Liangwei Nathan Zheng

Orcid: 0009-0007-2793-8110

According to our database1, Liangwei Nathan Zheng authored at least 11 papers between 2023 and 2026.

Collaborative distances:
  • Dijkstra number2 of four.
  • Erdős number3 of four.

Timeline

Legend:

Book  In proceedings  Article  PhD thesis  Dataset  Other 

Links

Online presence:

On csauthors.net:

Bibliography

2026
Tackling Multimodal Learning Challenges with Mixture-of-Expert: A Survey.
CoRR, May, 2026

Lifting Manifolds to Mitigate Pseudo-Alignment in LLM4TS.
Proceedings of the ACM Web Conference 2026, 2026

2025
Rethinking Gating Mechanism in Sparse MoE: Handling Arbitrary Modality Inputs with Confidence-Guided Gate.
CoRR, May, 2025

Understanding Why Large Language Models Can Be Ineffective in Time Series Analysis: The Impact of Modality Alignment.
Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining, V.2, 2025

Adaptive Spline Networks in the Kolmogorov-Arnold Framework: Knot Analysis and Stability Enhancement.
Proceedings of the 34th ACM International Conference on Information and Knowledge Management, 2025

Price Equilibrium Routing: A Lightweight Framework for Expert Selection in Mixture-of-Experts.
Proceedings of the AI 2025: Advances in Artificial Intelligence, 2025

2024
Revisited Large Language Model for Time Series Analysis through Modality Alignment.
CoRR, 2024

Irregularity-Informed Time Series Analysis: Adaptive Modelling of Spatial and Temporal Dynamics.
Proceedings of the 33rd ACM International Conference on Information and Knowledge Management, 2024

Devil in the Tail: A Multi-Modal Framework for Drug-Drug Interaction Prediction in Long Tail Distinction.
Proceedings of the 33rd ACM International Conference on Information and Knowledge Management, 2024

Boosting Certificate Robustness for Time Series Classification with Efficient Self-Ensemble.
Proceedings of the 33rd ACM International Conference on Information and Knowledge Management, 2024

2023
SWAP: Exploiting Second-Ranked Logits for Adversarial Attacks on Time Series.
Proceedings of the IEEE International Conference on Knowledge Graph, 2023


  Loading...