Weakly-supervised learning
Misinformation analysis
Follow
Google Scholar
↗
Citations & Impact
All-time
Citations
1,700
H-index
23
i10-index
49
Publications
20
Co-authors
1
list available
Publications
27 items
Estimating and Orthogonalizing Unknown Pre-training Gradients for Continual Fine-tuning of Large Language Models
2026
Cited
0
Factorize to Generalize: Retrieval-Guided Invariant-Dynamic Decomposition for Time Series Forecasting
2026
Cited
0
Backtracking When It Strays: Mitigating Dual Exposure Biases in LLM Reasoning Distillation
2026
Cited
0
Are Rationales Necessary and Sufficient? Tuning LLMs for Explainable Misinformation Detection
2026
Cited
0
Decomposing the Basic Abilities of Large Language Models: Mitigating Cross-Task Interference in Multi-Task Instruct-Tuning
2026
Cited
0
Improving Graph Few-shot Learning with Hyperbolic Space and Denoising Diffusion
2026
Cited
0
On the Step Length Confounding in LLM Reasoning Data Selection
2026
Cited
0
Generalizing Dynamics Modeling More Easily from Representation Perspective
2026
Cited
0
Load more
Co-authors
1 total
Yang Wang, 王杨
Hefei University of Technology
